@misc{cineagents2026,
  title = {{A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation}},
  author = {Zhang, Peixuan and Zhou, Chang and Zhang, Ziyuan and Liu, Hualuo and Zhang, Chunjie and Liu, Jingqi and Zhou, Xiaohui and Chen, Xi and Weng, Shuchen and Li, Si and Shi, Boxin},
  year = {2026},
  url = {https://arxiv.org/abs/2604.10456}
}

@misc{multimediaagent2026,
  title = {{A Versatile Multimodal Agent for Multimedia Content Generation}},
  author = {Zhang, Daoan and Yao, Wenlin and Wang, Xiaoyang and Hu, Yebowen and Luo, Jiebo and Yu, Dong},
  year = {2026},
  url = {https://arxiv.org/abs/2601.03250}
}

@misc{song2026a2rd,
  title = {{A\$^2\$RD: Agentic Autoregressive Diffusion for Long Video Consistency}},
  author = {Long, Do Xuan and Song, Yale and Kan, Min-Yen and Pfister, Tomas and Le, Long T.},
  year = {2026},
  url = {https://arxiv.org/abs/2605.06924}
}

@misc{jiang2026abotworld,
  title = {{ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU}},
  author = {Jiang, Fan and Sun, Zhaoxu and Wang, Mengchao and Zhu, Ziyu and Wang, Chiyu and Zhang, Yunpeng and Liu, Wenlin and Wang, Yun and Zheng, Xue and Sun, Rui and Ni, Junfeng and Pan, Hongyu and others},
  year = {2026},
  url = {https://arxiv.org/abs/2607.19191}
}

@misc{sam2026actionagent,
  title = {{Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion}},
  author = {Sam, Jeffrin and Khang, Nguyen and Mahmoud, Yara and Cabrera, Miguel Altamirano and Tsetserukou, Dzmitry},
  year = {2026},
  url = {https://arxiv.org/abs/2605.01477}
}

@misc{gao2026lingbotworld,
  title = {{Advancing Open-source World Models}},
  author = {Robbyant Team and Gao, Zelin and Wang, Qiuyu and Zeng, Yanhong and Zhu, Jiapeng and Cheng, Ka Leong and Li, Yixuan and Wang, Hanlin and Xu, Yinghao and Ma, Shuailei and Chen, Yihang and Liu, Jie and Cheng, Yansong and Yao, Yao and Zhu, Jiayi and Meng, Yihao and Zheng, Kecheng and Bai, Qingyan and Chen, Jingye and Shen, Zehong and Yu, Yue and Zhu, Xing and Shen, Yujun and Ouyang, Hao},
  year = {2026},
  url = {https://arxiv.org/abs/2601.20540}
}

@misc{chi2026agentgarten,
  title = {{AgentGarten: Code Worlds for Evolving Agents}},
  author = {Chi, Jiawei and Miao, Shangchen and Shi, Zhiyuan and Wu, Kailu and Wang, Hanyang and Chen, Weiliang and Dai, Qiyu and Li, Chengyang and Ren, Jinshan and Gao, Jun and Long, Mingsheng and Duan, Yueqi and Lyu, Jiangran and Wu, Jialong and Liu, Fangfu},
  year = {2026},
  url = {https://arxiv.org/abs/2610.12374}
}

@misc{wang2026artifactcreation,
  title = {{Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities}},
  author = {Wang, Tianfu and Hao, Zhezheng and Xia, Xilin and Liu, Lixin and Hu, Mengkang and Liu, Hongzhang and Chen, Xi and Liu, Ziyan and Lin, Xiankun and Zhang, Weijia and Yuan, Nicholas Jing and Xiong, Hui},
  year = {2026},
  url = {https://arxiv.org/abs/2608.28122}
}

@misc{zhang2025ace,
  title = {{Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models}},
  author = {Zhang, Qizheng and Hu, Changran and Upasani, Shubhangi and Ma, Boyuan and Hong, Fenglu and Kamanuru, Vamsidhar and Rainton, Jay and Wu, Chen and Ji, Mengmeng and Li, Hanchen and Thakker, Urmish and Zou, James and Olukotun, Kunle},
  year = {2026},
  url = {https://arxiv.org/abs/2510.04618}
}

@misc{xu2026ags,
  title = {{Agentic Generative Systems: A Survey on Autonomous Multimodal Content Creation}},
  author = {Xu, Xinli and Guo, Litao and Zhang, Yehang and Bai, Haotian and Lin, Jiantao and Feng, Jiawei and Wang, Luozhou and Yang, Zhen and Chen, Man and Zhang, Zixin and Chen, Harold Haodong and Min, Chen and Chen, Ying-Cong},
  year = {2026},
  url = {https://doi.org/10.20944/preprints202607.1997.v1}
}

@misc{deng2026agenticvideounderstanding,
  title = {{Agentic Video Understanding: A Survey}},
  author = {Deng, Xinyu and Luo, Siwen and Liu, Daochang},
  year = {2026},
  url = {https://arxiv.org/abs/2609.31713}
}

@misc{huang2026agenticvisual,
  title = {{Agentic Visual Generation: From Generative Models to Agentic Control}},
  author = {Huang, Yinming and Tu, Shuyuan and Yan, Xi and Zhan, Jiahao and Yang, Zihan and Xing, Zhen and Zhang, Hui and Zhang, Tiehua and Jiang, Yu-Gang and Wu, Zuxuan},
  year = {2026},
  url = {https://arxiv.org/abs/2609.06758}
}

@misc{chu2026agenticworldmodel,
  title = {{Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond}},
  author = {Chu, Meng and Zhang, Xuan Billy and Lin, Kevin Qinghong and Kong, Lingdong and Zhang, Jize and Tu, Teng and Ma, Weijian and Huang, Ziqi and Yang, Senqiao and others},
  year = {2026},
  url = {https://arxiv.org/abs/2604.22748}
}

@misc{agenticgen2026,
  title = {{AgenticGen: Reward-Guided Agentic Video Generation for Advertising}},
  author = {Bu, Xingyuan and Song, Chengru and Zhou, Hao and Zhou, Tao and Li, Dong and Li, Wei and Li, Shilong and Shi, Hao and Guo, Yongxin and Zhou, Donghao and Yang, Qiangpeng and Wen, Shilei},
  year = {2026},
  url = {https://arxiv.org/abs/2609.09187}
}

@misc{agentmv2026,
  title = {{AgentMV: A State-Guided Multi-Agent Framework for Budget-Aware Music Video Generation}},
  author = {Wang, Huimin and Xia, Chang and Ouyang, Leilei and Kang, Yongqi and Fu, Yu and Ouyang, Yuqi},
  year = {2026},
  url = {https://arxiv.org/abs/2605.10723}
}

@misc{sun2026agentslastexam,
  title = {{Agents' Last Exam}},
  author = {Sun, Yiyou and Han, Xinyang and Zhang, Weichen and Pang, Yuanbo and Wang, Tianyu and Cao, Yuhan and Huang, Yixiao and Duroiu, Chris and Zhang, Haoyun and Lin, Jeffrey and Zhang, Weishu and Zeng, Tyler and Yan, Ying and Liu, Bo and Wen, Hanson and Xu, Mingyang and Liu, Xiaoyuan and Chen, Zimeng and Shi, Weiyan and Dsouza, Amanda and Chen, Vincent Sunn and Bryant, Patrick and Boettiger, Carl and Rangan, Yamini and Rothenberg, Bradley and Steinfeld, Kyle and Rao, Arvind and Schneider, Tapio and Yannakakis, Georgios and Zanna, Laure and Ozbay, Kaan and Sim, Ida and Zohdi, Tarek and Karniadakis, George Em and Gallant, Jack and Head-Gordon, Teresa and Li, Yushan and Deng, Wenxi and Sun, Tao and Wang, Huiqi and Wang, Zhun and Xu, Justin and Liu, Chris Yuhao and Cheng, Yafei and Hu, Rongwang and Bacho, Aras and Cao, Shengcao and Qin, Zengyi and Chen, Yixiong and Fan, Hengduan and Liu, Hao and Zeng, Lin and Bharadwaj, Shashank Muralidhar and Gong, Litian and Yang, Yingxuan and Song, Maojia and Wang, Ruheng and Zhang, Zongzheng and Bao, Honglin and Lu, Shuo and Tu, Jianhong and Wang, Zhonghua and Zhang, Zheng and Chen, Zijiao and Jiang, Yanqiong and Li, Zhendong and Lyu, Bohan and Ma, Chang and Xu, Peiran and Zhang, Benran and Gu, Shangding and Hua, Haoyue and Li, Haoyang and Liao, Wanzhe and Liu, Chengzhi and Peng, Junbo and Sun, Haoran and Xu, Zechen and Chen, Bo and Cheng, Jiayi and Jiang, Yi and Kuang, Keying and Li, Yuan and Pan, Youbang and Rao, Ziyan and Schubert, Alexander and Shen, Yifan and Siu, Vincent and Sun, Xiatao and Zhang, Kangqi and Zhang, Xiaopan and Zhu, Yuchen and Chandok, Ishaan Singh and Ding, Lei and Fan, Jingxuan and Glover, Andrew and Hu, Jiaming and Hu, Yiran and Huang, Wenbo and Jiang, Zixin and Jin, Haoran and Kim, Lukas and Liu, Ming and Liu, Yang and Rafiei, Alireza and Shen, Xuhuan and Sun, Kunyang and Sun, Sophia and Sun, Ting and Wang, Eric and Wang, Yixin and Xing, Hanwen and Xu, Sihan and Xu, Yuzheng and Xu, Zhongxing and Yan, Zhiling and Yuan, Boqin and Zhang, Ruiqi and Zhang, Yifan and Zhao, Zibo and Liana and Antu, Santanu Bosu and Bai, Haoyue and Bosio, Carlo and Cavanagh, Joseph and Cavazos-Rehg, Patricia and Chen, Tianxing and Chen, Xuewen and Chen, Yipu and Zhu, Chenyu and Dai, Chen and De Castro, Stefano and Deng, Yunfu and Dhole, Kaustubh and Ding, Jiayuan and Du, Chenchen and Du, Zhehang and Fan, Hao and Fan, Run-Ze and Fu, Hengyu and Gu, Shi and Gu, Yifan and Guo, Charlie and Huang, Baihe and Huang, Baixiang and Jaiswal, Rimika and Jiang, Zhihan and Jin, Ran and Kasson, Erin and Lan, Xin and Lee, Joseph and Lei, Deren and Li, Chenyu and Li, Daofeng and Li, Haitao and Li, Hongwei and Li, Jingyan and Li, Xiao and Li, Yi and Li, Yinsheng and Li, Yuangang and Li, Zhixu and Liang, Wenyu and Liao, Longtai and Lin, Kevin Qinghong and Liu, Andy Zeyi and Liu, Che and Liu, Jiaming and Liu, Kaiyuan and Liu, Xuan and Lu, Pan and Lv, Wenbo and Lyu, Yicheng and Mang, Qiuyang and Montgomery, Kyle and Nie, Yuzhou and Ning, Ruoxi and Overwiening, Jorin and Pan, Xu and Paraboschi, Layna and Park, Core Francisco and Purnomo, Justin and Rajwal, Swati and Rankin, Scott and Ren, Bixuan and Rong, Yiren and Shang, HaoYang and Shaw, Ventus and Shen, Fiona and Shen, Jiawei and Shi, Minqi and Qiu, Shi and Yao, Huaxiu and Shi, Tianneng and So, Jonah and Susoy, Vladislav and Szlyk, Hannah and Wang, Haocheng and Wang, Jialu and Wang, Wei and Wang, Xinyu and Wang, Zehao and Wong, Dowling and Wu, Angela and Wu, Dehao and Wu, Fangyu and Wu, Mengyuan "Millie" and Wu, Yu and Wu, Yuchen and Wu, Yuhao and Wuwu, Qingpo and Xiao, Weihang and Xiong, Yongyi and Xu, Fan and Xu, Ruiling and Yan, Mingxuan and Yang, Benjamin and Yang, Jirong and Yang, Sen and Yang, Xiaoli and Yang, Yushi and Ye, Haoran and Yu, Xiaohu and Yu, Zhengming and Zhang, Chenlong and Zhang, Chi and Zhang, Hanning and Zhang, Hanwen and Zhang, Junge and Zhang, Kunpeng and Zhang, Song and Zhang, Wenjin and Zhang, Wenshuo and Zhang, Ying and Zhang, Yizhi and Zhao, Brian and Zhao, Qijian and Zhao, Yimin and Zheng, Yuhaohua and Zhou, Liwei and Zhou, Tianyue and Zhu, Sichen and Zhu, Siqi and Zhu, Yan and Zhu, Yishu and Zuo, Jierui and Cai, Chonghao and Casademunt, Helena and Chen, Wenjia and Cheng, Cheng and Deng, Nawen and Fu, Rao and Fu, Tianfu and Han, Yifan and Ren, He and He, Zhenyu and Jin, Qiao and Li, Langlang and Li, Yuetai and Liu, Sylvia and Lu, Lu and Zhou, Luqing and Mukherjee, Subhabrata and Ouyang, Yunqi and Ren, Yin and Shi, Dawei and Wu, Haoran and Wu, Zhiyue and Yao, Hannah and Yi, Zhuoran and Yu, Jenny and Zhan, Rhea and Zhou, Hang and Zhu, Blake and Zhu, Junfan and Yuille, Alan and Liu, Yang and Poldrack, Russell Alan and Li, Jiachen and Li, Zhenglu and Tao, Molei and Huang, Jing and Shi, Wenqi and Spanos, Costas and Sun, Lichao and Wang, Chenguang and Xu, Orson and Dong, Zhen and Gomez, Hector and Caliskan, Aylin and Emami, Ali and Hu, Haimin and Li, Zhi and Liu, Lihui and Niu, Murphy and Shao, Yi and Sun, Jianxin and Tolonen, Mikko and Wang, Ting and Das, Sanjiv and Gao, Yanjun and Guo, Wenbo and Schneider, Erika J and Lu, Zhiyong and Ma, Yian and Mueller, Mark and Poovendran, Radha and Sojoudi, Somayeh and Zhu, Yinglun and Song, Dawn},
  year = {2026},
  url = {https://arxiv.org/abs/2606.05405}
}

@misc{gu2026anyflow,
  title = {{AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation}},
  author = {Gu, Yuchao and Fang, Guian and Jiang, Yuxin and Mao, Weijia and Han, Song and Cai, Han and Shou, Mike Zheng},
  year = {2026},
  url = {https://arxiv.org/abs/2605.13724}
}

@misc{jeon2026atvg,
  title = {{ATVG: Agentic System for Factually Grounded Travel Advertisement Video Generation}},
  author = {Byung Eun Jeon and Xiao Bai and Wen Zhang and Jinchao Li},
  year = {2026},
  url = {https://doi.org/10.1145/3805712.3808387}
}

@misc{aurora2026,
  title = {{Aurora: Unified Video Editing with a Tool-Using Agent}},
  author = {Yu, Yongsheng and Zeng, Ziyun and Xiao, Zhiyuan and Zhou, Zhenghong and Hua, Hang and Xiong, Wei and Luo, Jiebo},
  year = {2026},
  url = {https://arxiv.org/abs/2605.18748}
}

@misc{gestagent2026,
  title = {{Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios}},
  author = {Cudlenco, Nicolae and Masala, Mihai and Leordeanu, Marius},
  year = {2026},
  url = {https://arxiv.org/abs/2604.10383}
}

@misc{karpathy2026autoresearch,
  title = {{autoresearch}},
  author = {Karpathy, Andrej},
  year = {2026},
  url = {https://github.com/karpathy/autoresearch}
}

@misc{li2026avaencoder,
  title = {{AVA-Encoder: Towards Agent-Native Video Representation Learning}},
  author = {Chuyue Li and Jinpeng Yu and Haozhe Wang and Tian Xueyun and Zhijing Zhang and Bingnan Li and Shuqi Gu and Kan Ren and Jiaming Liu and Ruihua Huang},
  year = {2026},
  url = {https://arxiv.org/abs/2608.12313}
}

@misc{zhou2026avgenbench,
  title = {{AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation}},
  author = {Zhou, Ziwei and Lai, Zeyuan and Wang, Rui and Yang, Yifan and Xing, Zhen and Yang, Yuqing and Dai, Qi and Qiu, Lili and Luo, Chong},
  year = {2026},
  url = {https://arxiv.org/abs/2604.08540}
}

@misc{chen2026cinecrew,
  title = {{Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation}},
  author = {Chen, Jiaben and Dong, Sixun and Zhou, Qinhong and Ma, Raine and Dou, Zhiyang and Matusik, Wojciech and Gan, Chuang},
  year = {2026},
  url = {https://arxiv.org/abs/2609.07720}
}

@misc{zeng2026cutcraft,
  title = {{Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation}},
  author = {Zeng, Tianyi and Liao, Junchao and Wei, Yujie and Zhang, Ziying and Li, Litao and Wang, Tianyi and Wei, Zhichao and Xu, Shuyao and Qiang, Wenwen and Zhu, Siyu and Zhang, Zhenghao and Qin, Long},
  year = {2026},
  url = {https://arxiv.org/abs/2609.08275}
}

@misc{beyondendtoend2026,
  title = {{Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation}},
  author = {Yan, Lingyong and Wu, Jiulong and Xie, Dong and Shi, Weixian and Xia, Deguo and Huang, Jizhou},
  year = {2026},
  url = {https://doi.org/10.1145/3770855.3818323}
}

@misc{beyondtrial2026,
  title = {{Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence}},
  author = {Tyagi, Aman and Boinpally, Hemanth and Chen, Jonathan and Gebert, Douglas and Hickson, Steven},
  year = {2026},
  url = {https://arxiv.org/abs/2608.12290}
}

@misc{chief2026,
  title = {{Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops}},
  author = {Savytski, Denis and Lei, Aiden and Liu, Heding and Yang, Warren and Liang, Sihan and Liu, Alexander and Zhao, Zhe},
  year = {2026},
  url = {https://arxiv.org/abs/2606.18591}
}

@misc{cameraartist2026,
  title = {{Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generation}},
  author = {Hu, Haobo and Mao, Qi and Li, Yuanhang and Jin, Libiao},
  year = {2026},
  url = {https://arxiv.org/abs/2604.09195}
}

@misc{campilot2026,
  title = {{CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation}},
  author = {Wu, Yang and Petrangeli, Stefano and Dasgupta, Ishita and Shen, Yu},
  year = {2026},
  url = {https://arxiv.org/abs/2609.10943}
}

@misc{mondal2026canvas,
  title = {{CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding}},
  author = {Mondal, Ishani and Song, Yiwen and Parmar, Mihir and Goyal, Palash and Boyd-Graber, Jordan and Pfister, Tomas and Song, Yale},
  year = {2026},
  url = {https://arxiv.org/abs/2604.13452}
}

@misc{zhu2026causal,
  title = {{Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation}},
  author = {Zhu, Hongzhou and Zhao, Min and He, Guande and Su, Hang and Li, Chongxuan and Zhu, Jun},
  year = {2026},
  url = {https://arxiv.org/abs/2602.02214}
}

@misc{cineagi2026,
  title = {{CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration}},
  author = {Xie, Tianyidan and Huang, Zhentao and Wang, Mingjie and Huang, Xin and Zhou, Jun and Gong, Minglun and Yi, Zili},
  year = {2026},
  url = {https://arxiv.org/abs/2604.23579}
}

@misc{cineforge2026,
  title = {{CineForge: Self-Improving Agents for Long-Horizon Video Generation}},
  author = {Liu, Junxiang and Wang, Lin and Shi, Haiyu and Ma, Hongxu and Yang, Xiaoyu and Chen, Chunjie and Xu, Xiaoxiao and Zhan, Kaiqiao and Wang, Boao and Shi, Shuizhou and Zhu, Tianyun and Li, Jie and Li, Jiangtong},
  year = {2026},
  url = {https://arxiv.org/abs/2608.29621}
}

@misc{codirector2026,
  title = {{Co-Director: Agentic Generative Video Storytelling}},
  author = {Song, Yale and Song, Yiwen and Losier, Nick and Hodson, Nathan and Jin, Ye and Zhu, Rhyard and Xu, Yan and Vlasic, Daniel and Claassen, Carina and Leon, Jasmine and LeViet, Khanh G. and Chomyn, Zack and Timmons, Joe and Slatkin, Brett and Penberthy, Scott and Pfister, Tomas},
  year = {2026},
  url = {https://arxiv.org/abs/2604.24842}
}

@misc{gomeznogales2026coarsetoreal,
  title = {{Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes}},
  author = {Gomez-Nogales, Gonzalo and Hong, Yicong and Ge, Chongjian and Zhuang, Peiye and Comino-Trinidad, Marc and Casas, Dan and Zhou, Yi},
  year = {2026},
  url = {https://arxiv.org/abs/2601.22301}
}

@misc{ning2026code,
  title = {{Code as Agent Harness}},
  author = {Ning, Xuying and Tieu, Katherine and Fu, Dongqi and Wei, Tianxin and Li, Zihao and Bei, Yuanchen and Zou, Jiaru and Ai, Mengting and Liu, Zhining and Li, Ting-Wei and others},
  year = {2026},
  url = {https://arxiv.org/abs/2605.18747}
}

@misc{liang2026codevideomodel,
  title = {{Code Video Model: Conditioning Video Generation on Code}},
  author = {Liang, Zhiyang and Zhang, Jiawei and Qian, Guocheng and Chen, Dongdong and Wan, Ziyu},
  year = {2026},
  url = {https://doi.org/10.13140/RG.2.2.34014.80961}
}

@misc{chen2026cwm,
  title = {{Code World Model: Coding Agent as World Brain}},
  author = {Chen, Yiwen and Lin, Guosheng and Zhang, Chi},
  year = {2026},
  url = {https://arxiv.org/abs/2608.25927}
}

@misc{code2video2026,
  title = {{Code2Video: A Code-centric Paradigm for Educational Video Creation}},
  author = {Chen, Yanzhe and Lin, Kevin Qinghong and Shou, Mike Zheng},
  year = {2026},
  url = {https://icml.cc/virtual/2026/poster/65050}
}

@misc{cogenpvg2026,
  title = {{CogenPVG: Cognitive-Enhanced Reflective Multi-Agent Framework for Persuasive Video Generation}},
  author = {Xiao, Yuntian and Zhang, Shoulong and Song, Wenfeng and Wang, Yan and Chen, Yi and Li, Shuai},
  year = {2026},
  url = {https://arxiv.org/abs/2609.25821}
}

@misc{c2pa2026,
  title = {{Content Credentials: C2PA Technical Specification}},
  author = {Coalition for Content Provenance and Authenticity},
  year = {2026},
  url = {https://spec.c2pa.org/specifications/specifications/2.4/specs/C2PA_Specification.html}
}

@misc{yan2026grpb,
  title = {{Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation}},
  author = {Yan, Lecheng and Lin, Jianze and Zhang, Yichong and Pan, Ben and Li, Wenxi and Lyu, Chenyang and Zhou, Liting and Gurrin, Cathal},
  year = {2026},
  url = {https://arxiv.org/abs/2608.02694}
}

@misc{crayotter2026,
  title = {{Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing}},
  author = {Yan, Lecheng and Zhang, Yichong and Xu, Xiantao and Lin, Jianze and Pan, Ben and Zheng, Xiaoyu and Qian, Jiawei and Wu, Anqi and Geng, Jiahui and Li, Ruizhe and Cai, Fengyu and Niu, Jingcheng and Li, Raymond and Li, Wenxi and Lyu, Chenyang},
  year = {2026},
  url = {https://arxiv.org/abs/2606.07636}
}

@misc{zhao2026cutclaw,
  title = {{CutClaw: Agentic Hours-Long Video Editing via Music Synchronization}},
  author = {Zhao, Shifang and Hu, Yihan and Shan, Ying and Wei, Yunchao and Cun, Xiaodong},
  year = {2026},
  url = {https://arxiv.org/abs/2603.29664}
}

@misc{cutsceneagent2026,
  title = {{Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation}},
  author = {He, Lanshan and Pang, Haozhou and Gan, Qi and Shen, Xin and Zhang, Ziwei and Liu, Yibo and Fang, Gang and Liu, Bo and Sheng, Kai and Zeng, Shengfeng and Li, Chaofan and Hui, Zhen and Zhou, Keer and Zhou, Lan and Dai, Shujun},
  year = {2026},
  url = {https://arxiv.org/abs/2604.25318}
}

@misc{hu2026cutverse,
  title = {{CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing}},
  author = {Hu, Haobo and Guo, Xiangwu and Chen, Zhiheng and Gao, Difei and Liu, Haotian and Jin, Libiao and Mao, Qi},
  year = {2026},
  url = {https://arxiv.org/abs/2605.19484}
}

@misc{zhang2025dgm,
  title = {{Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents}},
  author = {Zhang, Jenny and Hu, Shengran and Lu, Cong and Lange, Robert and Clune, Jeff},
  year = {2026},
  url = {https://arxiv.org/abs/2505.22954}
}

@misc{datamagic2026,
  title = {{DataMagic: Transforming Tabular Data into Data Insight Video}},
  author = {Xie, Yupeng and Ma, Chen and Wang, Zhenyang and Wang, Liangwei and Zhu, Jiayi and Zeng, Chuxuan and Shen, Zhouan and Li, Boyan and Luo, Yuyu},
  year = {2026},
  url = {https://arxiv.org/abs/2606.20388}
}

@misc{deeppresenter2026,
  title = {{DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation}},
  author = {Hao Zheng and Guozhao Mo and Xinru Yan and Qianhao Yuan and Wenkai Zhang and Xuanang Chen and Yaojie Lu and Hongyu Lin and Xianpei Han and Le Sun},
  year = {2026},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1578}
}

@misc{direct2026,
  title = {{DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing}},
  author = {Li, Ke and Li, Maoliang and Chen, Jialiang and Chen, Jiayu and Zheng, Zihao and Wang, Shaoqi and Chen, Xiang},
  year = {2026},
  url = {https://arxiv.org/abs/2604.04875}
}

@misc{chen2026directorbench,
  title = {{DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation}},
  author = {Jiamin Chen and Qianben Chen and Jiawen Zhang and Yidi Wu and Yuchen Li and Xiaokun Zhang and Wangchunshu Zhou and Chen Ma},
  year = {2026},
  url = {https://arxiv.org/abs/2605.30090}
}

@misc{dppgrpo2025,
  title = {{Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization}},
  author = {Kazimi, Tahira and Dunlop, Connor and Yanardag, Pinar},
  year = {2026},
  url = {https://arxiv.org/abs/2511.20647}
}

@misc{miao2026statebench,
  title = {{Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation}},
  author = {Miao, Yingmao and Zhang, Pengfei and Xu, Chaoran and Yu, Meng and Tang, Jing and Chu, Xiangxiang and Shen, Chao and Lin, Chenhao},
  year = {2026},
  url = {https://arxiv.org/abs/2609.03673}
}

@misc{xu2026dontreadlog,
  title = {{Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents}},
  author = {Xu, Jian},
  year = {2026},
  url = {https://arxiv.org/abs/2609.28564}
}

@misc{zhou2026dramadirector,
  title = {{DramaDirector: Geometry-Guided Short Drama Generation}},
  author = {Zhou, Hengji and Liu, Sijie and Chen, Jianrun and Zou, Xingchen and Xia, Lianghao and Nie, Liqiang},
  year = {2026},
  url = {https://arxiv.org/abs/2606.24107}
}

@misc{yang2026dualipo,
  title = {{Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation}},
  author = {Yang, Xiaomeng and Yang, Mengping and Gong, Jia and Qin, Luozheng and Tan, Zhiyu and Li, Hao},
  year = {2026},
  url = {https://arxiv.org/abs/2502.02088}
}

@misc{vast2026edenlive,
  title = {{EdenLive: Real-Time Generative Rendering from Any Visual Reference}},
  author = {Huang, Zehuan and Xu, Tian-Xing and Peng, Chunli and Zhang, Cheng and Zheng, Zeyi and Song, Yifei and Gu, Zekai and Yu, Zhipeng and Wang, Peng and Cao, Yan-Pei},
  year = {2026},
  url = {https://assets.vast-eden.ai/assets/edenlive/EdenLive-tech-report.pdf}
}

@misc{ellmpeg2026,
  title = {{ELLMPEG: An Edge-based Agentic LLM Video Processing Tool}},
  author = {Zoha Azimi and Reza Farahani and Radu Prodan and Christian Timmerer},
  year = {2026},
  url = {https://doi.org/10.1145/3793853.3795760}
}

@misc{vandersanden2026emvid,
  title = {{EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation}},
  author = {Vandersanden, Jente and Gadelha, Matheus and Huang, Chun-Hao P. and Jeong, Hyeonho and Gryaditskaya, Yulia},
  year = {2026},
  url = {https://arxiv.org/abs/2605.23610}
}

@misc{yang2026evalverse,
  title = {{EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation}},
  author = {Yang, Songlin and Zhong, Haobin and Zhang, Ruilin and Zhao, Xiaotong and Li, Shuai and Zheng, Kai and Yang, Xuyi and Wang, Zhe and Tang, Zhenchen and Li, Yang and Gu, Bohai and Peng, Zhengwei and Huang, Yidan and Luo, Mengzhou and Bo, Yihang and Feng, Dalu and Zhang, Yujia and Ma, Juntao and Wang, Ruiqi and Zhang, Lvmin and Guo, Yuwei and Guan, Frank and Agrawala, Maneesh and Fu, Hongbo and Zhao, Alan and Rao, Anyi},
  year = {2026},
  url = {https://arxiv.org/abs/2605.23271}
}

@misc{huang2026evobench,
  title = {{Evo-Bench: Can Language Models Improve Agent Harness?}},
  author = {Huang, Lisheng and Yang, Chen and Zhou, Hao and Song, Huatong and Chen, Zongchao and Le, Ran and Song, Yang and Zhao, Wayne Xin and Zhang, Tao},
  year = {2026},
  url = {https://arxiv.org/abs/2608.09096}
}

@misc{wei2026evoharness,
  title = {{Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents}},
  author = {Wei, Tianxin and Shi, Zhan and Lin, Minhua and He, Bing and Liu, Zewen and Sang, Yisi and Bei, Yuanchen and Ning, Xuying and Zou, Jiaru and Li, Ting-Wei and Lin, Xiao and Zhao, Yanjun and Wang, Chi and Dumoulin, Benoit and Wang, Dakuo and He, Jingrui and Lu, Hanqing},
  year = {2026},
  url = {https://arxiv.org/abs/2608.15071}
}

@misc{ke2026evoharnessbench,
  title = {{EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?}},
  author = {Ke, Zixuan and Patil, Vaidehi and Shi, Haizhou and Li, Yang and Liu, Ye and Shekkizhar, Sarath and Koul, Anurag and Wang, Jiayu and Nguyen, Xuan Phi and Yavuz, Semih and Bansal, Mohit and Joty, Shafiq},
  year = {2026},
  url = {https://arxiv.org/abs/2609.04280}
}

@misc{mavfr2026,
  title = {{Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration}},
  author = {Tang, Bowen and Wang, Tao and Zhang, Miao and Yu, Xin and Chen, Jinwei and Li, Bo and Zhang, Kaihao},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026F/html/Tang_Evolutionary_Multi-Agent_Collaboration_for_Real-World_Video_Face_Restoration_CVPRF_2026_paper.html}
}

@misc{cotrisygen2026,
  title = {{EvoState: Closed-Loop Visual State Management for Long-Form Video Generation}},
  author = {Yin, Xinlei and Peng, Xiulian and Li, Xiao and Xiong, Zhiwei and Lu, Yan},
  year = {2026},
  url = {https://arxiv.org/abs/2606.16184}
}

@misc{fantasyhsi2026,
  title = {{FantasyHSI: Video-Generation-Centric 4D Human Synthesis in Any Scene Through a Graph-Based Multi-Agent Framework}},
  author = {Lingzhou Mu and Wang Qiang and Fan Jiang and Mengchao Wang and Mu Xu and Kai Zhang},
  year = {2026},
  url = {https://doi.org/10.1609/aaai.v40i10.37758}
}

@misc{filmaster2025,
  title = {{FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation}},
  author = {Huang, Kaiyi and Huang, Yukun and WANG, Xintao and Lin, Zinan and Ning, Xuefei and Wan, Pengfei and ZHANG, Di and Wang, Yu and Liu, Xihui},
  year = {2026},
  url = {https://filmaster-ai.github.io/}
}

@misc{luo2026filmweaver,
  title = {{FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion}},
  author = {Luo, Xiangyang and Li, Qingyu and Liu, Xiaokun and Qin, Wenyu and Yang, Miao and Wang, Meng and Wan, Pengfei and Zhang, Di and Gai, Kun and Huang, Shao-Lun},
  year = {2026},
  url = {https://doi.org/10.1609/aaai.v40i9.37711}
}

@misc{filmworld2026,
  title = {{FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling}},
  author = {Zuo, Jialong and Zuo, Haotong and Zhang, Shiwei and Wang, Xiang and Li, Chen and Sang, Nong and Gao, Changxin and Bai, Xiang},
  year = {2026},
  url = {https://arxiv.org/abs/2607.19038}
}

@misc{frameworkers2026,
  title = {{FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production}},
  author = {Li, Zhendong and Sun, Lei and Shi, Letian and Zhang, Deheng and Ming, Ruibo and Hu, Mengshun and Xu, Dannong and Wang, Jian and Paudel, Danda and Van Gool, Luc and Gu, Jinjin},
  year = {2026},
  url = {https://arxiv.org/abs/2608.29814}
}

@misc{peng2026freemem,
  title = {{FreeMem: Enhancing Consistency in Long Video Generation via Tuning-Free Memory}},
  author = {Peng, Jibin and Lin, Di and Xu, Zhecheng and Lu, Haoran and Liu, Ruonan and Xie, Wuyuan and Wang, Miaohui and Liang, Lingyu and Wang, Yi and Guo, Qing},
  year = {2026},
  url = {https://doi.org/10.1609/aaai.v40i10.37783}
}

@misc{odin2026clayrender,
  title = {{From Clay 3D Render to a Real Action Short: A 3D-to-AI Pipeline with Total Control}},
  author = {Odin, Lovis},
  year = {2026},
  url = {https://blog.fal.ai/from-clay-3d-render-to-a-real-action-short-a-3d-to-ai-pipeline-with-total-control/}
}

@misc{guo2026harnessdesign,
  title = {{From Question Answering to Task Completion: A Survey on Agent System and Harness Design}},
  author = {Guo, Jianyuan and Hao, Zhiwei and Wang, Chengcheng and Fan, Cheng and Luo, Tingzhang and Li, Hongguang and Gao, Ying and Mei, Hefei and Peng, Jiankun and Xu, Rongjian and Dong, Minjing and Wu, Han and Zheng, Mengyu and Han, Kai and Wang, Shiqi and Xu, Chang and Wang, Yunhe},
  year = {2026},
  url = {https://arxiv.org/abs/2606.20683}
}

@misc{huang2026worldrenderer,
  title = {{Generative World Renderer}},
  author = {Huang, Zheng-Hui and Wang, Zhixiang and Tan, Jiaming and Yu, Ruihan and Zhang, Yidan and Zheng, Bo and Liu, Yu-Lun and Chuang, Yung-Yu and Zhang, Kaipeng},
  year = {2026},
  url = {https://arxiv.org/abs/2604.02329}
}

@misc{alaya2026renderer,
  title = {{Generative World Renderer at the Speed of Play}},
  author = {Lin, Guixu and Huang, Zheng-Hui and Yang, Siqi and Yang, Ming-Hsuan and Zhang, Kaipeng and Wang, Zhixiang},
  year = {2026},
  url = {https://arxiv.org/abs/2607.18703}
}

@misc{hadsell2026genie4,
  title = {{Genie 4: A new generation of world simulation}},
  author = {Hadsell, Raia and Rivas, Diego and Qi, Hang},
  year = {2026},
  url = {https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/}
}

@misc{huang2026genmac,
  title = {{GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration}},
  author = {Kaiyi Huang and Yukun Huang and Xuefei Ning and Zinan Lin and Yu Wang and Xihui Liu},
  year = {2026},
  url = {https://doi.org/10.1609/aaai.v40i7.37418}
}

@misc{agrawal2025gepa,
  title = {{GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning}},
  author = {Agrawal, Lakshya A and Tan, Shangyin and Soylu, Dilara and Ziems, Noah and Khare, Rishi and Opsahl-Ong, Krista and Singhvi, Arnav and Shandilya, Herumb and Ryan, Michael J and Jiang, Meng and Potts, Christopher and Sen, Koushik and Dimakis, Alexandros G. and Stoica, Ion and Klein, Dan and Zaharia, Matei and Khattab, Omar},
  year = {2026},
  url = {https://arxiv.org/abs/2507.19457}
}

@misc{openai2026gpt6astra,
  title = {{GPT-6 Astra: A New Generation of Intelligence}},
  author = {OpenAI},
  year = {2026},
  url = {https://openai.com/index/gpt-6-astra/}
}

@misc{groundshot2026,
  title = {{GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling}},
  author = {Lai, Yixuan and Shao, Tianjia and Dou, Weijia and Zhu, Siyu and Wang, Jingdong},
  year = {2026},
  url = {https://arxiv.org/abs/2606.20799}
}

@misc{weng2026harness,
  title = {{Harness Engineering for Self-Improvement}},
  author = {Weng, Lilian},
  year = {2026},
  url = {https://lilianweng.github.io/posts/2026-07-04-harness/}
}

@misc{holocine2026,
  title = {{HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives}},
  author = {Meng, Yihao and Ouyang, Hao and Yu, Yue and Wang, Qiuyu and Wang, Wen and Cheng, Ka Leong and Wang, Hanlin and Ma, Shuailei and Li, Yixuan and Chen, Cheng and Zeng, Yanhong and Zhu, Xing and Shen, Yujun and Qu, Huamin},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Meng_HoloCine_Holistic_Generation_of_Cinematic_Multi-Shot_Long_Video_Narratives_CVPR_2026_paper.html}
}

@misc{aesr2026,
  title = {{Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair}},
  author = {Gao, Jiayi and Hua, Changcheng and Tang, Jiaqi and Peng, Yuxin and Liu, Yang},
  year = {2026},
  url = {https://arxiv.org/abs/2608.20749}
}

@misc{gao2026lingbotworld2,
  title = {{Infinite Worlds with Versatile Interactions}},
  author = {Gao, Zelin and Wang, Qiuyu and Zhu, Jiapeng and Chen, Jingye and Liu, Zichen and Bai, Qingyan and Wang, Jiahao and Yuan, Yufeng and Wang, Hanlin and Lu, Yichong and Cheng, Ka Leong and Zhang, Haojie and Gao, Jian and Feng, Tianrui and Liu, Yuzheng and Yao, Yao and Xu, Yinghao and Zhu, Xing and Shen, Yujun and Ouyang, Hao},
  year = {2026},
  url = {https://arxiv.org/abs/2607.07534}
}

@misc{zhang2026interacvid,
  title = {{InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos}},
  author = {Chi Zhang and Haoyang Shi and Yueyi Liu and Zhaokun Yan and Yishu Yin and Yuhang Wu and Miao Liu},
  year = {2026},
  url = {https://arxiv.org/abs/2608.01157}
}

@misc{lee2026scenesplit,
  title = {{Jailbreaking on Text-to-Video Models via Scene Splitting Strategy}},
  author = {Lee, Wonjun and Park, Haon and Lee, Doehyeon and Ham, Bumsub and Kim, Suhyun},
  year = {2026},
  url = {https://arxiv.org/abs/2509.22292}
}

@misc{chen2026javedit,
  title = {{JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation}},
  author = {Yinan Chen and Chuming Lin and Zhennan Chen and Yuxiang Zeng and Junwei Zhu and Yali Bi and Xijie Huang and Chengming Xu and Donghao Luo and Zhucun Xue and Xiaobin Hu and Chengjie Wang and Yong Liu and Jiangning Zhang and Shuicheng Yan},
  year = {2026},
  url = {https://arxiv.org/abs/2606.03168}
}

@misc{liver2026,
  title = {{Lighting-grounded Video Generation with Renderer-based Agent Reasoning}},
  author = {Cai, Ziqi and Yang, Taoyu and Chang, Zheng and Li, Si and Jiang, Han and Weng, Shuchen and Shi, Boxin},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Cai_Lighting-grounded_Video_Generation_with_Renderer-based_Agent_Reasoning_CVPR_2026_paper.html}
}

@misc{cai2026liver,
  title = {{Lighting-grounded Video Generation with Renderer-based Agent Reasoning}},
  author = {Cai, Ziqi and Yang, Taoyu and Chang, Zheng and Li, Si and Jiang, Han and Weng, Shuchen and Shi, Boxin},
  year = {2026},
  url = {https://arxiv.org/abs/2604.07966}
}

@misc{lvmark2024,
  title = {{LVMark: Robust Watermark for Latent Video Diffusion Models}},
  author = {Jang, Youngdong and Jang, MinHyuk and Lee, JaeHyeok and Yang, Feng and Oh, Gyeongrok and Jeong, Jongheon and Kim, Sangpil},
  year = {2026},
  url = {https://doi.org/10.1109/TIFS.2026.3688194}
}

@misc{zhan2026magpie,
  title = {{Magpie: Real-Time World Renderer for Interactive Games}},
  author = {Zhan, Xiaoyu and Wang, Xinyu and Zhang, Xiaohong and Zhu, Huanjie and Sun, Tengjiao and Fang, Pengcheng and Yu, Jiaxing and Guo, Yanwen and Fu, Dongjie},
  year = {2026},
  url = {https://arxiv.org/abs/2608.27168}
}

@misc{zhang2026matrixgame4,
  title = {{Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds}},
  author = {Zhang, Jihai and Qian, Runjia and Kong, Kaiqin and Jiang, Biao and Wang, Puyi and Chen, Siru and Li, Tianle and Chen, Guanjie and Wu, Junyi and Chen, Chubin and Li, Yuanhang and Huang, Kaichen and Zhang, Haobo and Li, Yangguang and Yu, Wei and Chen, Guibin and Cheng, Yu and Zhou, Yahui},
  year = {2026},
  url = {https://arxiv.org/abs/2610.27999}
}

@misc{mavis2025,
  title = {{MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling}},
  author = {Qian Wang and Ziqi Huang and Ruoxi Jia and Paul Debevec and Ning Yu},
  year = {2026},
  url = {https://aclanthology.org/2026.eacl-long.101/}
}

@misc{wei2026memento,
  title = {{Memento: Reconstruct to Remember for Consistent Long Video Generation}},
  author = {Wei, Xuan and Ji, Longbin and Wang, Guan and Liu, Xiangrui and Zhang, Zhenyu and Wang, Shuohuan and Sun, Yu and Hong, Qingqi},
  year = {2026},
  url = {https://arxiv.org/abs/2606.14667}
}

@misc{lee2026memoryv2v,
  title = {{Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-turn Editing}},
  author = {Lee, Dohun and Huang, Chun-Hao Paul and Chen, Xuelin and Ye, Jong Chul and Ceylan, Duygu and Jeong, Hyeonho},
  year = {2026},
  url = {https://doi.org/10.1007/978-3-032-37324-3_5}
}

@misc{kim2026memrope,
  title = {{MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens}},
  author = {Kim, Youngrae and Hu, Qixin and Kuo, C.-C. Jay and Beerel, Peter},
  year = {2026},
  url = {https://doi.org/10.1007/978-3-032-37356-4_14}
}

@misc{lee2026metaharness,
  title = {{Meta-Harness: End-to-End Optimization of Model Harnesses}},
  author = {Lee, Yoonho and Nair, Roshen and Zhang, Qizheng and Lee, Kangwook and Khattab, Omar and Finn, Chelsea},
  year = {2026},
  url = {https://arxiv.org/abs/2603.28052}
}

@misc{mindofdirector2026,
  title = {{Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making}},
  author = {Nan, Shufeng and Li, Mengtian and Zheng, Sixiao and Lu, Yuwei and Zhang, Han and Fu, Yanwei},
  year = {2026},
  url = {https://arxiv.org/abs/2603.14790}
}

@misc{moregen2025,
  title = {{MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis}},
  author = {Bai, Xiangyu and Liang, He and Galoaa, Bishoy and Nandi, Utsav and Moezzi, Shayda and He, Yuhang and Ostadabbas, Sarah},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Bai_MoReGen_Multi-Agent_Motion-Reasoning_Engine_for_Code-based_Text-to-Video_Synthesis_CVPR_2026_paper.html}
}

@misc{mpresenter2026,
  title = {{MPRESENTER: Multilingual Agentic System for Paper-to-Video Generation}},
  author = {Wenhan Han and Xiao Xiao and Mykola Pechenizkiy and Meng Fang},
  year = {2026},
  url = {https://aclanthology.org/2026.findings-acl.805/}
}

@misc{multiagentcad2026,
  title = {{Multi-Agent CAD Code Generation}},
  author = {Yang Liu and Daxuan Ren and Yijie Ding and Jianmin Zheng and Fang Deng},
  year = {2026},
  url = {https://doi.org/10.1145/3799902.3811067}
}

@misc{muse2026,
  title = {{MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration}},
  author = {Sun, Wenzhang and Wang, Zhenyu and Hu, Zhangchi and Wang, Chunfeng and Li, Hao and Chen, Wei},
  year = {2026},
  url = {https://arxiv.org/abs/2602.03028}
}

@misc{kong2026mvagent,
  title = {{MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization}},
  author = {Kong, Xiangyu and Zhou, Wenjie and Tian, Fengping and Fang, Lihua and Sun, Haoqin and Lyu, Chenyang and Wang, Longyue and Luo, Weihua},
  year = {2026},
  url = {https://arxiv.org/abs/2609.30609}
}

@misc{mvweaver2026,
  title = {{MVWeaver: A Hierarchical Music Video Generation Agent with a Learned Song-to-Visual Bridge}},
  author = {Li, Sifei and Luo, Minyan and Li, Xu and Qi, Guodong and Wang, Xincan and Wang, Hanwen and Zhang, Chen and Wan, Pengfei and Deussen, Oliver and Dong, Weiming},
  year = {2026},
  url = {https://arxiv.org/abs/2609.06478}
}

@misc{feng2026newton,
  title = {{NEWTON: Agentic Planning for Physically Grounded Video Generation}},
  author = {Feng, Yuxiang and Wang, Juncheng and Xu, Chao and Qian, Yijie and Wang, Huihan and Hou, Wenlong and Liu, Yang and Sun, Baigui and Liu, Yong and Wang, Shujun},
  year = {2026},
  url = {https://arxiv.org/abs/2605.18396}
}

@misc{meng2026omnidrive,
  title = {{OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation}},
  author = {Meng, Zijie and Liu, Yufei and Ma, Chengqian and Li, Zhiyu and Liu, Jiyuan and Nie, Wenhua and Wei, Bingcai and Chen, Shuqin and Xu, Weichen and Yuan, Jiquan and Zhang, Miao},
  year = {2026},
  url = {https://arxiv.org/abs/2606.17536}
}

@misc{onesentence2026,
  title = {{One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems}},
  author = {Shi, Yufei and Yan, Weilong and Huang, Naixuan and Chen, Yucheng and Zhang, Chenyu and He, Tao and Yeo, Si Yong and Li, Ming},
  year = {2026},
  url = {https://arxiv.org/abs/2605.22144}
}

@misc{bytedance2026seedance25,
  title = {{One-take Creation, Flexible Referencing: Introducing Seedance 2.5}},
  author = {ByteDance Seed},
  year = {2026},
  url = {https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5}
}

@misc{an2026onestory,
  title = {{OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory}},
  author = {An, Zhaochong and Jia, Menglin and Qiu, Haonan and Zhou, Zijian and Huang, Xiaoke and Liu, Zhiheng and Ren, Weiming and Kahatapitiya, Kumara and Liu, Ding and He, Sen and Zhang, Chenyang and Xiang, Tao and Yang, Fanny and Belongie, Serge and Xie, Tian},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/An_OneStory_Coherent_Multi-Shot_Video_Generation_with_Adaptive_Memory_CVPR_2026_paper.html}
}

@misc{tian2026openevaluationagent,
  title = {{Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models}},
  author = {Tian, Shulin and Huang, Ziqi and Zhang, Fan and Zhu, Hongyuan and Qiao, Yu and Liu, Ziwei},
  year = {2026},
  url = {https://arxiv.org/abs/2608.09666}
}

@misc{lu2026orbia,
  title = {{Orbia: Do Generated Videos Form a Consistent 3D World?}},
  author = {Lu, Dongyue and Fang, Guian and Lim, Hur and Wu, Yonggang and Wang, Yanrong and Chen, Hongshan and Qian, Shengju and Liao, Yue and Chow, Wei and Kong, Lingdong and Huang, Tianxin and Yang, Yu and Yang, Hongji and Huang, Junchao and Liang, Ao and Wang, Yihao and Wang, Zihan and Li, Rong and Chen, Hanlin and Wang, Xin and Ooi, Wei Tsang and Shou, Mike Zheng and Yan, Shuicheng},
  year = {2026},
  url = {https://arxiv.org/abs/2610.20693}
}

@misc{shaul2026pdd,
  title = {{Parallel Decoding Distillation for Fast Image and Video Generation}},
  author = {Shaul, Neta and Liu, Chao and Vahdat, Arash and Berner, Julius},
  year = {2026},
  url = {https://arxiv.org/abs/2607.26004}
}

@misc{chen2025phantomdata,
  title = {{Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset}},
  author = {Chen, Zhuowei and Li, Bingchuan and Ma, Tianxiang and Liu, Lijie and Liu, Mingcong and Jiang, Yunsheng and Li, Li and Li, Xinghui and Chen, Liyang and Zhou, Siyu and He, Qian and Wu, Xinglong},
  year = {2026},
  url = {https://arxiv.org/abs/2506.18851}
}

@misc{lin2026phyground,
  title = {{PhyGround: Benchmarking Physical Reasoning in Generative World Models}},
  author = {Lin, Juyi and Akbari, Arash and He, Yumei and Zhao, Lin and Zhang, Haichao and Akbari, Arman and Xu, Xingchen and Lu, Zoe Y. and Nan, Enfu and Deng, Hokin and Yeh, Edmund and Ostadabbas, Sarah and Fu, Yun and Dy, Jennifer and Zhao, Pu and Wang, Yanzhi},
  year = {2026},
  url = {https://arxiv.org/abs/2605.10806}
}

@misc{phyprompt2026,
  title = {{PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation}},
  author = {Wu, Shang and Xu, Chenwei and Xia, Zhuofan and Li, Weijian and Lu, Lie and Maneriker, Pranav and Du, Fan and Li, Manling and Liu, Han},
  year = {2026},
  url = {https://arxiv.org/abs/2603.03505}
}

@misc{physagent2026,
  title = {{PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation}},
  author = {Li, Qirui and Hao, Jinkun and Li, Yibo and Yi, Ran and Rosin, Paul L. and Lai, Yu-Kun},
  year = {2026},
  url = {https://arxiv.org/abs/2607.16355}
}

@misc{zhou2026physinone,
  title = {{PhysInOne: Visual Physics Learning and Reasoning in One Suite}},
  author = {Zhou, Siyuan and Wang, Hejun and Cheng, Hu and Li, Jinxi and Wang, Dongsheng and Jiang, Junwei and Jin, Yixiao and Huang, Jiayue and Mao, Shiwei and Liu, Shangjia and Yang, Yafei and Song, Hongkang and Wei, Shenxing and Zhang, Zihui and Wang, Bing and Wang, Zhihua and Zou, Chuhang and Yang, Bo},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Zhou_PhysInOne_Visual_Physics_Learning_and_Reasoning_in_One_Suite_CVPR_2026_paper.html}
}

@misc{nguyen2026physplan,
  title = {{PhysPlan: Grounded Physical State Reasoning and Graph-Guided Optimization for Physically Plausible Video Generation}},
  author = {Nguyen, Minh-Loi and Le, Xuan-Vu and Le, Trung-Nghia and Nguyen, Tam V. and Tran, Minh-Triet and Do, Thanh-Toan},
  year = {2026},
  url = {https://arxiv.org/abs/2609.13006}
}

@misc{ding2026playworld,
  title = {{PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives}},
  author = {Ding, Kaixin and Chen, Xi and Cai, Minghong and Xu, Zhiyuan and Wang, Yiyang and Lu, Yuxiang and Li, Junyi and Chen, Shuyang and Gao, Yuan and Tao, Xin and Wan, Pengfei and Zhao, Hengshuang},
  year = {2026},
  url = {https://arxiv.org/abs/2608.13552}
}

@misc{evopresent2026,
  title = {{Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations}},
  author = {Liu, Chengzhi and Yang, Yuzhe and Zhou, Kaiwen and Zhang, Zhen and Fan, Yue and Xie, Yanan and Qi, Peng and Wang, Xin Eric},
  year = {2026},
  url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/d848cb2c84f0bba7f1f73cf232734c40-Abstract-Conference.html}
}

@misc{huang2026programmable,
  title = {{Programmable World Model}},
  author = {Huang, Zheng-Hui and Lin, Guixu and Lin, Jiacheng and Huang, Yi-Chuan and Yu, Ruihan and Niu, Muyao and Yang, Siqi and Liu, Yu-Lun and Chuang, Yung-Yu and Zhang, Kaipeng and Wang, Zhixiang},
  year = {2026},
  url = {https://arxiv.org/abs/2609.10540}
}

@misc{xu2026proxy2world,
  title = {{Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them}},
  author = {Xu, Hongli and Yan, Weilong and Wang, Anbang and Zou, Chunyu and Hong, Siyu and Huang, Jingwei},
  year = {2026},
  url = {https://arxiv.org/abs/2609.35023}
}

@misc{yang2026quovadis,
  title = {{Quo Vadis, World Modeling?}},
  author = {Yang, Yu and Yang, Xuemeng and Wen, Licheng and Kong, Lingdong and Hu, Xiaobin and Lu, Dongyue and Chow, Wei and Huang, Xiyan and Feng, Yuxiang and Liao, Yue and Mei, Jianbiao and Fu, Daocheng and Wu, Rong and Cai, Pinlong and Yi, Ran and Tai, Ying and Zhang, Jiangning and Shi, Botian and Liu, Yong and Yan, Shuicheng},
  year = {2026},
  url = {https://arxiv.org/abs/2608.02713}
}

@misc{jia2026raveneval,
  title = {{RAVEN-Eval: Rubric-Guided Automatic Evaluation for AI Video Generation Models Based on LMM Preference Judgement}},
  author = {Jia, Ziheng and Qian, Jiaying and Zhang, Zicheng and Zhu, Xiaorong and Gao, Lancheng and Min, Xiongkuo},
  year = {2026},
  url = {https://arxiv.org/abs/2608.09111}
}

@misc{liu2026reca,
  title = {{ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation}},
  author = {Liu, Akide and Xing, Jinbo and Mao, Chaojie and Li, Ye and Zhang, Zeyu and He, Yefei and Wang, Weijie and Wang, Zihan and Liu, Yu and Haffari, Gholamreza and Zhuang, Bohan},
  year = {2026},
  url = {https://arxiv.org/abs/2605.26525}
}

@misc{cheng2026rag,
  title = {{Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale}},
  author = {Cheng, Yanhua and Wang, Bo and Zhang, Haotian and Gao, Xinyuan and Yin, Zhihui and Xue, Ben and Li, Yongzhi and Xue, Jieting and Ma, Ye and Wang, Minquan and Li, Jiahui and Xu, Tianyu and Liu, Zhiqiang and Lin, Xiao and Wen, Shiyang and Li, Changcheng and Liu, Liu and Chen, Quan and Jiang, Peng and Gai, Kun},
  year = {2026},
  url = {https://arxiv.org/abs/2606.25496}
}

@misc{chen2026surveyr04,
  title = {{Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops}},
  author = {Chen, Mingguang and Wang, Licheng and Qu, Bo},
  year = {2026},
  url = {https://arxiv.org/abs/2607.07663}
}

@misc{wang2026harnessevaluation,
  title = {{Rethinking the Evaluation of Harness Evolution for Agents}},
  author = {Wang, Yike and Zhu, Huaisheng and Hu, Zhengyu and Yuan, Yige and Chen, Zhengyu and Senthil, Shakti and Hajishirzi, Hannaneh and Tsvetkov, Yulia and Smith, Noah A. and Dasigi, Pradeep and Xiao, Teng},
  year = {2026},
  url = {https://arxiv.org/abs/2607.12227}
}

@misc{tang2026rewardverse,
  title = {{RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling}},
  author = {Tang, Zhenchen and Li, Yang and Yang, Songlin and Peng, Bo and Zhao, Xiaotong and Li, Shuai and Fan, Haotian and Zhao, Alan and Dong, Jing},
  year = {2026},
  url = {https://arxiv.org/abs/2609.22947}
}

@misc{zeng2026rgbx,
  title = {{RGBX-Next: Towards Realistic Generative Rendering from G-Buffers}},
  author = {Zeng, Zheng and Salvi, Marco and Wu, Lifan and Novák, Jan and Lin, Daqi and Hadadan, Saeed and Sheng, Yichen and Pottorff, Robert and Liu, Shiqiu and Ramamoorthi, Ravi and Yan, Ling-Qi and Hašan, Miloš},
  year = {2026},
  url = {https://arxiv.org/abs/2608.13929}
}

@misc{xue2026ringforcing,
  title = {{Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion}},
  author = {Xue, Bowen and Feng, Brandon Y. and Lin, Chenguo and Lin, Yuchen and Zeng, Yujia and Zhang, Lvmin and Agrawala, Maneesh and Yan, Honglei and Pan, Panwang},
  year = {2026},
  url = {https://doi.org/10.1007/978-3-032-37602-2_13}
}

@misc{mei2026surveyn19,
  title = {{Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions}},
  author = {Mei, Zhiting and Yin, Tenny and Shorinwa, Ola and Badithela, Apurva and Zheng, Zhonghe and Bruno, Joseph and Bland, Madison and Zha, Lihan and Hancock, Asher and Fisac, Jaime Fernández and Dames, Philip and Majumdar, Anirudha},
  year = {2026},
  url = {https://arxiv.org/abs/2601.07823}
}

@misc{xia2026rrsi,
  title = {{RRSI: Regularized Recursive Self-Improvement of Agent Harnesses}},
  author = {Xia, Peng and Han, Rujun and Wang, Zifeng and Chen, Yanfei and Zhuang, Yufan and Lee, Yoonho and Huang, Chengsong and Yu, Han and CuiZhu, Zhongying and Ming, Yifei and Yao, Huaxiu and Gokturk, Burak and Pfister, Tomas and Lee, Chen-Yu},
  year = {2026},
  url = {https://arxiv.org/abs/2609.24972}
}

@misc{bai2025ditto,
  title = {{Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset}},
  author = {Bai, Qingyan and Wang, Qiuyu and Ouyang, Hao and Yu, Yue and Wang, Hanlin and Wang, Wen and Cheng, Ka Leong and Ma, Shuailei and Zeng, Yanhong and Liu, Zichen and Xu, Yinghao and Shen, Yujun and Chen, Qifeng},
  year = {2026},
  url = {https://arxiv.org/abs/2510.15742}
}

@misc{mei2026scene2scene,
  title = {{Scene2Scene: LLM-driven 3D Spatial Blockout for Guided AI Video Synthesis}},
  author = {Mei, Yutong Alison and Cai, Wei},
  year = {2026},
  url = {https://doi.org/10.1145/3807895.3807932}
}

@misc{scmapr2026,
  title = {{SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation}},
  author = {Chengyi Yang and Pengzhen Li and Jiayin Qi and Aimin Zhou and Ji Wu and Ji Liu},
  year = {2026},
  url = {https://aclanthology.org/2026.findings-acl.345/}
}

@misc{jiang2026scope,
  title = {{SCOPE: Score-Isolated Agentic Optimization for Video World Models}},
  author = {Jiang, Yuhua and Wang, Jiaming and Liu, Qingbin and Gao, Feifei},
  year = {2026},
  url = {https://arxiv.org/abs/2608.15043}
}

@misc{lee2026videorepair,
  title = {{Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement}},
  author = {Lee, Daeun and Yoon, Jaehong and Cho, Jaemin and Bansal, Mohit},
  year = {2026},
  url = {https://arxiv.org/abs/2411.15115}
}

@misc{ren2026surveyr03,
  title = {{Self-Improvements in Modern Agentic Systems: A Survey}},
  author = {Ren, Zhe and Chen, Yimeng and Guo, Dandan and Rong, Guowei and Li, Tonghui and Xiong, R. B. and Lan, Qingfeng and Wang, Wenyi and Nanbo, Li and Yang, Yibo and Zhuge, Mingchen and Schmidhuber, Jürgen},
  year = {2026},
  url = {https://arxiv.org/abs/2607.13104}
}

@misc{sigmark2026,
  title = {{SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video Diffusion}},
  author = {Zhu, Xinjie and Zhao, Zijing and Jin, Hui and Guo, Qingxiao and Ma, Yilong and Wang, Yunhao and Guo, Xiaobing and Zhang, Weifeng},
  year = {2026},
  url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/f3f6f1739b646e0bd20111261ce23adb-Abstract-Conference.html}
}

@misc{simworlds2026,
  title = {{SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation}},
  author = {Liu, Chunjiang and Wang, Xiaoyuan and Chen, Haoyu and Zhao, Yizhou and Yang, Ming-Hsuan and Jeni, Laszlo A.},
  year = {2026},
  url = {https://arxiv.org/abs/2607.01766}
}

@misc{skillpe2026,
  title = {{SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering}},
  author = {Huang, Yanwei and Zhu, Mingxuan and Li, Shujie and Liu, Shiyuan and Zhang, Yuanxing and Narechania, Arpit},
  year = {2026},
  url = {https://arxiv.org/abs/2609.34335}
}

@misc{matsuda2026slvmeval,
  title = {{SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation}},
  author = {Matsuda, Ryosuke and Kudo, Keito and Yoshida, Haruto and Shimizu, Nobuyuki and Suzuki, Jun},
  year = {2026},
  url = {https://arxiv.org/abs/2603.29186}
}

@misc{soap2soap2026,
  title = {{Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration}},
  author = {Song, Yiren and Zhong, Huilin and Lin, Kevin Qinghong and Wang, Haofan and Shou, Mike Zheng},
  year = {2026},
  url = {https://arxiv.org/abs/2605.17423}
}

@misc{fang2026solarrenderer,
  title = {{SolarRenderer: Few-Step Generative Reference Rendering}},
  author = {Fang, Guian and Qian, Shengju and Lu, Dongyue and Huang, Junchao and Jiang, Lutao and Wang, Xin and Song, Yiren and Jiang, Li and Shou, Mike Zheng},
  year = {2026},
  url = {https://arxiv.org/abs/2610.28630}
}

@misc{huang2026solarwm,
  title = {{SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models}},
  author = {Huang, Junchao and Fang, Guian and Qian, Shengju and Kong, Xianghao and Zhao, Zhuoran and Huang, Wei and Du, Yihua and Zhang, Zixin and Cui, Justin and Gu, Yuchao and Chen, Yukang and Hu, Xinting and He, Tianyu and Shi, Shaoshuai and Tian, Zhuotao and Wang, Xin and Shou, Mike Zheng and Jiang, Li},
  year = {2026},
  url = {https://arxiv.org/abs/2609.02886}
}

@misc{spagent2024,
  title = {{SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing}},
  author = {Tu, Rong-Cheng and Sun, Wenhao and Jin, Zhao and Liao, Jingyi and Huang, Jiaxing and Tao, Dacheng},
  year = {2026},
  url = {https://arxiv.org/abs/2411.18983}
}

@misc{spdmark2026,
  title = {{SPDMark: Selective Parameter Displacement for Robust Video Watermarking}},
  author = {Fares, Samar and Tastan, Nurbek and Nandakumar, Karthik},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Fares_SPDMark_Selective_Parameter_Displacement_for_Robust_Video_Watermarking_CVPR_2026_paper.html}
}

@misc{yang2026spiral,
  title = {{SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents}},
  author = {Yang, Yu and Liao, Yue and Mei, Jianbiao and Wang, Baisen and Yang, Xuemeng and Wen, Licheng and Zhang, Jiangning and Li, Xiangtai and Lv, Liang and Chen, Hanlin and Shi, Botian and Liu, Yong and Yan, Shuicheng and Lee, Gim Hee},
  year = {2026},
  url = {https://arxiv.org/abs/2603.08403}
}

@misc{liao2026streamingcwm,
  title = {{Streaming Code World Model}},
  author = {Liao, Tingting and Liu, Guangyi},
  year = {2026},
  url = {https://github.com/TingtingLiao/streaming-code-world-model}
}

@misc{worldweaver2026,
  title = {{Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers}},
  author = {Mo, Sicheng and Li, Yuheng and Leng, Ziyang and Singh, Krishna Kumar and Zhou, Bolei},
  year = {2026},
  url = {https://arxiv.org/abs/2607.21594}
}

@misc{nvidia2026streamrender,
  title = {{StreamRender-H3: Interactive Coding Worlds with Real-time Streaming Diffusion Render}},
  author = {Lu, Yanzuo and Ye, Tian and Li, Yitong and Xue, Shuchen and Liu, Haozhe and Han, Song and Xie, Enze},
  year = {2026},
  url = {https://nvlabs.github.io/Sana/Sol-Engine/StreamRender-H3/}
}

@misc{teachmaster2026,
  title = {{TeachMaster: Generative Teaching via Code}},
  author = {Yuheng Wang and Runde Yang and Lin Wu and Jie Zhang and Jingru Fan and Tianle Zhou and Ruoyu Fu and Huatao Li and Ruijie Shi and Siheng Chen and Weinan E and Chen Qian},
  year = {2026},
  url = {https://aclanthology.org/2026.acl-industry.7/}
}

@misc{he2026tear,
  title = {{TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models}},
  author = {He, Jiaming and Hou, Guanyu and Li, Hongwei and Huang, Zhicong and Chen, Kangjie and Yu, Yi and Jiang, Wenbo and Xu, Guowen and Zhang, Tianwei},
  year = {2026},
  url = {https://arxiv.org/abs/2511.21145}
}

@misc{duan2026surveyn21,
  title = {{The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement}},
  author = {Duan, Yi and Liu, Ying and Tang, Zirui and Chen, Haodong and Zhou, Jun and Liu, Yumou and Xu, Bangrui and Wu, Yukai and Chen, Sidi and Zhou, Yuhan and Wang, Haoyu and Yu, Xiaoyou and Han, Shaokun and Zhu, Xuzhou and Zhou, Le and Lu, Bolin and Zhou, Wei and Liu, Jiachen and Fang, Nuozhou and Tian, Jiaxin and Chen, Ruoyu and Li, Yuxuan and Zuo, Kai and Zhang, Kaiyan and Yang, Qianyu and Wang, Zijie and Qiu, Jiantao and He, Conghui and Li, Guoliang and Zhou, Bowen and Liu, Zhiyuan and Wen, Zhoufutu and Kang, Jihua and Zhou, Xuanhe and Wu, Fan},
  year = {2026},
  url = {https://arxiv.org/abs/2609.11873}
}

@misc{chen2026surveyn14,
  title = {{The Past Frames the Future: Memory for Autoregressive Video Generation}},
  author = {Chen, Harold Haodong and Guo, Rongjin and Lan, Disen and Shu, Wen-Jie and Zhang, Hongfei and Hu, Hanzhe and Yao, Shengtao and Zhang, Zixin and Zhang, Guibin and Rao, Zhefan and Liu, Jinxiu and Liu, Yexin and Peng, Rui and Liu, Yuhao and Ren, Bin and Yang, Shuai and Chen, Yukang and Khan, Salman and Chen, Ying-Cong and Lim, Ser-Nam and Lau, Rynson W. H. and Sebe, Nicu and Cheng, Yu and Yang, Ming-Hsuan and Chen, Qifeng},
  year = {2026},
  url = {https://arxiv.org/abs/2609.28466}
}

@misc{scriptallneed2026,
  title = {{The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation}},
  author = {Mu, Chenyu and He, Xin and Yang, Qu and Chen, Wanshun and Yao, Jiadi and Liu, Huang and Yi, Zihao and Zhao, Bo and Chen, Xingyu and Ma, Ruotian and Ye, Fanghua and Yang, Erkun and Deng, Cheng and Tu, Zhaopeng and Li, Xiaolong and Linus},
  year = {2026},
  url = {https://arxiv.org/abs/2601.17737}
}

@misc{mmlveagent2026,
  title = {{Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning}},
  author = {Wu, Chenyang and Long, Fuchen and Huang, Binyuan and Sun, Xinlong and Chen, Xi and Guo, Chun-Le and Li, Chongyi},
  year = {2026},
  url = {https://arxiv.org/abs/2608.26809}
}

@misc{liu2026interactiveworldmodel,
  title = {{Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends}},
  author = {Liu, Jiuming and Ni, Chaojun and Liu, Mengmeng and Peng, Chensheng and Wang, Fangjinhua and Shen, Sitian and Pollefeys, Marc and Tomizuka, Masayoshi and Tewari, Ayush and Kristensson, Per Ola},
  year = {2026},
  url = {https://arxiv.org/abs/2606.01164}
}

@misc{silva2026manimagent,
  title = {{Training and Agentic Inference Strategies for LLM-based Manim Animation Generation}},
  author = {Silva, Ravidu Suien Rammuni and Lotfi, Ahmad and Ihianle, Isibor Kennedy and Shahtahmassebi, Golnaz and Bird, Jordan J.},
  year = {2026},
  url = {https://arxiv.org/abs/2604.18364}
}

@misc{nie2026transition,
  title = {{Transition Matching Distillation for Fast Video Generation}},
  author = {Nie, Weili and Berner, Julius and Ma, Nanye and Liu, Chao and Xie, Saining and Vahdat, Arash},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Nie_Transition_Matching_Distillation_for_Fast_Video_Generation_CVPR_2026_paper.html}
}

@misc{liu2026v2vbench,
  title = {{V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation}},
  author = {Liu, Tao and Krishna, Leela and Kumar, Gouti Pavan and K, Sreeja and Garg, Vishav},
  year = {2026},
  url = {https://arxiv.org/abs/2606.05665}
}

@misc{li2026videoposttraining,
  title = {{Video Generation Models: A Survey of Post-Training and Alignment}},
  author = {Li, Chaoyu and Gu, Xiaoyi and Kulkarni, Yogesh and Im, Eun Woo and Honarmand, Mohammadmahdi and Wang, Zeyu and Song, Juntong and Du, Fei and Jiang, Xilin and Zheng, Kexin and Li, Tianzhi and Tao, Fei and Fazli, Pooyan},
  year = {2026},
  url = {https://openreview.net/forum?id=YlUEWLESIu}
}

@misc{luo2026videorsi,
  title = {{Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution}},
  author = {Luo, Bingjun and Guo, Jialin and Li, Siqi},
  year = {2026},
  url = {https://arxiv.org/abs/2609.37950}
}

@misc{zhou2026videoagentediting,
  title = {{VideoAgent: All-in-One Framework for Video Understanding and Editing}},
  author = {Zhou, Hengji and Huang, Lingxuan and Wang, Jian and Zhou, Bing and Wu, Si and Xia, Lianghao and Huang, Chao},
  year = {2026},
  url = {https://arxiv.org/abs/2606.23327}
}

@misc{zeng2026videoargus,
  title = {{VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing}},
  author = {Zeng, Ziyun and Wang, Zixuan and Yu, Yongsheng and Hua, Hang and Luo, Jiebo},
  year = {2026},
  url = {https://arxiv.org/abs/2608.05485}
}

@misc{videococo2026,
  title = {{VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System}},
  author = {Li, Haodong and Ren, Tianfei and Ma, Xiaoxiao and Qing, Chunmei and Fang, Zhen and He, Sipeng and Guo, Ziyu and Wu, Haoyu and Tian, Juanxi and Zou, Yihang and An, Ruichuan and Jiang, Dongzhi and Yang, Boxue and Xie, Ji and Huang, Xu and Yan, Wenhao and Zou, Jialv and Yue, Zhengrong and Luo, Yaxin and Li, Xiaotong and Wang, Yuzhu and Ye, Junyan and Zhao, Jinjing and Chen, Zehui and Chen, Lin and Yan, Renye and Zhao, Feng and Heng, Pheng-Ann},
  year = {2026},
  url = {https://arxiv.org/abs/2607.27380}
}

@misc{videocreator2026,
  title = {{VideoCreator: An Agentic System for Multi-turn Video Production}},
  author = {Zhengyang Liang and Yan Shu and Cathal Gurrin and Nicu Sebe and Lizi Liao},
  year = {2026},
  url = {https://doi.org/10.1145/3805622.3810431}
}

@misc{li2026videogenagent,
  title = {{VideoGen-Agent: Reinforcing Video Generation Agents}},
  author = {Li, Binxu and Duan, Haoyi and Zhang, Yuhui and Zhang, Yaohui and Lin, Zihao and Feng, Kaituo and Huang, Suozhi and Li, Xiangyi and Li, Yu and Li, Chunyuan and Liu, Shilong and Wang, Mengdi},
  year = {2026},
  url = {https://arxiv.org/abs/2609.24997}
}

@misc{videomemory2026,
  title = {{VideoMemory: Toward Consistent Video Generation via Memory Integration}},
  author = {Zhou, Jinsong and Du, Yihua and Xu, Xinli and Wang, Luozhou and Zhuang, Zijie and Zhang, Yehang and Li, Shuaibo and Hu, Xiaojun and Su, Bolan and Chen, Ying-cong},
  year = {2026},
  url = {https://arxiv.org/abs/2601.03655}
}

@misc{bansal2025videophy2,
  title = {{VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation}},
  author = {Bansal, Hritik and Peng, Clark and Bitton, Yonatan and Goldenberg, Roman and Grover, Aditya and Chang, Kai-Wei},
  year = {2026},
  url = {https://arxiv.org/abs/2503.06800}
}

@misc{he2025videoscore2,
  title = {{VideoScore2: Think before You Score in Generated Video Evaluation}},
  author = {He, Xuan and Jiang, Dongfu and Nie, Ping and Liu, Minghao and Jiang, Zhengxuan and Su, Mingyi and Ma, Wentao and Lin, Junru and Ye, Chun and Lu, Yi and Wu, Keming and Schneider, Benjamin and Do, Quy Duc and Li, Zhuofeng and Jia, Yiming and Zhang, Yuxuan and Cheng, Guo and Wang, Haozhe and Zhou, Wangchunshu and Lin, Qunshu and Zhang, Yuanxing and Zhang, Ge and Huang, Wenhao and Chen, Wenhu},
  year = {2026},
  url = {https://arxiv.org/abs/2509.22799}
}

@misc{wei2026videoweaver,
  title = {{VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation}},
  author = {Wei, Jianhui and Zhang, Yan and Tan, Jie and Zhu, Hengchuan and Zhang, Xiaotian and Chen, Ziyi and Zhang, Daoan and Xu, Wei and Jin, Yeying and Liu, Zuozhu},
  year = {2026},
  url = {https://arxiv.org/abs/2606.08091}
}

@misc{zhang2026vidus2,
  title = {{Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation}},
  author = {Zhang, Jintao and Jiang, Kai and Chen, Jintao and Wang, Xu and Liu, Deyuan and Li, Jungang and Chen, Dechuang and Lin, Ming and Zhou, Jingjiang and Jin, Haopeng and Jia, Qi and Wang, Xiaohang and Wang, Yaole and Zhang, Zhanqiang and Li, Ran and Huang, Zhengkun and Xiong, Shuyue and Wang, Yuji and Dai, Zikun and He, Hui and Luo, Yang and Ning, Mang and Feng, Weiqi and Ye, Chengyang and Lin, Xinyue and Zhao, Min and Zhu, Hongzhou and Tan, Hengkai and Wang, Zeyuan and Xiang, Chendong and Zheng, Kaiwen and Deng, Zhijie and Bao, Fan and Chen, Jianfei and Zhu, Jun},
  year = {2026},
  url = {https://arxiv.org/abs/2609.11638}
}

@misc{huang2026vimax,
  title = {{ViMax: Agentic Video Generation}},
  author = {Huang, Lingxuan and He, Sizhe and Zhou, Hengji and Nie, Liqiang and Xia, Lianghao and Huang, Chao},
  year = {2026},
  url = {https://arxiv.org/abs/2606.07649}
}

@misc{qu2026vincienext,
  title = {{VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling}},
  author = {Qu, Leigang and Cheng, Feng and Yang, Ziyan and Yang, Bangbang and Huang, Zhaoyang and Chow, Wei and Li, Yicong and Wang, Wenjie and Chua, Tat-Seng and Zeng, Yan},
  year = {2026},
  url = {https://arxiv.org/abs/2610.12104}
}

@misc{chen2026viper,
  title = {{VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation}},
  author = {Chen, Tianxiao and Chen, Hanmo and Chen, Huajin and Li, Bo and Ye, Qi and Jiang, Peng-Tao},
  year = {2026},
  url = {https://arxiv.org/abs/2607.23472}
}

@misc{liu2026visionwormhole,
  title = {{Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems}},
  author = {Liu, Xiaoze and Zhang, Ruowang and Yu, Weichen and Xiong, Siheng and He, Liu and Wu, Feijie and Jung, Hoin and Fredrikson, Matt and Wang, Xiaoqian and Gao, Jing},
  year = {2026},
  url = {https://arxiv.org/abs/2602.15382}
}

@misc{vista2025,
  title = {{VISTA: A Test-Time Self-Improving Video Generation Agent}},
  author = {Long, Do Xuan and Wan, Xingchen and Nakhost, Hootan and Lee, Chen-Yu and Pfister, Tomas and Arik, Sercan Ö.},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Long_VISTA_A_Test-Time_Self-Improving_Video_Generation_Agent_CVPR_2026_paper.html}
}

@misc{wu2026visualnewera,
  title = {{Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling}},
  author = {Wu, Keming and Yang, Zuhao and Zhang, Kaichen and Wang, Shizun and Zhu, Haowei and Leng, Sicong and Yang, Zhongyu and Wang, Qijie and Wang, Sudong and Wang, Ziting and Wang, Zili and Zhang, Hui and Wang, Haonan and Zhou, Hang and Pu, Yifan and Li, Xingxuan and Zhan, Fangneng and Li, Bo and Bing, Lidong and Song, Yuxin and Liu, Ziwei and Chen, Wenhu and Wang, Jingdong and Wang, Xinchao and Qi, Xiaojuan and Lu, Shijian and Wang, Bin},
  year = {2026},
  url = {https://arxiv.org/abs/2604.28185}
}

@misc{guo2026vlaw,
  title = {{VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model}},
  author = {Guo, Yanjiang and Lee, Tony and Shi, Lucy Xiaoyang and Chen, Jianyu and Liang, Percy and Finn, Chelsea},
  year = {2026},
  url = {https://arxiv.org/abs/2602.12063}
}

@misc{zhang2026vqinsight,
  title = {{VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning}},
  author = {Xuanyu Zhang and Weiqi Li and Shijie Zhao and Junlin Li and Li Zhang and Jian Zhang},
  year = {2026},
  url = {https://doi.org/10.1609/aaai.v40i15.38285}
}

@misc{song2026vqqa,
  title = {{VQQA: An Agentic Approach for Video Evaluation and Quality Improvement}},
  author = {Song, Yiwen and Pfister, Tomas and Song, Yale},
  year = {2026},
  url = {https://arxiv.org/abs/2603.12310}
}

@misc{wang2025vrthinker,
  title = {{VR-Thinker: Boosting Video Reward Models through Think-with-Image Reasoning}},
  author = {Wang, Qunzhong and Liu, Jie and Liang, Jiajun and Zhang, Yuanxing and Jiang, Yilei and Zheng, Yaozhi and Wang, Xintao and Wan, Pengfei and Yue, Xiangyu and Liu, Jiaheng},
  year = {2026},
  url = {https://arxiv.org/abs/2510.10518}
}

@misc{ye2026dreamzero,
  title = {{World Action Models are Zero-shot Policies}},
  author = {Ye, Seonghyeon and Ge, Yunhao and Zheng, Kaiyuan and Gao, Shenyuan and Yu, Sihyun and Kurian, George and Indupuru, Suneel and Tan, You Liang and Zhu, Chuning and Xiang, Jiannan and others},
  year = {2026},
  url = {https://arxiv.org/abs/2602.15922}
}

@misc{hou2026robotworldmodels,
  title = {{World Model for Robot Learning: A Comprehensive Survey}},
  author = {Hou, Bohan and Li, Gen and Jia, Jindou and An, Tuo and Guo, Xinying and Leng, Sicong and Geng, Haoran and Ze, Yanjie and Harada, Tatsuya and Torr, Philip and Mees, Oier and Pollefeys, Marc and Liu, Zhuang and Wu, Jiajun and Abbeel, Pieter and Malik, Jitendra and Du, Yilun and Yang, Jianfei},
  year = {2026},
  url = {https://arxiv.org/abs/2605.00080}
}

@misc{yao2026surveyn16,
  title = {{World Models for Embodied Intelligence: From Plausible to Controllable to Actionable}},
  author = {Yao, Nanjie and Wang, Hao and Cheng, Chong and Chen, Zhikang and Li, Wenzhe and Lyu, Jiafei and Shen, Li and Zhao, Peilin and Lu, Zongqing and Huang, Gao and Hoi, Steven and Tao, Dacheng and Ye, Deheng},
  year = {2026},
  url = {https://arxiv.org/abs/2609.16697}
}

@misc{wang2026surveyn20,
  title = {{World Models for Robotic Manipulation: A Survey}},
  author = {Wang, Fangyuan and Wang, Ziyuan and Pei, Guorui and Zhang, Mengshi and Liang, Canxi and Hu, Jun and Li, Zhongxuan and Wu, Jinsong and Han, Ning and Zhang, Zeqing and Qi, Jiaming and Wu, Hongmin and Zhang, Shiyao and Zheng, Pai and Pan, Jia and Navarro-Alarcon, David and Liu, Sichao and Zhou, Peng},
  year = {2026},
  url = {https://arxiv.org/abs/2606.00113}
}

@misc{chen2026wnm,
  title = {{World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration}},
  author = {Chen, Ye and Chen, Xuanhong and Zhu, Yupeng and Tan, Liming and Wan, Zhewen and Xiong, Yuxuan and Wang, Tielong and Liu, Jinfan and Zhang, Wuze and Zhang, Xiongzhen and Li, Feifei and Luo, Xianglin and Zhao, Zhehan and Zhang, Zhifan and Kou, Laisheng and Liang, Zhujin and Chen, Yugang and Chen, Muchun and Miao, Xu and Zhang, Yijing and Sheng, Xiaojie and Hu, Qiang and Chen, Jialiang and Zhang, Weimin and Zhang, Wenjun and Ni, Bingbing},
  year = {2026},
  url = {https://arxiv.org/abs/2606.31946}
}

@misc{lu2026surveyn17,
  title = {{World-Action Models for Robot Learning and Control: A Survey}},
  author = {Lu, Zuxing and Zhai, Hongjia and Wang, Guanzhi and Zeng, Huajian and Yang, Jiaqi and Liu, Jingyu and Cheng, Lei and Zhang, Yuantai and Qiu, Yuheng and Cheng, Zezhou and Laptev, Ivan and Xu, Danfei and Riviere, Benjamin and Loianno, Giuseppe and Xing, Eric and Zuo, Xingxing},
  year = {2026},
  url = {https://arxiv.org/abs/2609.16074}
}

@misc{shang2026worldarena,
  title = {{WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models}},
  author = {Shang, Yu and Li, Zhuohang and Ma, Yiding and Su, Weikang and others},
  year = {2026},
  url = {https://arxiv.org/abs/2602.08971}
}

@misc{sun2026worldplay,
  title = {{WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling}},
  author = {Sun, Wenqiang and Zhang, Haiyu and Wang, Haoyuan and Wu, Junta and Wang, Zehan and Wang, Zhenwei and Wang, Yunhong and Zhang, Jun and Wang, Tengfei and Guo, Chunchao},
  year = {2026},
  url = {https://arxiv.org/abs/2512.14614}
}

@misc{blenderagentic2025,
  title = {{3D Animation Generation Using Blender and Agentic AI}},
  author = {Shreya and Abhijit Jadhav and Sidharth Sinhasane and Prathmesh Vharkal and Alisha Borde},
  year = {2025},
  url = {https://doi.org/10.5220/0014628000004852}
}

@misc{li2025embodiedworldmodels,
  title = {{A Comprehensive Survey on World Models for Embodied AI}},
  author = {Li, Xinqing and He, Xin and Zhang, Le and Wu, Min and Li, Xiaoli and Liu, Yun},
  year = {2025},
  url = {https://arxiv.org/abs/2510.16732}
}

@misc{robeyns2025sica,
  title = {{A Self-Improving Coding Agent}},
  author = {Robeyns, Maxime and Szummer, Martin and Aitchison, Laurence},
  year = {2025},
  url = {https://arxiv.org/abs/2504.15228}
}

@misc{zhang2025surveyn18,
  title = {{A Step Toward World Models: A Survey on Robotic Manipulation}},
  author = {Zhang, Peng-Fei and Cheng, Ying and Sun, Xiaofan and Wang, Shijie and Li, Fengling and Zhu, Lei and Shen, Heng Tao},
  year = {2025},
  url = {https://arxiv.org/abs/2511.02097}
}

@misc{yu2025surveyn12,
  title = {{A Survey of Interactive Generative Video}},
  author = {Yu, Jiwen and Qin, Yiran and Che, Haoxuan and Liu, Quande and Wang, Xintao and Wan, Pengfei and Zhang, Di and Gai, Kun and Chen, Hao and Liu, Xihui},
  year = {2025},
  url = {https://arxiv.org/abs/2504.21853}
}

@misc{gao2025surveyr02,
  title = {{A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence}},
  author = {Gao, Huan-ang and Geng, Jiayi and Hua, Wenyue and Hu, Mengkang and Juan, Xinzhe and Liu, Hongzhang and Liu, Shilong and Qiu, Jiahao and Qi, Xuan and Wu, Yiran and Wang, Hongru and Xiao, Han and Zhou, Yuhang and Zhang, Shaokun and Zhang, Jiayi and Xiang, Jinyu and Fang, Yixiong and Zhao, Qiwen and Liu, Dongrui and Ren, Qihan and Qian, Cheng and Wang, Zhenhailong and Hu, Minda and Wang, Huazheng and Wu, Qingyun and Ji, Heng and Wang, Mengdi},
  year = {2025},
  url = {https://arxiv.org/abs/2507.21046}
}

@misc{yin2025spatiotemporal,
  title = {{A Survey: Spatiotemporal Consistency in Video Generation}},
  author = {Yin, Zhiyu and Chen, Kehai and Bai, Xuefeng and Jiang, Ruili and Li, Juntao and Li, Hongdong and Liu, Jin and Xiang, Yang and Yu, Jun and Zhang, Min},
  year = {2025},
  url = {https://arxiv.org/abs/2502.17863}
}

@misc{gao2025adaworld,
  title = {{AdaWorld: Learning Adaptable World Models with Latent Actions}},
  author = {Gao, Shenyuan and Zhou, Siyuan and Du, Yilun and Zhang, Jun and Gan, Chuang},
  year = {2025},
  url = {https://proceedings.mlr.press/v267/gao25u.html}
}

@misc{zhang2024aflow,
  title = {{AFlow: Automating Agentic Workflow Generation}},
  author = {Zhang, Jiayi and Xiang, Jinyu and Yu, Zhaoyang and Teng, Fengwei and Chen, Xionghui and Chen, Jiaqi and Zhuge, Mingchen and Cheng, Xin and Hong, Sirui and Wang, Jinlin and Zheng, Bingnan and Liu, Bang and Luo, Yuyu and Wu, Chenglin},
  year = {2025},
  url = {https://arxiv.org/abs/2410.10762}
}

@misc{wang2025awm,
  title = {{Agent Workflow Memory}},
  author = {Wang, Zora Zhiruo and Mao, Jiayuan and Fried, Daniel and Neubig, Graham},
  year = {2025},
  url = {https://proceedings.mlr.press/v267/wang25bx.html}
}

@misc{li2025agentdropout,
  title = {{AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration}},
  author = {Zhexuan Wang and Yutong Wang and Xuebo Liu and Liang Ding and Miao Zhang and Jie Liu and Min Zhang},
  year = {2025},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1170}
}

@misc{liu2025aigvemacs,
  title = {{AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation}},
  author = {Liu, Xiao and Zhang, Jiawei},
  year = {2025},
  url = {https://arxiv.org/abs/2507.01255}
}

@misc{animaker2025,
  title = {{AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation}},
  author = {Shi, Haoyuan and Li, Yunxin and Chen, Xinyu and Wang, Longyue and Hu, Baotian and Zhang, Min},
  year = {2025},
  url = {https://animaker-dev.github.io/}
}

@misc{anime2025,
  title = {{AniME: Adaptive Multi-Agent Planning for Long Animation Generation}},
  author = {Zhang, Lisai and Xu, Baohan and Yang, Siqian and Yin, Mingyu and Liu, Jing and Xu, Chao and Wang, Siqi and Wu, Yidi and Hong, Yuxin and Zhang, Zihao and Liang, Yanzhang and Jiang, Yudong},
  year = {2025},
  url = {https://doi.org/10.1145/3757374.3771455}
}

@misc{hu2024adas,
  title = {{Automated Design of Agentic Systems}},
  author = {Hu, Shengran and Lu, Cong and Clune, Jeff},
  year = {2025},
  url = {https://arxiv.org/abs/2408.08435}
}

@misc{wu2025movieagent,
  title = {{Automated Movie Generation via Multi-Agent CoT Planning}},
  author = {Wu, Weijia and Zhu, Zeyu and Shou, Mike Zheng},
  year = {2025},
  url = {https://arxiv.org/abs/2503.07314}
}

@misc{automv2025,
  title = {{AutoMV: An Automatic Multi-Agent System for Music Video Generation}},
  author = {Tang, Xiaoxuan and Lei, Xinping and Zhu, Chaoran and Chen, Shiyun and Yuan, Ruibin and Li, Yizhi and Oh, Changjae and Zhang, Ge and Huang, Wenhao and Benetos, Emmanouil and Liu, Yang and Liu, Jiaheng and Ma, Yinghao},
  year = {2025},
  url = {https://arxiv.org/abs/2512.12196}
}

@misc{automvrealestate2025,
  title = {{AutoMV: An Autonomous Agent Framework for Real Estate Marketing Video Generation}},
  author = {Kuizong Wu and Shaozu Yuan and Chang Shen and Long Xu and Meng Chen},
  year = {2025},
  url = {https://doi.org/10.1609/aaai.v39i28.35377}
}

@misc{chen2025code2video,
  title = {{Code2Video: A Code-centric Paradigm for Educational Video Generation}},
  author = {Chen, Yanzhe and Lin, Kevin Qinghong and Shou, Mike Zheng},
  year = {2025},
  url = {https://arxiv.org/abs/2510.01174}
}

@misc{yang2024cogvideox,
  title = {{CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer}},
  author = {Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and Yin, Da and Zhang, Yuxuan and Wang, Weihan and Cheng, Yean and Xu, Bin and Gu, Xiaotao and Dong, Yuxiao and Tang, Jie},
  year = {2025},
  url = {https://arxiv.org/abs/2408.06072}
}

@misc{comfygpt2025,
  title = {{ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation}},
  author = {Huang, Oucheng and Ma, Yuhang and Zhao, Zeng and Wu, Mingrui and Ji, Jiayi and Zhang, Rongsheng and Hu, Zhipeng and Sun, Xiaoshuai and Ji, Rongrong},
  year = {2025},
  url = {https://arxiv.org/abs/2503.17671}
}

@misc{comfymind2025,
  title = {{ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback}},
  author = {Guo, Litao and Xu, Xinli and Wang, Luozhou and Lin, Jiantao and Zhou, Jinsong and Zhang, Zixin and Su, Bolan and Chen, Ying-Cong},
  year = {2025},
  url = {https://arxiv.org/abs/2505.17908}
}

@misc{yu2025contextmemory,
  title = {{Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval}},
  author = {Yu, Jiwen and Bai, Jianhong and Qin, Yiran and Liu, Quande and Wang, Xintao and Wan, Pengfei and Zhang, Di and Liu, Xihui},
  year = {2025},
  url = {https://arxiv.org/abs/2506.03141}
}

@misc{ma2025controllablevideo,
  title = {{Controllable Video Generation: A Survey}},
  author = {Yue Ma and Kunyu Feng and Zhongyuan Hu and Xinyu Wang and Yucheng Wang and Mingzhe Zheng and Bingyuan Wang and Qinghe Wang and Xuanhua He and Hongfa Wang and Chenyang Zhu and Hongyu Liu and Yingqing He and Zeyu Wang and Zhifeng Li and Xiu Li and Sirui Han and Yike Guo and Wei Liu and Dan Xu and Linfeng Zhang and Qifeng Chen},
  year = {2025},
  url = {https://arxiv.org/abs/2507.16869}
}

@misc{wu2025corgi,
  title = {{Corgi: Cached Memory Guided Video Generation}},
  author = {Wu, Xindi and Singer, Uriel and Lin, Zhaojiang and Madotto, Andrea and Xia, Xide and Xu, Yifan and Crook, Paul and Dong, Xin Luna and Moon, Seungwhan},
  year = {2025},
  url = {https://doi.org/10.1109/WACV61041.2025.00450}
}

@misc{nvidia2025cosmos,
  title = {{Cosmos World Foundation Model Platform for Physical AI}},
  author = {NVIDIA and Agarwal, Niket and Ali, Arslan and Bala, Maciej and Balaji, Yogesh and Barker, Erik and Cai, Tiffany and others},
  year = {2025},
  url = {https://arxiv.org/abs/2501.03575}
}

@misc{xue2025dancegrpo,
  title = {{DanceGRPO: Unleashing GRPO on Visual Generation}},
  author = {Xue, Zeyue and Wu, Jie and Gao, Yu and Kong, Fangyuan and Zhu, Lingting and Chen, Mengzhao and Liu, Zhiheng and Liu, Wei and Guo, Qiushan and Huang, Weilin and Luo, Ping},
  year = {2025},
  url = {https://arxiv.org/abs/2505.07818}
}

@misc{valevski2025gamengen,
  title = {{Diffusion Models Are Real-Time Game Engines}},
  author = {Valevski, Dani and Leviathan, Yaniv and Arar, Moab and Fruchter, Shlomi},
  year = {2025},
  url = {https://arxiv.org/abs/2408.14837}
}

@misc{liang2025diffusionrenderer,
  title = {{Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models}},
  author = {Liang, Ruofan and Gojcic, Zan and Ling, Huan and Munkberg, Jacob and Hasselgren, Jon and Lin, Chih-Hao and Gao, Jun and Keller, Alexander and Vijaykumar, Nandita and Fidler, Sanja and Wang, Zian},
  year = {2025},
  url = {https://arxiv.org/abs/2501.18590}
}

@misc{sandoval2025editduet,
  title = {{EditDuet: A Multi-Agent System for Video Non-Linear Editing}},
  author = {Marcelo Sandoval-Castañeda and Bryan Russell and Josef Sivic and Gregory Shakhnarovich and Fabian Caba Heilbron},
  year = {2025},
  url = {https://doi.org/10.1145/3721238.3730761}
}

@misc{chi2025eva,
  title = {{Empowering World Models with Reflection for Embodied Video Prediction}},
  author = {Chi, Xiaowei and Fan, Chun-Kai and Zhang, Hengyuan and Qi, Xingqun and Zhang, Rongyu and Chen, Anthony and Chan, Chi-Min and Xue, Wei and Liu, Qifeng and Zhang, Shanghang and Guo, Yike},
  year = {2025},
  url = {https://proceedings.mlr.press/v267/chi25b.html}
}

@misc{zhang2025evaluationagent,
  title = {{Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models}},
  author = {Zhang, Fan and Tian, Shulin and Huang, Ziqi and Qiao, Yu and Liu, Ziwei},
  year = {2025},
  url = {https://aclanthology.org/2025.acl-long.374/}
}

@misc{savov2025autoexplore,
  title = {{Exploration-Driven Generative Interactive Environments}},
  author = {Savov, Nedko and Kazemi, Naser and Mahdi, Mohammad and Paudel, Danda Pani and Wang, Xi and Van Gool, Luc},
  year = {2025},
  url = {https://arxiv.org/abs/2504.02515}
}

@misc{lin2025physicscognitionsurvey,
  title = {{Exploring the Evolution of Physics Cognition in Video Generation: A Survey}},
  author = {Minghui Lin and Xiang Wang and Yishan Wang and Shu Wang and Fengqi Dai and Pengxiang Ding and Cunxiang Wang and Zhengrong Zuo and Nong Sang and Siteng Huang and Donglin Wang},
  year = {2025},
  url = {https://arxiv.org/abs/2503.21765}
}

@misc{hu2025filmagent,
  title = {{FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces}},
  author = {Xu, Zhenran and Wang, Longyue and Wang, Jifang and Li, Zhouyi and Shi, Senbao and Yang, Xue and Wang, Yiyu and Hu, Baotian and Yu, Jun and Zhang, Min},
  year = {2025},
  url = {https://arxiv.org/abs/2501.12909}
}

@misc{feng2025followyourinstruction,
  title = {{Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis}},
  author = {Feng, Kunyu and Ma, Yue and Zhang, Xinhua and Liu, Boshi and Yuluo, Yikuang and Zhang, Yinhan and Liu, Runtao and Liu, Hongyu and Qin, Zhiyuan and Mo, Shanhui and Chen, Qifeng and Wang, Zeyu},
  year = {2025},
  url = {https://arxiv.org/abs/2508.05580}
}

@misc{yin2025causvid,
  title = {{From Slow Bidirectional to Fast Autoregressive Video Diffusion Models}},
  author = {Yin, Tianwei and Zhang, Qiang and Zhang, Richard and Freeman, William T. and Durand, Fredo and Shechtman, Eli and Huang, Xun},
  year = {2025},
  url = {https://arxiv.org/abs/2412.07772}
}

@misc{he2025fulldit2,
  title = {{FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers}},
  author = {He, Xuanhua and Liu, Quande and Ye, Zixuan and Ye, Weicai and Wang, Qiulin and Wang, Xintao and Chen, Qifeng and Wan, Pengfei and Zhang, Di and Gai, Kun},
  year = {2025},
  url = {https://arxiv.org/abs/2506.04213}
}

@misc{che2025gamegenx,
  title = {{GameGen-X: Interactive Open-world Game Video Generation}},
  author = {Che, Haoxuan and He, Xuanhua and Liu, Quande and Jin, Cheng and Chen, Hao},
  year = {2025},
  url = {https://arxiv.org/abs/2411.00769}
}

@misc{parkerholder2025genie3,
  title = {{Genie 3: A New Frontier for World Models}},
  author = {Parker-Holder, Jack and Fruchter, Shlomi},
  year = {2025},
  url = {https://deepmind.google/blog/genie-3-a-new-frontier-for-world-models/}
}

@misc{hollywoodtown2025,
  title = {{Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration}},
  author = {Wei, Zheng and Li, Mingchen and Zhang, Zeqian and Yuan, Ruibin and Hui, Pan and Qu, Huamin and Evans, James and Agrawala, Maneesh and Rao, Anyi},
  year = {2025},
  url = {https://arxiv.org/abs/2510.22431}
}

@misc{liu2025videoalign,
  title = {{Improving Video Generation with Human Feedback}},
  author = {Liu, Jie and Liu, Gongye and Liang, Jiajun and Yuan, Ziyang and Liu, Xiaokun and Zheng, Mingwu and Wu, Xiele and Wang, Qiulin and Xia, Menghan and Wang, Xintao and Liu, Xiaohong and Yang, Fei and Wan, Pengfei and Zhang, Di and Gai, Kun and Yang, Yujiu and Ouyang, Wanli},
  year = {2025},
  url = {https://arxiv.org/abs/2501.13918}
}

@misc{dubois2025llmagents,
  title = {{Introduction to Training LLMs for AI Agents}},
  author = {Dubois, Yann},
  year = {2025},
  url = {https://rdi.berkeley.edu/agentic-ai/slides/lecture1.pdf}
}

@misc{wang2025koala,
  title = {{Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content}},
  author = {Wang, Qiuheng and Shi, Yukai and Ou, Jiarong and Chen, Rui and Lin, Ke and Wang, Jiahao and Jiang, Boyuan and Yang, Haotian and Zheng, Mingwu and Tao, Xin and Yang, Fei and Wan, Pengfei and Zhang, Di},
  year = {2025},
  url = {https://arxiv.org/abs/2410.08260}
}

@misc{zou2025latentmas,
  title = {{Latent Collaboration in Multi-Agent Systems}},
  author = {Zou, Jiaru and Qiu, Ruizhong and Li, Gaotang and Yang, Xiyuan and Tieu, Katherine and Lu, Pan and Shen, Ke and Tong, Hanghang and Choi, Yejin and He, Jingrui and Zou, James and Wang, Mengdi and Yang, Ling},
  year = {2025},
  url = {https://arxiv.org/abs/2511.20639}
}

@misc{guo2025lct,
  title = {{Long Context Tuning for Video Generation}},
  author = {Guo, Yuwei and Yang, Ceyuan and Yang, Ziyan and Ma, Zhibei and Lin, Zhijie and Yang, Zhenheng and Lin, Dahua and Jiang, Lu},
  year = {2025},
  url = {https://arxiv.org/abs/2503.10589}
}

@misc{chen2025longanimation,
  title = {{LongAnimation: Long Animation Generation with Dynamic Global-Local Memory}},
  author = {Chen, Nan and Huang, Mengqi and Meng, Yihao and Mao, Zhendong},
  year = {2025},
  url = {https://arxiv.org/abs/2507.01945}
}

@misc{manimator2025,
  title = {{Manimator: Transforming Research Papers into Visual Explanations}},
  author = {Samarth P and Jain, Vyoman and Golugula, Shiva and Sathvik, Motamarri Sai},
  year = {2025},
  url = {https://arxiv.org/abs/2507.14306}
}

@misc{yue2025masrouter,
  title = {{MasRouter: Learning to Route LLMs for Multi-Agent Systems}},
  author = {Yanwei Yue and Guibin Zhang and Boyang Liu and Guancheng Wan and Kun Wang and Dawei Cheng and Yiyan Qi},
  year = {2025},
  url = {https://doi.org/10.18653/v1/2025.acl-long.757}
}

@misc{he2025matrixgame2,
  title = {{Matrix-game 2.0: An open-source real-time and streaming interactive world model}},
  author = {He, Xianglong and Peng, Chunli and Liu, Zexiang and Wang, Boyang and Zhang, Yifan and Cui, Qi and Kang, Fei and Jiang, Biao and An, Mengyin and Ren, Yangyang and Xu, Baixin and Guo, Hao-Xiang and Gong, Kaixiong and Wu, Size and Li, Wei and Song, Xuchen and Liu, Yang and Li, Yangguang and Zhou, Yahui},
  year = {2025},
  url = {https://arxiv.org/abs/2508.13009}
}

@misc{shirakawa2025mggen,
  title = {{MG-Gen: Single Image to Motion Graphics Generation}},
  author = {Shirakawa, Takahiro and Suzuki, Tomoyuki and Narumoto, Takuto and Haraguchi, Daichi},
  year = {2025},
  url = {https://arxiv.org/abs/2504.02361}
}

@misc{mmstoryagent2025,
  title = {{MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio}},
  author = {Xu, Xuenan and Mei, Jiahao and Li, Chenliang and Wu, Yuning and Yan, Ming and Lai, Shaopeng and Zhang, Ji and Wu, Mengyue},
  year = {2025},
  url = {https://arxiv.org/abs/2503.05242}
}

@misc{mcp2025tools,
  title = {{Model Context Protocol Specification: Tools}},
  author = {Model Context Protocol},
  year = {2025},
  url = {https://modelcontextprotocol.io/specification/2025-06-18/server/tools}
}

@misc{motionagent2025,
  title = {{MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent}},
  author = {Liao, Xinyao and Zeng, Xianfang and Wang, Liao and Yu, Gang and Lin, Guosheng and Zhang, Chi},
  year = {2025},
  url = {https://openaccess.thecvf.com/content/ICCV2025/html/Liao_MotionAgent_Fine-grained_Controllable_Video_Generation_via_Motion_Field_Agent_ICCV_2025_paper.html}
}

@misc{ma2025mover,
  title = {{MoVer: Motion Verification for Motion Graphics Animations}},
  author = {Ma, Jiaju and Agrawala, Maneesh},
  year = {2025},
  url = {https://arxiv.org/abs/2502.13372}
}

@misc{nan2024openvid,
  title = {{OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation}},
  author = {Nan, Kepan and Xie, Rui and Zhou, Penghao and Fan, Tiehan and Yang, Zhenheng and Chen, Zhijie and Li, Xiang and Yang, Jian and Tai, Ying},
  year = {2025},
  url = {https://arxiv.org/abs/2407.02371}
}

@misc{paper2video2025,
  title = {{Paper2Video: Automatic Video Generation from Scientific Papers}},
  author = {Zhu, Zeyu and Lin, Kevin Qinghong and Shou, Mike Zheng},
  year = {2025},
  url = {https://arxiv.org/abs/2510.05096}
}

@misc{phyt2v2025,
  title = {{PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation}},
  author = {Xue, Qiyao and Yin, Xiangyu and Yang, Boyuan and Gao, Wei},
  year = {2025},
  url = {https://openaccess.thecvf.com/content/CVPR2025/html/Xue_PhyT2V_LLM-Guided_Iterative_Self-Refinement_for_Physics-Grounded_Text-to-Video_Generation_CVPR_2025_paper.html}
}

@misc{preacher2025,
  title = {{Preacher: Paper-to-Video Agentic System}},
  author = {Jingwei Liu and Ling Yang and Hao Luo and Fan Wang and Hongyan Li and Mengdi Wang},
  year = {2025},
  url = {https://arxiv.org/abs/2508.09632}
}

@misc{wu2025surveyn05,
  title = {{Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing}},
  author = {Wu, Sihao and Si, Xiaonan and Xing, Chi and Wang, Jianhong and Jin, Gaojie and Cheng, Guangliang and Zhang, Lijun and Huang, Xiaowei},
  year = {2025},
  url = {https://arxiv.org/abs/2502.07829}
}

@misc{presentagent2025,
  title = {{PresentAgent: Multimodal Agent for Presentation Video Generation}},
  author = {Jingwei Shi and Zeyu Zhang and Biao Wu and Yanjie Liang and Meng Fang and Ling Chen and Yang Zhao},
  year = {2025},
  url = {https://doi.org/10.18653/v1/2025.emnlp-demos.58}
}

@misc{rbmark2025,
  title = {{RBMark: Robust and blind video watermark in DT CWT domain}},
  author = {Huang, I.-Chun and Wu, Ji-Yan and Ooi, Wei Tsang},
  year = {2025},
  url = {https://doi.org/10.1016/j.jvcir.2025.104438}
}

@misc{wu2025rewarddance,
  title = {{Rewarddance: Reward scaling in visual generation}},
  author = {Wu, Jie and Gao, Yu and Ye, Zilyu and Li, Ming and Li, Liang and Guo, Hanzhong and Liu, Jie and Xue, Zeyue and Hou, Xiaoxia and Liu, Wei and others},
  year = {2025},
  url = {https://arxiv.org/abs/2509.08826}
}

@misc{huang2025selfforcing,
  title = {{Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion}},
  author = {Huang, Xun and Li, Zhengqi and He, Guande and Zhou, Mingyuan and Shechtman, Eli},
  year = {2025},
  url = {https://arxiv.org/abs/2506.08009}
}

@misc{sepvamark2025,
  title = {{SepVAMark: Deep Separable Visual-Audio Fusion Watermarking for Source Tracing and Deepfake Detection}},
  author = {Zhang, Chuan and Li, Zihan and Xu, Zihao and Ren, Xuhao and Zhu, Liehuang},
  year = {2025},
  url = {https://doi.org/10.1145/3746027.3755783}
}

@misc{sima2025sima2,
  title = {{SIMA 2: A Generalist Embodied Agent for Virtual Worlds}},
  author = {SIMA Team},
  year = {2025},
  url = {https://arxiv.org/abs/2512.04797}
}

@misc{yue2025surveyn13,
  title = {{Simulating the Visual World with Artificial Intelligence: A Roadmap}},
  author = {Yue, Jingtong and Huang, Ziqi and Chen, Zhaoxi and Wang, Xintao and Wan, Pengfei and Liu, Ziwei},
  year = {2025},
  url = {https://arxiv.org/abs/2511.08585}
}

@misc{chinchure2025spotlight,
  title = {{Spotlight: Identifying and Localizing Video Generation Errors Using VLMs}},
  author = {Chinchure, Aditya and Ravi, Sahithya and Shukla, Pushkar and Shwartz, Vered and Sigal, Leonid},
  year = {2025},
  url = {https://arxiv.org/abs/2511.18102}
}

@misc{zhang2025storymem,
  title = {{StoryMem: Multi-shot Long Video Storytelling with Memory}},
  author = {Zhang, Kaiwen and Jiang, Liming and Wang, Angtian and Fang, Jacob Zhiyuan and Zhi, Tiancheng and Yan, Qing and Kang, Hao and Lu, Xin and Pan, Xingang},
  year = {2025},
  url = {https://arxiv.org/abs/2512.19539}
}

@misc{peng2025svbench,
  title = {{SVBench: Evaluation of Video Generation Models on Social Reasoning}},
  author = {Wenshuo Peng and Gongxuan Wang and Tianmeng Yang and Chuanhao Li and Xiaojie Xu and Hui He and Kaipeng Zhang},
  year = {2025},
  url = {https://arxiv.org/abs/2512.21507}
}

@misc{wang2023videofactory,
  title = {{Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation}},
  author = {Wang, Wenjing and Yang, Huan and Tuo, Zixi and He, Huiguo and Zhu, Junchen and Fu, Jianlong and Liu, Jiaying},
  year = {2025},
  url = {https://arxiv.org/abs/2305.10874}
}

@misc{sun2025t2vcompbench,
  title = {{T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation}},
  author = {Sun, Kaiyue and Huang, Kaiyi and Liu, Xian and Wu, Yue and Xu, Zihan and Li, Zhenguo and Liu, Xihui},
  year = {2025},
  url = {https://arxiv.org/abs/2407.14505}
}

@misc{li2025t2vturbov2,
  title = {{T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design}},
  author = {Li, Jiachen and Long, Qian and Zheng, Jian and Gao, Xiaofeng and Piramuthu, Robinson and Chen, Wenhu and Wang, William Yang},
  year = {2025},
  url = {https://arxiv.org/abs/2410.05677}
}

@misc{theoremexplainagent2025,
  title = {{TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding}},
  author = {Max Ku and Cheuk Hei Chong and Jonathan Leung and Krish Shah and Alvin Yu and Wenhu Chen},
  year = {2025},
  url = {https://aclanthology.org/2025.acl-long.332/}
}

@misc{liang2025univa,
  title = {{UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist}},
  author = {Liang, Zhengyang and Zhang, Daoan and Zhou, Huichi and Huang, Rui and Li, Bobo and Zhang, Yuechen and Wu, Shengqiong and Wang, Xiaohan and Luo, Jiebo and Liao, Lizi and Fei, Hao},
  year = {2025},
  url = {https://arxiv.org/abs/2511.08521}
}

@misc{liu2025uve,
  title = {{UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?}},
  author = {Liu, Yuanxin and Zhu, Rui and Ren, Shuhuai and Wang, Jiacong and Guo, Haoyuan and Sun, Xu and Jiang, Lu},
  year = {2025},
  url = {https://arxiv.org/abs/2503.09949}
}

@misc{vace2025,
  title = {{VACE: All-in-One Video Creation and Editing}},
  author = {Jiang, Zeyinzi and Han, Zhen and Mao, Chaojie and Zhang, Jingfeng and Pan, Yulin and Liu, Yu},
  year = {2025},
  url = {https://openaccess.thecvf.com/content/ICCV2025/html/Jiang_VACE_All-in-One_Video_Creation_and_Editing_ICCV_2025_paper.html}
}

@misc{zheng2025vbench2,
  title = {{VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness}},
  author = {Zheng, Dian and Huang, Ziqi and Liu, Hongbo and Zou, Kai and He, Yinan and Zhang, Fan and Gu, Lulu and Zhang, Yuanhan and He, Jingwen and Zheng, Wei-Shi and Qiao, Yu and Liu, Ziwei},
  year = {2025},
  url = {https://arxiv.org/abs/2503.21755}
}

@misc{zhang2025vcagent,
  title = {{VC-Agent: An Interactive Agent for Customized Video Dataset Collection}},
  author = {Zhang, Yidan and Xu, Mutian and Hao, Yiming and Zhou, Kun and Chang, Jiahao and Liu, Xiaoqiang and Wan, Pengfei and Fu, Hongbo and Han, Xiaoguang},
  year = {2025},
  url = {https://arxiv.org/abs/2509.21291}
}

@misc{wu2025spatialmemory,
  title = {{Video World Models with Long-term Spatial Memory}},
  author = {Wu, Tong and Yang, Shuai and Po, Ryan and Xu, Yinghao and Liu, Ziwei and Lin, Dahua and Wetzstein, Gordon},
  year = {2025},
  url = {https://arxiv.org/abs/2506.05284}
}

@misc{bian2025videoasprompt,
  title = {{Video-As-Prompt: Unified Semantic Control for Video Generation}},
  author = {Bian, Yuxuan and Chen, Xin and Li, Zenan and Zhi, Tiancheng and Sang, Shen and Luo, Linjie and Xu, Qiang},
  year = {2025},
  url = {https://arxiv.org/abs/2510.20888}
}

@misc{han2025videobench,
  title = {{Video-Bench: Human-Aligned Video Generation Benchmark}},
  author = {Han, Hui and Li, Siyuan and Chen, Jiaqi and Yuan, Yiwen and Wu, Yuling and Deng, Yufan and Leong, Chak Tou and Du, Hanwen and Fu, Junchen and Li, Youhua and Zhang, Jie and Zhang, Chi and Li, Li-jia and Ni, Yongxin},
  year = {2025},
  url = {https://arxiv.org/abs/2504.04907}
}

@misc{liu2025videodpo,
  title = {{VideoDPO: Omni-Preference Alignment for Video Diffusion Generation}},
  author = {Liu, Runtao and Wu, Haoyu and Zheng, Ziqiang and Wei, Chen and He, Yingqing and Pi, Renjie and Chen, Qifeng},
  year = {2025},
  url = {https://arxiv.org/abs/2412.14167}
}

@misc{yang2025videogeneval,
  title = {{VideoGen-Eval: Agent-based System for Video Generation Evaluation}},
  author = {Yang, Yuhang and Fan, Ke and Sun, Shangkun and Li, Hongxiang and Zeng, Ailing and Han, FeiLin and Zhai, Wei and Liu, Wei and Cao, Yang and Zha, Zheng-Jun},
  year = {2025},
  url = {https://arxiv.org/abs/2503.23452}
}

@misc{bansal2024videophy,
  title = {{VideoPhy: Evaluating Physical Commonsense for Video Generation}},
  author = {Bansal, Hritik and Lin, Zongyu and Xie, Tianyi and Zong, Zeshun and Yarom, Michal and Bitton, Yonatan and Jiang, Chenfanfu and Sun, Yizhou and Chang, Kai-Wei and Grover, Aditya},
  year = {2025},
  url = {https://arxiv.org/abs/2406.03520}
}

@misc{videoshield2025,
  title = {{VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking}},
  author = {Hu, Runyi and Zhang, Jie and Li, Yiming and Li, Jiwei and Guo, Qing and Qiu, Han and Zhang, Tianwei},
  year = {2025},
  url = {https://proceedings.iclr.cc/paper_files/paper/2025/hash/8227285e32f70e07fa3a247f3a48006d-Abstract-Conference.html}
}

@misc{wang2025videotree,
  title = {{VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos}},
  author = {Wang, Ziyang and Yu, Shoubin and Stengel-Eskin, Elias and Yoon, Jaehong and Cheng, Feng and Bertasius, Gedas and Bansal, Mohit},
  year = {2025},
  url = {https://arxiv.org/abs/2405.19209}
}

@misc{wang2025videoufo,
  title = {{VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation}},
  author = {Wang, Wenhao and Yang, Yi},
  year = {2025},
  url = {https://arxiv.org/abs/2503.01739}
}

@misc{li2025vmem,
  title = {{VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory}},
  author = {Li, Runjia and Torr, Philip and Vedaldi, Andrea and Jakab, Tomas},
  year = {2025},
  url = {https://arxiv.org/abs/2506.18903}
}

@misc{wan2025wan,
  title = {{Wan: Open and advanced large-scale video generative models}},
  author = {Wan, Team and Wang, Ang and Ai, Baole and Wen, Bin and Mao, Chaojie and Xie, Chen-Wei and Chen, Di and Yu, Feiwu and Zhao, Haiming and Yang, Jianxiao and others},
  year = {2025},
  url = {https://arxiv.org/abs/2503.20314}
}

@misc{xiao2025worldmem,
  title = {{WorldMem: Long-term Consistent World Simulation with Memory}},
  author = {Xiao, Zeqi and Lan, Yushi and Zhou, Yifan and Ouyang, Wenqi and Yang, Shuai and Zeng, Yanhong and Pan, Xingang},
  year = {2025},
  url = {https://arxiv.org/abs/2504.12369}
}

@misc{duan2025worldscore,
  title = {{WorldScore: A Unified Evaluation Benchmark for World Generation}},
  author = {Duan, Haoyi and Yu, Hong-Xing and Chen, Sirui and Fei-Fei, Li and Wu, Jiajun},
  year = {2025},
  url = {https://openaccess.thecvf.com/content/ICCV2025/papers/Duan_WorldScore_A_Unified_Evaluation_Benchmark_for_World_Generation_ICCV_2025_paper.pdf}
}

@misc{song2025worldwander,
  title = {{WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation}},
  author = {Song, Quanjian and Song, Yiren and Peng, Kelly and Gao, Yuan and Shou, Mike Zheng},
  year = {2025},
  url = {https://arxiv.org/abs/2511.22098}
}

@misc{lei2024humanvideosurvey,
  title = {{A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights}},
  author = {Wentao Lei and Jinting Wang and Fengji Ma and Guanjie Huang and Li Liu},
  year = {2024},
  url = {https://arxiv.org/abs/2407.08428}
}

@misc{liu2024videogenerationevaluation,
  title = {{A Survey of AI-Generated Video Evaluation}},
  author = {Liu, Xiao and Xiang, Xinhao and Li, Zizhong and Wang, Yongheng and Li, Zhuoheng and Liu, Zhuosheng and Zhang, Weidi and Ye, Weiqi and Zhang, Jiawei},
  year = {2024},
  url = {https://arxiv.org/abs/2410.19884}
}

@misc{li2024longvideosurvey,
  title = {{A Survey on Long Video Generation: Challenges, Methods, and Prospects}},
  author = {Chengxuan Li and Di Huang and Zeyu Lu and Yang Xiao and Qingqi Pei and Lei Bai},
  year = {2024},
  url = {https://arxiv.org/abs/2403.16407}
}

@misc{tao2024surveyr01,
  title = {{A Survey on Self-Evolution of Large Language Models}},
  author = {Tao, Zhengwei and Lin, Ting-En and Chen, Xiancai and Li, Hangyu and Wu, Yuchuan and Li, Yongbin and Jin, Zhi and Huang, Fei and Tao, Dacheng and Zhou, Jingren},
  year = {2024},
  url = {https://arxiv.org/abs/2404.14387}
}

@misc{wang2024aesopagent,
  title = {{AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production}},
  author = {Wang, Jiuniu and Du, Zehua and Zhao, Yuyuan and Yuan, Bo and Wang, Kexiang and Liang, Jian and Zhao, Yaxi and Lu, Yihen and Li, Gengliang and Gao, Junlong and Tu, Xin and Guo, Zhenyu},
  year = {2024},
  url = {https://arxiv.org/abs/2403.07952}
}

@misc{liu2024aicl,
  title = {{AICL: Action In-Context Learning for Video Diffusion Model}},
  author = {Liu, Jianzhi and Zhu, Junchen and Gao, Lianli and Shen, Heng Tao and Song, Jingkuan},
  year = {2024},
  url = {https://arxiv.org/abs/2403.11535}
}

@misc{liu2024surveyn11,
  title = {{Alignment of Diffusion Models: Fundamentals, Challenges, and Future}},
  author = {Liu, Buhua and Shao, Shitong and Li, Bao and Bai, Lichen and Xu, Zhiqiang and Xiong, Haoyi and Kwok, James and Helal, Sumi and Xie, Zeke},
  year = {2024},
  url = {https://arxiv.org/abs/2409.07253}
}

@misc{animdirector2024,
  title = {{Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation}},
  author = {Li, Yunxin and Shi, Haoyuan and Hu, Baotian and Wang, Longyue and Zhu, Jiashun and Xu, Jinyi and Zhao, Zhen and Zhang, Min},
  year = {2024},
  url = {https://doi.org/10.1145/3680528.3687688}
}

@misc{guo2024animatediff,
  title = {{AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning}},
  author = {Yuwei Guo and Ceyuan Yang and Anyi Rao and Zhengyang Liang and Yaohui Wang and Yu Qiao and Maneesh Agrawala and Dahua Lin and Bo Dai},
  year = {2024},
  url = {https://proceedings.iclr.cc/paper_files/paper/2024/hash/94894cf9bab20c00f6eaaff3b7f2be70-Abstract-Conference.html}
}

@misc{gao2024assisteditor,
  title = {{AssistEditor: Multi-Agent Collaboration for GUI Workflow Automation in Video Creation}},
  author = {Gao, Difei and Hu, Siyuan and Bai, Zechen and Lin, Qinghong and Shou, Mike Zheng},
  year = {2024},
  url = {https://doi.org/10.1145/3664647.3684998}
}

@misc{xiong2024surveyn06,
  title = {{Autoregressive Models in Vision: A Survey}},
  author = {Xiong, Jing and Liu, Gongye and Huang, Lun and Wu, Chengyue and Wu, Taiqiang and Mu, Yao and Yao, Yuan and Shen, Hui and Wan, Zhongwei and Huang, Jinfa and Tao, Chaofan and Yan, Shen and Yao, Huaxiu and Kong, Lingpeng and Yang, Hongxia and Zhang, Mi and Sapiro, Guillermo and Luo, Jiebo and Luo, Ping and Wong, Ngai},
  year = {2024},
  url = {https://arxiv.org/abs/2411.05902}
}

@misc{comfybench2024,
  title = {{ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems}},
  author = {Xue, Xiangyuan and Lu, Zeyu and Huang, Di and Wang, Zidong and Ouyang, Wanli and Bai, Lei},
  year = {2024},
  url = {https://arxiv.org/abs/2409.01392}
}

@misc{cao2024surveyn04,
  title = {{Controllable Generation with Text-to-Image Diffusion Models: A Survey}},
  author = {Cao, Pu and Zhou, Feng and Song, Qing and Yang, Lu},
  year = {2024},
  url = {https://arxiv.org/abs/2403.04279}
}

@misc{huang2024surveyn03,
  title = {{Diffusion Model-Based Image Editing: A Survey}},
  author = {Huang, Yi and Huang, Jiancheng and Liu, Yifan and Yan, Mingfu and Lv, Jiaxi and Liu, Jianzhuang and Xiong, Wei and Zhang, He and Cao, Liangliang and Chen, Shifeng},
  year = {2024},
  url = {https://arxiv.org/abs/2402.17525}
}

@misc{sun2024videoeditingsurvey,
  title = {{Diffusion Model-Based Video Editing: A Survey}},
  author = {Wenhao Sun and Rong-Cheng Tu and Jingyi Liao and Dacheng Tao},
  year = {2024},
  url = {https://arxiv.org/abs/2407.07111}
}

@misc{xie2024dreamfactory,
  title = {{DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework}},
  author = {Xie, Zhifei and Tang, Daniel and Tan, Dingwei and Klein, Jacques and Bissyand, Tegawend F. and Ezzini, Saad},
  year = {2024},
  url = {https://arxiv.org/abs/2408.11788}
}

@misc{wang2024dreamrunner,
  title = {{DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation}},
  author = {Wang, Zun and Li, Jialu and Lin, Han and Yoon, Jaehong and Bansal, Mohit},
  year = {2024},
  url = {https://arxiv.org/abs/2411.16657}
}

@misc{liu2024evalcrafter,
  title = {{EvalCrafter: Benchmarking and Evaluating Large Video Generation Models}},
  author = {Liu, Yaofang and Cun, Xiaodong and Liu, Xuebo and Wang, Xintao and Zhang, Yong and Chen, Haoxin and Liu, Yang and Zeng, Tieyong and Chan, Raymond and Shan, Ying},
  year = {2024},
  url = {https://openaccess.thecvf.com/content/CVPR2024/html/Liu_EvalCrafter_Benchmarking_and_Evaluating_Large_Video_Generation_Models_CVPR_2024_paper.html}
}

@misc{zhao2024expel,
  title = {{ExpeL: LLM Agents Are Experiential Learners}},
  author = {Zhao, Andrew and Huang, Daniel and Xu, Quentin and Lin, Matthieu and Liu, Yong-Jin and Huang, Gao},
  year = {2024},
  url = {https://doi.org/10.1609/aaai.v38i17.29936}
}

@misc{filmagent2024,
  title = {{FilmAgent: Automating Virtual Film Production Through a Multi-Agent Collaborative Framework}},
  author = {Zhenran Xu and Jifang Wang and Longyue Wang and Zhouyi Li and Senbao Shi and Baotian Hu and Min Zhang},
  year = {2024},
  url = {https://doi.org/10.1145/3681758.3698014}
}

@misc{liu2024fvmd,
  title = {{Frechet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos}},
  author = {Liu, Jiahe and Qu, Youran and Yan, Qi and Zeng, Xiaohui and Wang, Lele and Liao, Renjie},
  year = {2024},
  url = {https://arxiv.org/abs/2407.16124}
}

@misc{shen2024datastory,
  title = {{From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems}},
  author = {Shen, Leixian and Li, Haotian and Wang, Yun and Qu, Huamin},
  year = {2024},
  url = {https://arxiv.org/abs/2408.03876}
}

@misc{sun2024sorasurvey,
  title = {{From Sora What We Can See: A Survey of Text-to-Video Generation}},
  author = {Rui Sun and Yumin Zhang and Tejal Shah and Jiahao Sun and Shuoying Zhang and Wenqi Li and Haoran Duan and Bo Wei and Rajiv Ranjan},
  year = {2024},
  url = {https://arxiv.org/abs/2405.10674}
}

@misc{bruce2024genie,
  title = {{Genie: Generative Interactive Environments}},
  author = {Bruce, Jake and Dennis, Michael D. and Edwards, Ashley and Parker-Holder, Jack and Shi, Yuge and Hughes, Edward and Lai, Matthew and Mavalankar, Aditi and Steigerwald, Richie and Apps, Chris and Aytar, Yusuf and Bechtle, Sarah Maria Elisabeth and Behbahani, Feryal and Chan, Stephanie C. Y. and Heess, Nicolas and Gonzalez, Lucy and Osindero, Simon and Ozair, Sherjil and Reed, Scott and Zhang, Jingwei and Zolna, Konrad and Clune, Jeff and de Freitas, Nando and Singh, Satinder and Rocktaschel, Tim},
  year = {2024},
  url = {https://proceedings.mlr.press/v235/bruce24a.html}
}

@misc{lv2024gpt4motion,
  title = {{GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning}},
  author = {Lv, Jiaxi and Huang, Yi and Yan, Mingfu and Huang, Jiancheng and Liu, Jianzhuang and Liu, Yifan and Wen, Yafei and Chen, Xiaoxin and Chen, Shifeng},
  year = {2024},
  url = {https://arxiv.org/abs/2311.12631}
}

@misc{kong2024hunyuanvideo,
  title = {{HunyuanVideo: A Systematic Framework For Large Video Generative Models}},
  author = {Kong, Weijie and Tian, Qi and Zhang, Zijian and Min, Rox and Dai, Zuozhuo and Zhou, Jin and Xiong, Jiangfeng and Li, Xin and Wu, Bo and Zhang, Jianwei and others},
  year = {2024},
  url = {https://arxiv.org/abs/2412.03603}
}

@misc{yuan2024instructvideo,
  title = {{InstructVideo: Instructing Video Diffusion Models with Human Feedback}},
  author = {Yuan, Hangjie and Zhang, Shiwei and Wang, Xiang and Wei, Yujie and Feng, Tao and Pan, Yining and Zhang, Yingya and Liu, Ziwei and Albanie, Samuel and Ni, Dong},
  year = {2024},
  url = {https://arxiv.org/abs/2312.12490}
}

@misc{tseng2024keyframer,
  title = {{Keyframer: Empowering Animation Design using Large Language Models}},
  author = {Tseng, Tiffany and Cheng, Ruijia and Nichols, Jeffrey},
  year = {2024},
  url = {https://arxiv.org/abs/2402.06071}
}

@misc{he2024kubrick,
  title = {{Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation}},
  author = {He, Liu and Song, Yizhi and Huang, Hejun and Liu, Pinxin and Tang, Yunlong and Aliaga, Daniel and Zhou, Xin},
  year = {2024},
  url = {https://arxiv.org/abs/2408.10453}
}

@misc{zhou2024lats,
  title = {{Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models}},
  author = {Zhou, Andy and Yan, Kai and Shlapentokh-Rothman, Michal and Wang, Haohan and Wang, Yu-Xiong},
  year = {2024},
  url = {https://arxiv.org/abs/2310.04406}
}

@misc{wang2024lave,
  title = {{LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing}},
  author = {Bryan Wang and Yuliang Li and Zhaoyang Lv and Haijun Xia and Yan Xu and Raj Sodhi},
  year = {2024},
  url = {https://doi.org/10.1145/3640543.3645143}
}

@misc{yang2024unisim,
  title = {{Learning Interactive Real-World Simulators}},
  author = {Yang, Sherry and Du, Yilun and Ghasemipour, Seyed Kamyar Seyed and Tompson, Jonathan and Kaelbling, Leslie Pack and Schuurmans, Dale and Abbeel, Pieter},
  year = {2024},
  url = {https://openreview.net/forum?id=sFyTZEqmUY}
}

@misc{lian2024llmgrounded,
  title = {{LLM-grounded Video Diffusion Models}},
  author = {Lian, Long and Shi, Baifeng and Yala, Adam and Darrell, Trevor and Li, Boyi},
  year = {2024},
  url = {https://arxiv.org/abs/2309.17444}
}

@misc{he2024llmsgenerationediting,
  title = {{LLMs Meet Multimodal Generation and Editing: A Survey}},
  author = {Yingqing He and Zhaoyang Liu and Jingye Chen and Zeyue Tian and Hongyu Liu and Xiaowei Chi and Runtao Liu and Ruibin Yuan and Yazhou Xing and Wenhai Wang and Jifeng Dai and Yong Zhang and Wei Xue and Qifeng Liu and Yike Guo and Qifeng Chen},
  year = {2024},
  url = {https://arxiv.org/abs/2405.19334}
}

@misc{bartal2024lumiere,
  title = {{Lumiere: A Space-Time Diffusion Model for Video Generation}},
  author = {Bar-Tal, Omer and Chefer, Hila and Tov, Omer and Herrmann, Charles and Paiss, Roni and Zada, Shiran and Ephrat, Ariel and Hur, Junhwa and Liu, Guanghui and Raj, Amit and Li, Yuanzhen and Rubinstein, Michael and Michaeli, Tomer and Wang, Oliver and Sun, Deqing and Dekel, Tali and Mosseri, Inbar},
  year = {2024},
  url = {https://arxiv.org/abs/2401.12945}
}

@misc{he2024malmm,
  title = {{MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding}},
  author = {He, Bo and Li, Hengduo and Jang, Young Kyun and Jia, Menglin and Cao, Xuefei and Shah, Ashish and Shrivastava, Abhinav and Lim, Ser-Nam},
  year = {2024},
  url = {https://arxiv.org/abs/2404.05726}
}

@misc{yuan2024mora,
  title = {{Mora: Enabling Generalist Video Generation via A Multi-Agent Framework}},
  author = {Yuan, Zhengqing and Liu, Yixin and Cao, Yihan and Sun, Weixiang and Jia, Haolong and Chen, Ruoxi and Li, Zhaoxu and Lin, Bin and Yuan, Li and He, Lifang and Wang, Chi and Ye, Yanfang and Sun, Lichao},
  year = {2024},
  url = {https://arxiv.org/abs/2403.13248}
}

@misc{li2024moreagents,
  title = {{More Agents Is All You Need}},
  author = {Li, Junyou and Zhang, Qin and Yu, Yangbin and Fu, Qiang and Ye, Deheng},
  year = {2024},
  url = {https://arxiv.org/abs/2402.05120}
}

@misc{zhai2024motion,
  title = {{Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation}},
  author = {Zhai, Yuanhao and Lin, Kevin and Yang, Zhengyuan and Li, Linjie and Wang, Jianfeng and Lin, Chung-Ching and Doermann, David and Yuan, Junsong and Wang, Lijuan},
  year = {2024},
  url = {https://arxiv.org/abs/2406.06890}
}

@misc{zhao2023motiondirector,
  title = {{MotionDirector: Motion Customization of Text-to-Video Diffusion Models}},
  author = {Zhao, Rui and Gu, Yuchao and Wu, Jay Zhangjie and Zhang, David Junhao and Liu, Jiawei and Wu, Weijia and Keppo, Jussi and Shou, Mike Zheng},
  year = {2024},
  url = {https://arxiv.org/abs/2310.08465}
}

@misc{song2024moviechat,
  title = {{MovieChat: From Dense Token to Sparse Memory for Long Video Understanding}},
  author = {Song, Enxin and Chai, Wenhao and Wang, Guanhong and Zhang, Yucheng and Zhou, Haoyang and Wu, Feiyang and Chi, Haozhe and Guo, Xun and Ye, Tian and Zhang, Yanting and Lu, Yan and Hwang, Jenq-Neng and Wang, Gaoang},
  year = {2024},
  url = {https://arxiv.org/abs/2307.16449}
}

@misc{ge2024contentbias,
  title = {{On the Content Bias in Frechet Video Distance}},
  author = {Ge, Songwei and Mahapatra, Aniruddha and Parmar, Gaurav and Zhu, Jun-Yan and Huang, Jia-Bin},
  year = {2024},
  url = {https://arxiv.org/abs/2404.12391}
}

@misc{xie2024osworld,
  title = {{OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments}},
  author = {Xie, Tianbao and Zhang, Danyang and Chen, Jixuan and Li, Xiaochuan and Zhao, Siheng and Cao, Ruisheng and Hua, Toh Jing and Cheng, Zhoujun and Shin, Dongchan and Lei, Fangyu and Liu, Yitao and Xu, Yiheng and Zhou, Shuyan and Savarese, Silvio and Xiong, Caiming and Zhong, Victor and Yu, Tao},
  year = {2024},
  url = {https://arxiv.org/abs/2404.07972}
}

@misc{chen2024panda,
  title = {{Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers}},
  author = {Chen, Tsai-Shien and Siarohin, Aliaksandr and Menapace, Willi and Deyneka, Ekaterina and Chao, Hsiang-wei and Jeon, Byung Eun and Fang, Yuwei and Lee, Hsin-Ying and Ren, Jian and Yang, Ming-Hsuan and Tulyakov, Sergey},
  year = {2024},
  url = {https://arxiv.org/abs/2402.19479}
}

@misc{dai2024safesora,
  title = {{SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset}},
  author = {Dai, Josef and Chen, Tianle and Wang, Xuyao and Yang, Ziran and Chen, Taiye and Ji, Jiaming and Yang, Yaodong},
  year = {2024},
  url = {https://arxiv.org/abs/2406.14477}
}

@misc{niu2024screenagent,
  title = {{ScreenAgent: A Vision Language Model-driven Computer Control Agent}},
  author = {Niu, Runliang and Li, Jindong and Wang, Shiqi and Fu, Yali and Hu, Xiyu and Leng, Xueyuan and Kong, He and Chang, Yi and Wang, Qi},
  year = {2024},
  url = {https://arxiv.org/abs/2402.07945}
}

@misc{alemohammad2024mad,
  title = {{Self-Consuming Generative Models Go MAD}},
  author = {Alemohammad, Sina and Casco-Rodriguez, Josue and Luzi, Lorenzo and Humayun, Ahmed Imtiaz and Babaei, Hossein and LeJeune, Daniel and Siahkoohi, Ali and Baraniuk, Richard G.},
  year = {2024},
  url = {https://arxiv.org/abs/2307.01850}
}

@misc{chen2024sharegpt4video,
  title = {{ShareGPT4Video: Improving Video Understanding and Generation with Better Captions}},
  author = {Chen, Lin and Wei, Xilin and Li, Jinsong and Dong, Xiaoyi and Zhang, Pan and Zang, Yuhang and Chen, Zehui and Duan, Haodong and Lin, Bin and Tang, Zhenyu and Yuan, Li and Qiao, Yu and Lin, Dahua and Zhao, Feng and Wang, Jiaqi},
  year = {2024},
  url = {https://arxiv.org/abs/2406.04325}
}

@misc{puspitasari2024soraworldsurvey,
  title = {{Sora as a World Model? A Complete Survey on Text-to-Video Generation}},
  author = {Fachrina Dewi Puspitasari and Chaoning Zhang and Joseph Cho and Adnan Haider and Noor Ul Eman and Omer Amin and Alexis Mankowski and Muhammad Umair and Jingyao Zheng and Sheng Zheng and Lik-Hang Lee and Caiyan Qin and Tae-Ho Kim and Choong Seon Hong and Yang Yang and Heng Tao Shen},
  year = {2024},
  url = {https://arxiv.org/abs/2403.05131}
}

@misc{hu2024storyagent,
  title = {{StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration}},
  author = {Hu, Panwen and Jiang, Jin and Chen, Jianqi and Han, Mingfei and Liao, Shengcai and Chang, Xiaojun and Liang, Xiaodan},
  year = {2024},
  url = {https://arxiv.org/abs/2411.04925}
}

@misc{li2024t2vturbo,
  title = {{T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback}},
  author = {Li, Jiachen and Feng, Weixi and Fu, Tsu-Jui and Wang, Xinyi and Basu, Sugato and Chen, Wenhu and Wang, William Yang},
  year = {2024},
  url = {https://arxiv.org/abs/2405.18750}
}

@misc{lu2024aiscientist,
  title = {{The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery}},
  author = {Lu, Chris and Lu, Cong and Lange, Robert Tjarko and Foerster, Jakob and Clune, Jeff and Ha, David},
  year = {2024},
  url = {https://arxiv.org/abs/2408.06292}
}

@misc{ding2024worldmodels,
  title = {{Understanding World or Predicting Future? A Comprehensive Survey of World Models}},
  author = {Ding, Jingtao and Zhang, Yunke and Shang, Yu and Feng, Jie and Zhang, Yuheng and Zong, Zefang and Yuan, Yuan and Su, Hongyuan and Li, Nian and Piao, Jinghua and Deng, Yucheng and Sukiennik, Nicholas and Gao, Chen and Xu, Fengli and Li, Yong},
  year = {2024},
  url = {https://arxiv.org/abs/2411.14499}
}

@misc{huang2024vbench,
  title = {{VBench: Comprehensive Benchmark Suite for Video Generative Models}},
  author = {Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and Wang, Yaohui and Chen, Xinyuan and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei},
  year = {2024},
  url = {https://arxiv.org/abs/2311.17982}
}

@misc{melnik2024videodiffusionsurvey,
  title = {{Video Diffusion Models: A Survey}},
  author = {Andrew Melnik and Michal Ljubljanac and Cong Lu and Qi Yan and Weiming Ren and Helge Ritter},
  year = {2024},
  url = {https://arxiv.org/abs/2405.03150}
}

@misc{fei2024videoincontext,
  title = {{Video Diffusion Transformers are In-Context Learners}},
  author = {Fei, Zhengcong and Qiu, Di and Li, Debang and Yu, Changqian and Fan, Mingyuan},
  year = {2024},
  url = {https://arxiv.org/abs/2412.10783}
}

@misc{zhang2024vidit,
  title = {{Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators}},
  author = {Zhang, Wentao and Guo, Junliang and He, Tianyu and Zhao, Li and Xu, Linli and Bian, Jiang},
  year = {2024},
  url = {https://arxiv.org/abs/2407.07356}
}

@misc{waseem2024surveyn07,
  title = {{Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation}},
  author = {Waseem, Faraz and Shahzad, Muhammad},
  year = {2024},
  url = {https://arxiv.org/abs/2412.18688}
}

@misc{fan2024videoagent,
  title = {{VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding}},
  author = {Fan, Yue and Ma, Xiaojian and Wu, Rujie and Du, Yuntao and Li, Jiaqi and Gao, Zhi and Li, Qing},
  year = {2024},
  url = {https://arxiv.org/abs/2403.11481}
}

@misc{soni2024videoagentself,
  title = {{VideoAgent: Self-Improving Video Generation}},
  author = {Soni, Achint and Venkataraman, Sreyas and Chandra, Abhranil and Fischmeister, Sebastian and Liang, Percy and Dai, Bo and Yang, Sherry},
  year = {2024},
  url = {https://arxiv.org/abs/2410.10076}
}

@misc{chen2024videocrafter2,
  title = {{VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models}},
  author = {Chen, Haoxin and Zhang, Yong and Cun, Xiaodong and Xia, Menghan and Wang, Xintao and Weng, Chao and Shan, Ying},
  year = {2024},
  url = {https://arxiv.org/abs/2401.09047}
}

@misc{lin2024videodirectorgpt,
  title = {{VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning}},
  author = {Lin, Han and Zala, Abhay and Cho, Jaemin and Bansal, Mohit},
  year = {2024},
  url = {https://arxiv.org/abs/2309.15091}
}

@misc{cheng2024videogui,
  title = {{VideoGUI: A Benchmark for GUI Automation from Instructional Videos}},
  author = {Lin, Kevin Qinghong and Li, Linjie and Gao, Difei and WU, Qinchen and Yan, Mingyi and Yang, Zhengyuan and Wang, Lijuan and Shou, Mike Zheng},
  year = {2024},
  url = {https://arxiv.org/abs/2406.10227}
}

@misc{kondratyuk2023videopoet,
  title = {{VideoPoet: A Large Language Model for Zero-Shot Video Generation}},
  author = {Kondratyuk, Dan and Yu, Lijun and Gu, Xiuye and Lezama, Jose and Huang, Jonathan and Schindler, Grant and Hornung, Rachel and Birodkar, Vighnesh and Yan, Jimmy and Chiu, Ming-Chang and others},
  year = {2024},
  url = {https://arxiv.org/abs/2312.14125}
}

@misc{he2024videoscore,
  title = {{VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation}},
  author = {He, Xuan and Jiang, Dongfu and Zhang, Ge and Ku, Max and Soni, Achint and Siu, Sherman and Chen, Haonan and Chandra, Abhranil and Jiang, Ziyan and Arulraj, Aaran and Wang, Kai and Do, Quy Duc and Ni, Yuansheng and Lyu, Bohan and Narsupalli, Yaswanth and Fan, Rongqi and Lyu, Zhiheng and Lin, Yuchen and Chen, Wenhu},
  year = {2024},
  url = {https://arxiv.org/abs/2406.15252}
}

@misc{long2024videostudio,
  title = {{VideoStudio: Generating Consistent-Content and Multi-Scene Videos}},
  author = {Long, Fuchen and Qiu, Zhaofan and Yao, Ting and Mei, Tao},
  year = {2024},
  url = {https://arxiv.org/abs/2401.01256}
}

@misc{wang2024voyager,
  title = {{Voyager: An Open-Ended Embodied Agent with Large Language Models}},
  author = {Wang, Guanzhi and Xie, Yuqi and Jiang, Yunfan and Mandlekar, Ajay and Xiao, Chaowei and Zhu, Yuke and Fan, Linxi and Anandkumar, Anima},
  year = {2024},
  url = {https://arxiv.org/abs/2305.16291}
}

@misc{lipman2022flowmatching,
  title = {{Flow Matching for Generative Modeling}},
  author = {Lipman, Yaron and Chen, Ricky T. Q. and Ben-Hamu, Heli and Nickel, Maximilian and Le, Matt},
  year = {2023},
  url = {https://arxiv.org/abs/2210.02747}
}

@misc{xu2023freebloom,
  title = {{Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator}},
  author = {Huang, Hanzhuo and Feng, Yufan and Shi, Cheng and Xu, Lan and Yu, Jingyi and Yang, Sibei},
  year = {2023},
  url = {https://arxiv.org/abs/2309.14494}
}

@misc{park2023generativeagents,
  title = {{Generative Agents: Interactive Simulacra of Human Behavior}},
  author = {Park, Joon Sung and O'Brien, Joseph C. and Cai, Carrie J. and Morris, Meredith Ringel and Liang, Percy and Bernstein, Michael S.},
  year = {2023},
  url = {https://arxiv.org/abs/2304.03442}
}

@misc{weng2023agents,
  title = {{LLM Powered Autonomous Agents}},
  author = {Weng, Lilian},
  year = {2023},
  url = {https://lilianweng.github.io/posts/2023-06-23-agent/}
}

@misc{liu2023lostmiddle,
  title = {{Lost in the Middle: How Language Models Use Long Contexts}},
  author = {Liu, Nelson F. and Lin, Kevin and Hewitt, John and Paranjape, Ashwin and Bevilacqua, Michele and Petroni, Fabio and Liang, Percy},
  year = {2023},
  url = {https://arxiv.org/abs/2307.03172}
}

@misc{singer2022make,
  title = {{Make-a-video: Text-to-video generation without text-video data}},
  author = {Singer, Uriel and Polyak, Adam and Hayes, Thomas and Yin, Xi and An, Jie and Zhang, Songyang and Hu, Qiyuan and Yang, Harry and Ashual, Oron and Gafni, Oran and others},
  year = {2023},
  url = {https://arxiv.org/abs/2209.14792}
}

@misc{villegas2022phenaki,
  title = {{Phenaki: Variable Length Video Generation From Open Domain Textual Descriptions}},
  author = {Villegas, Ruben and Babaeizadeh, Mohammad and Kindermans, Pieter-Jan and Moraldo, Hernan and Zhang, Han and Saffar, Mohammad Taghi and Castro, Santiago and Kunze, Julius and Erhan, Dumitru},
  year = {2023},
  url = {https://arxiv.org/abs/2210.02399}
}

@misc{yao2023react,
  title = {{ReAct: Synergizing Reasoning and Acting in Language Models}},
  author = {Yao, Shunyu and Zhao, Jeffrey and Yu, Dian and Du, Nan and Shafran, Izhak and Narasimhan, Karthik and Cao, Yuan},
  year = {2023},
  url = {https://arxiv.org/abs/2210.03629}
}

@misc{shinn2023reflexion,
  title = {{Reflexion: Language Agents with Verbal Reinforcement Learning}},
  author = {Shinn, Noah and Cassano, Federico and Gopinath, Ashwin and Narasimhan, Karthik and Yao, Shunyu},
  year = {2023},
  url = {https://arxiv.org/abs/2303.11366}
}

@misc{bie2023surveyn09,
  title = {{RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model}},
  author = {Bie, Fengxiang and Yang, Yibo and Zhou, Zhongzhu and Ghanem, Adam and Zhang, Minjia and Yao, Zhewei and Wu, Xiaoxia and Holmes, Connor and Golnari, Pareesa and Clifton, David A. and He, Yuxiong and Tao, Dacheng and Song, Shuaiwen Leon},
  year = {2023},
  url = {https://arxiv.org/abs/2309.00810}
}

@misc{peebles2022dit,
  title = {{Scalable Diffusion Models with Transformers}},
  author = {Peebles, William and Xie, Saining},
  year = {2023},
  url = {https://arxiv.org/abs/2212.09748}
}

@misc{gao2023overoptimization,
  title = {{Scaling Laws for Reward Model Overoptimization}},
  author = {Gao, Leo and Schulman, John and Hilton, Jacob},
  year = {2023},
  url = {https://arxiv.org/abs/2210.10760}
}

@misc{blattmann2023stablevideo,
  title = {{Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets}},
  author = {Blattmann, Andreas and Dockhorn, Tim and Kulal, Sumith and Mendelevitch, Daniel and Kilian, Maciej and Lorenz, Dominik and Levi, Yam and English, Zion and Voleti, Vikram and Letts, Adam and Jampani, Varun and Rombach, Robin},
  year = {2023},
  url = {https://arxiv.org/abs/2311.15127}
}

@misc{zhang2023surveyn02,
  title = {{Text-to-image Diffusion Models in Generative AI: A Survey}},
  author = {Zhang, Chenshuang and Zhang, Chaoning and Zhang, Mengchun and Kweon, In So and Kim, Junmo},
  year = {2023},
  url = {https://arxiv.org/abs/2303.07909}
}

@misc{shumailov2023curse,
  title = {{The Curse of Recursion: Training on Generated Data Makes Models Forget}},
  author = {Shumailov, Ilia and Shumaylov, Zakhar and Zhao, Yiren and Gal, Yarin and Papernot, Nicolas and Anderson, Ross},
  year = {2023},
  url = {https://arxiv.org/abs/2305.17493}
}

@misc{wu2023tune,
  title = {{Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation}},
  author = {Wu, Jay Zhangjie and Ge, Yixiao and Wang, Xintao and Lei, Stan Weixian and Gu, Yuchao and Shi, Yufei and Hsu, Wynne and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng},
  year = {2023},
  url = {https://doi.org/10.1109/ICCV51070.2023.00701}
}

@misc{suris2023vipergpt,
  title = {{ViperGPT: Visual Inference via Python Execution for Reasoning}},
  author = {D\'Sur\'and Sachit Menon and Carl Vondrick},
  year = {2023},
  url = {https://arxiv.org/abs/2303.08128}
}

@misc{gupta2023visprog,
  title = {{Visual Programming: Compositional Visual Reasoning without Training}},
  author = {Tanmay Gupta and Aniruddha Kembhavi},
  year = {2023},
  url = {https://arxiv.org/abs/2211.11559}
}

@misc{yang2022surveyn08,
  title = {{Diffusion Models: A Comprehensive Survey of Methods and Applications}},
  author = {Yang, Ling and Zhang, Zhilong and Song, Yang and Hong, Shenda and Xu, Runsheng and Zhao, Yue and Zhang, Wentao and Cui, Bin and Yang, Ming-Hsuan},
  year = {2022},
  url = {https://arxiv.org/abs/2209.00796}
}

@misc{dao2022flashattention,
  title = {{FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness}},
  author = {Dao, Tri and Fu, Daniel Y. and Ermon, Stefano and Rudra, Atri and Re, Christopher},
  year = {2022},
  url = {https://arxiv.org/abs/2205.14135}
}

@misc{rombach2021latentdiffusion,
  title = {{High-Resolution Image Synthesis with Latent Diffusion Models}},
  author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bjorn},
  year = {2022},
  url = {https://arxiv.org/abs/2112.10752}
}

@misc{ho2022videodiffusion,
  title = {{Video Diffusion Models}},
  author = {Ho, Jonathan and Salimans, Tim and Gritsenko, Alexey and Chan, William and Norouzi, Mohammad and Fleet, David J.},
  year = {2022},
  url = {https://arxiv.org/abs/2204.03458}
}

@misc{kossen2021activetesting,
  title = {{Active Testing: Sample-Efficient Model Evaluation}},
  author = {Kossen, Jannik and Farquhar, Sebastian and Gal, Yarin and Rainforth, Tom},
  year = {2021},
  url = {https://proceedings.mlr.press/v139/kossen21a.html}
}

@misc{frolov2021surveyn01,
  title = {{Adversarial Text-to-Image Synthesis: A Review}},
  author = {Frolov, Stanislav and Hinz, Tobias and Raue, Federico and Hees, Jörn and Dengel, Andreas},
  year = {2021},
  url = {https://arxiv.org/abs/2101.09983}
}

@misc{liu2021persuasivevideosurvey,
  title = {{AI-Empowered Persuasive Video Generation: A Survey}},
  author = {Chang Liu and Han Yu},
  year = {2021},
  url = {https://arxiv.org/abs/2112.09401}
}

@misc{bain2021frozen,
  title = {{Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval}},
  author = {Bain, Max and Nagrani, Arsha and Varol, Gul and Zisserman, Andrew},
  year = {2021},
  url = {https://arxiv.org/abs/2104.00650}
}

@misc{brown2020fewshot,
  title = {{Language Models are Few-Shot Learners}},
  author = {Brown, Tom B. and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom and Child, Rewon and Ramesh, Aditya and Ziegler, Daniel M. and Wu, Jeffrey and Winter, Clemens and Hesse, Christopher and Chen, Mark and Sigler, Eric and Litwin, Mateusz and Gray, Scott and Chess, Benjamin and Clark, Jack and Berner, Christopher and McCandlish, Sam and Radford, Alec and Sutskever, Ilya and Amodei, Dario},
  year = {2020},
  url = {https://arxiv.org/abs/2005.14165}
}

@misc{unterthiner2018fvd,
  title = {{Towards Accurate Generative Models of Video: A New Metric \& Challenges}},
  author = {Unterthiner, Thomas and van Steenkiste, Sjoerd and Kurach, Karol and Marinier, Raphael and Michalski, Marcin and Gelly, Sylvain},
  year = {2018},
  url = {https://arxiv.org/abs/1812.01717}
}

@misc{agentskills2026spec,
  title = {{Agent Skills Specification}},
  author = {Agent Skills},
  url = {https://agentskills.io/specification}
}

@misc{comfy2026mcp,
  title = {{Comfy MCP}},
  author = {Comfy Org},
  url = {https://docs.comfy.org/agent-tools/mcp}
}

@misc{comfy2026skills,
  title = {{Comfy Skills for Coding Agents}},
  author = {Comfy Org},
  url = {https://docs.comfy.org/agent-tools/skills}
}

@misc{comfy2026nodes,
  title = {{ComfyUI Nodes: Types, Inputs, and Outputs}},
  author = {Comfy Org},
  url = {https://docs.comfy.org/basic-concepts/nodes}
}

@misc{filmswarm2026,
  title = {{FilmSwarm: AI Agent Swarm for Film Pre-production}},
  author = {AI Makers},
  url = {https://github.com/AiMakers-co/filmswarm}
}

@misc{swarmzero2026video,
  title = {{Livepeer Youtube Video Generator Swarm}},
  author = {SwarmZero},
  url = {https://docs.swarmzero.ai/examples/swarms/livepeer-youtube-video-generator-swarm}
}