# Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

arXiv: https://arxiv.org/abs/2609.40358 · HTML: https://mlsanity.com/paper/2609.40358/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 36 of its 83 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 36)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025)
- [AgentEvolver: Towards Efficient Self-Evolving Agent System](https://mlsanity.com/paper/2511.10395/) (2025)
- [ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent](https://mlsanity.com/paper/2312.10003/) (2023)
- [Think Before You Diffuse: Infusing Physical Rules into Video Diffusion](https://mlsanity.com/paper/2505.21653/) (2025)
- [PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection](https://mlsanity.com/paper/2511.03997/) (2025)
- [EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.03108/) (2026)
- [Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility](https://mlsanity.com/paper/2509.24702/) (2025)
- [PhyGround: Benchmarking Physical Reasoning in Generative World Models](https://mlsanity.com/paper/2605.10806/) (2026)
- [NEWTON: Agentic Planning for Physically Grounded Video Generation](https://mlsanity.com/paper/2605.18396/) (2026)
- [SEAL: Synergistic Co-Evolution of Agents and Learning Environments](https://mlsanity.com/paper/2605.24426/) (2026)
- [Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning](https://mlsanity.com/paper/2601.04153/) (2026)
- [Physics-IQ Verified](https://mlsanity.com/paper/2606.18943/) (2026)
- [VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System](https://mlsanity.com/paper/2607.27380/) (2026)
- [Learning Plug-and-play Memory for Guiding Video Diffusion Models](https://mlsanity.com/paper/2511.19229/) (2025)
- [PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance](https://mlsanity.com/paper/2601.03665/) (2026)
- [PhyWorld: Physics-Faithful World Model for Video Generation](https://mlsanity.com/paper/2605.19242/) (2026)
- [STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding](https://mlsanity.com/paper/2510.14588/) (2025)
- [PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation](https://mlsanity.com/paper/2603.03505/) (2026)
- [CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation](https://mlsanity.com/paper/2606.14317/) (2026)
- [When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video Generation](https://mlsanity.com/paper/2607.16947/) (2026)
- [Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement](https://mlsanity.com/paper/2511.20280/) (2025)
- [Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics](https://mlsanity.com/paper/2603.10408/) (2026)
- [MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modeling](https://mlsanity.com/paper/2604.02817/) (2026)
- [Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration](https://mlsanity.com/paper/2604.18131/) (2026)
- [Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers](https://mlsanity.com/paper/2605.07503/) (2026)

## Abstract (arXiv)

Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical principles. Existing approaches commonly assume that natural language is insufficient to represent the physical knowledge required for reliable generation, and therefore introduce additional visual, latent, numerical, or planning-based signals. We revisit this assumption and introduce Physis-Lang, a self-evolving framework that treats physical language as a shared and optimizable representation across data curation, model training, and video generation. Physis-Lang represents physical processes through language that describes their relevant entities, causes, interactions, governing principles, temporal evolution, and effects. To improve this representation, we construct PhysCapBench, which decomposes physical processes into atomic assertions and evaluates captions using recall and precision. An agentic loop iteratively analyzes assertion-level errors and refines the instruction used to produce physical captions. Physis-Lang further converts model deficiencies into textual descriptions and uses language-guided retrieval to identify visually diverse videos that cover missing physical processes. Experiments on four widely used physical video benchmarks with Wan and Cosmos backbones demonstrate consistent improvements in physical plausibility. Notably, starting from open-source Cosmos3-Nano backbones, our Physis-Lang-enhanced models surpass the leading proprietary Veo 3.1 model.