# World models for language agents Area: [World models](https://mlsanity.com/wm/index.md). HTML: https://mlsanity.com/wm/world-models-for-language-agents/ ## Key facts - World models for language agents: 486 papers on arXiv since 2013 (data through 14 Oct 2026). - 81 of its 486 mapped papers (17%) cite “Reasoning with Language Model is Planning with World Model” (2023, arXiv 2305.14992). - 74 of its 486 mapped papers (15%) cite “Language Models are Few-Shot Learners” (2020, arXiv 2005.14165). - 53 new papers 17 Sep–14 Oct. ## Most cited here - [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023), cited by 81 papers here - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020), cited by 74 papers here - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023), cited by 52 papers here - [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020), cited by 45 papers here - [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024), cited by 36 papers here - [WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment](https://mlsanity.com/paper/2402.12275/) (2024), cited by 33 papers here - [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024), cited by 32 papers here - [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024), cited by 32 papers here - [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025), cited by 32 papers here - [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023), cited by 31 papers here ## New (17 Sep–14 Oct) - [When Reality Outpaces Cognition: A New Scaling Principle for Reliable Intelligence](https://mlsanity.com/paper/2610.20764/) (2026-10-14) - [Neurosymbolic Learning of Interpretable World Models](https://mlsanity.com/paper/2610.19955/) (2026-10-14) - [Model What Matters: Decision-Guided Selective World Modeling for Language Agents](https://mlsanity.com/paper/2610.19642/) (2026-10-14) - [Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context](https://mlsanity.com/paper/2610.19364/) (2026-10-14) - [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026-10-13) - [Relational Learning as World Modeling](https://mlsanity.com/paper/2610.16763/) (2026-10-12) - [CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds](https://mlsanity.com/paper/2610.16450/) (2026-10-12) - [Same Goal, Different Words: Spatial Instruction Sensitivity in World-Action Models](https://mlsanity.com/paper/2610.16242/) (2026-10-12) - [ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs](https://mlsanity.com/paper/2610.15368/) (2026-10-11) - [ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling](https://mlsanity.com/paper/2610.15166/) (2026-10-10) - [RSI-Anything: Unlocking Recursive Self-Improvement with World Models](https://mlsanity.com/paper/2610.13912/) (2026-10-09) - [JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models](https://mlsanity.com/paper/2610.13194/) (2026-10-09) - [RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions](https://mlsanity.com/paper/2610.13172/) (2026-10-09) - [Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing](https://mlsanity.com/paper/2610.12881/) (2026-10-09) - [EvoBelief: Falsifiable World Models for Self-Improving LLM Agents](https://mlsanity.com/paper/2610.12789/) (2026-10-08) - [Language Models as AI Research World Models](https://mlsanity.com/paper/2610.12235/) (2026-10-08) - [Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks](https://mlsanity.com/paper/2610.11794/) (2026-10-08) - [LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models](https://mlsanity.com/paper/2610.11253/) (2026-10-08) - [MemoWM: How World Models Change What Agents Need to Remember](https://mlsanity.com/paper/2610.10778/) (2026-10-07) - [Long-Horizon Textual World Modeling through Structured Reasoning](https://mlsanity.com/paper/2610.06637/) (2026-10-05) - [From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation](https://mlsanity.com/paper/2610.06100/) (2026-10-05) - [When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models](https://mlsanity.com/paper/2610.05550/) (2026-10-04) - [What Should World Models Forget? Stratified Retention for Continual Adaptation](https://mlsanity.com/paper/2610.03713/) (2026-10-02) - [ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models](https://mlsanity.com/paper/2610.03356/) (2026-10-02) - [EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models](https://mlsanity.com/paper/2610.02744/) (2026-10-02) - [CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges](https://mlsanity.com/paper/2610.02622/) (2026-10-02) - [How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling](https://mlsanity.com/paper/2610.02542/) (2026-10-01) - [World Editing: Intervening on Executable Worlds at Increasing Depth](https://mlsanity.com/paper/2610.02331/) (2026-10-01) - [On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models](https://mlsanity.com/paper/2610.01842/) (2026-10-01) - [In CEM, a World Model Is Also a Proposal Mechanism](https://mlsanity.com/paper/2610.00921/) (2026-10-01)