PhyEvolve is a multi-agent framework that improves physics-aware video generation by enhancing natural-language prompts through structured state-evolution planning. It employs three agents—a Director, a Physical Evolver, and a Composer—to ground scenes, identify physical mechanisms, and construct causally linked state transitions that guide video generation. The method works with existing generators via prompt replacement and achieves state‑of‑the‑art performance, outperforming the prior agentic baseline by an average of 7.9 percentage points on four major benchmarks.
arXiv:2607. 16355v1 Announce Type: cross Abstract: Recent advances in physics-grounded video generation leverage physics simulation as a physical prior to guide video synthesis toward physically plausible outcomes.
By Qirui Li, Jinkun Hao, Yibo Li, Ran Yi, Paul L. Rosin, Yu-Kun Lai
VideoEvolve is a framework that automatically evolves agent harnesses for video temporal grounding, a task that localizes events in videos based on natural-language queries. It introduces a Cloze-Structured Harness Representation to keep stage interfaces stable while allowing agent workflows and instructions to change, and uses Branch-Guided Harness Evolution to preserve promising code branches, guide local edits with execution feedback, and validate improvements. Experiments show that this automated evolution improves grounding performance across multiple benchmarks, with instruction refinement consistently yielding gains.
By Bingjun Luo, Yuhuan Fan, Jialin Guo, Siqi Li
arXiv:2607. 27380v2 Announce Type: replace-cross Abstract: Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt.
By Haodong Li, Tianfei Ren, Xiaoxiao Ma, Chunmei Qing, Zhen Fang, Sipeng He, Ziyu Guo, Haoyu Wu, Juanxi Tian, Yihang Zou, Ruichuan An, Dongzhi Jiang, Boxue Yang, Ji Xie, Xu Huang, Wenhao Yan, Jialv Zou, Zhengrong Yue, Yaxin Luo, Xiaotong Li, Yuzhu Wang, Junyan Ye, Jinjing Zhao, Zehui Chen, Lin Chen, Renye Yan, Feng Zhao, Pheng-Ann Heng
Oneira is an interactive video world model that links open-ended generation with persistent interaction. It uses a coding agent to manage an extensible world state, allowing newly generated or discovered entities to become actionable and ensuring that changes made by an agent are retained across video segments. Experiments demonstrate that Oneira supports consistent interaction with new objects while preserving prior interaction effects over long horizons.
By Xindi Yang, Baolu Li, Liam Lee, Zhenfei Yin, Songxin Zhang, Zhuoyang Song, Xu Jia, Jianfei Cai, Tien-Tsin Wong, Bingyi Jing, Mengyue Yang
The paper introduces Physically Plausible Video Generation (PPVG), a method that generates videos consistent with physical laws by treating physical evolution as a chain of causally connected events. It employs three modules: Physics-driven Event Chain Reasoning to decompose phenomena into scene-graph events, Transition-aware Routed Keyframe Conditioning to guide keyframe synthesis for smooth transitions, and Physics-injected Contrastive Semantic Guidance to steer generation toward plausible dynamics. Experiments on multiple physics benchmarks show improved physical plausibility compared to prior approaches.
By Zixuan Wang, Yixin Hu, Wen Li, Feng Chen, Yan Liu, Duo Peng, Yinjie Lei
arXiv:2608.29621v1 Announce Type: cross
Abstract: Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt con...
By Junxiang Liu, Lin Wang, Haiyu Shi, Hongxu Ma, Xiaoyu Yang, Chunjie Chen, Xiaoxiao Xu, Kaiqiao Zhan, Boao Wang, Shuizhou Shi, Tianyun Zhu, Jie Li, Jiangtong Li
arXiv:2605. 14398v2 Announce Type: replace Abstract: World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches demonstrating impressive progress in generating visually plausible dynamics.
By Hongyu Wang, Jingquan Wang, Bocheng Zou, Radu Serban, Dan Negrut
CineEvolve is a new agentic self‑evolution framework for cinematic multi‑shot video generation that integrates a Director and a Critic into a single vision‑language policy. The system alternates reinforcement learning steps, letting the Director identify flaws and the Critic refine its guidance, while a novel Evolutionary GRPO (E‑GRPO) stabilizes co‑evolution by anchoring history and safeguarding revisions. The authors also release CineTraj, a 40K‑sample dataset of cinematic trajectories, and show that CineEvolve outperforms existing methods in extensive experiments.
By Jingzhe Zhang, Peixuan Zhang, Genying Li, Bing Ma, Shuchen Weng, Si Li, Boxin Shi
Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, sp...
The paper introduces SMART, a Self‑evolving Multi‑Agent Refinement Framework for conversational text‑to‑motion generation. It enables users to iteratively refine specific spatio‑temporal regions of a motion sequence based on natural language feedback, preserving the rest of the motion. The framework incorporates a semantic‑guided masked editing mechanism and a memory‑based self‑evolving strategy to reuse past editing knowledge and reduce redundant exploration.
By Jianan Li, Jiawei Zhao, Yangtao Zhou, Zhifu Zhao, Shaoxin Wu, Yutao Wang, Dezhen Wang, Hua Chu, Fu Li
arXiv:2607. 01766v1 Announce Type: new Abstract: LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output.
By Chunjiang Liu, Xiaoyuan Wang, Haoyu Chen, Yizhou Zhao, Ming-Hsuan Yang, L\'aszl\'o A. Jeni