LLM World Models

LLM: Large Language Model

LLM world models represent environments as states and predict how actions change them, from web pages and APIs to games, spatial tasks, and research experiments. Common approaches fine-tune models on interaction traces, retrieve transition rules from memory, combine language models with symbolic constraints, or learn latent dynamics that agents can rehearse before acting. These models are used to generate training experience, improve long-horizon planning, and assess risks or candidate actions without repeated real-world interaction. A central challenge is that accurate local predictions or latent representations may still fail to support reliable reasoning over long horizons, hidden states, or rare but consequential events.

Latest papers

34 papers11 papers in the last four weeks, up 267% on the four weeks before. 0.1% of all new papers.

From Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?
Oct 21, 2026Juntong Ni, Zewen Liu, Bohan Wang +2LLM World Models World Models
Emory University
LLM-Based Exogenous World Modeling for Dynamic Scheduling
Oct 21, 2026Ni Zhang, Haofeng Yuan, Jianan Zhou +2Model-Based Planning Combinatorial Optimization
Singapore Management University · Tsinghua University · Nanyang Technological University
Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model
Oct 21, 2026Jiongxiao Wang, Han Ding, Youzhi Luo +4LLM World Models LLM Agents
University of Wisconsin–Madison · AWS AI
GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations
Oct 15, 2026Nicholas Saban, Charvi Bannur, Mariya Vasileva +1World Model Evaluation LLM World Models
Patronus AI
Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Oct 13, 2026Xiyang Wu, Zhichao Liu, Shengxin zhang +4Long-Horizon LLM Agents Long-Horizon Reasoning
University of Maryland · Google · MBZUAI
CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds
Oct 12, 2026Ang Li, Haofei Yu, Zhengwei Tao +7LLM World Models World Model Evaluation
The Chinese University of Hong Kong · University of Illinois at Urbana-Champaign · UniPat AI +3
RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions
Oct 9, 2026Boyuan Xiao, Pu Wang, Ji Feng +1World Models LLM World Models
State Key Lab of CAD&CG Zhejiang University, China · Baiont Quant, China
Language Models as AI Research World Models
Oct 8, 2026Zijun Wang, Zewen Liu, Minhua Lin +10LLM World Models Autonomous Research Agents
Amazon · UC Santa Cruz · Emory University +2
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Oct 5, 2026Quanyu Long, Xiao Chen, Jianda Chen +4LLM World Models Interactive World Models
Nanyang Technological University · The Hong Kong Polytechnic University
How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling
Oct 1, 2026Dhananjay Ashok, Shantanu Agarwal, Vivek Datla +2LLM World Models World Model Learning
Information Sciences Institute University of Southern California · CapitalOne · Capital One
Do World Models Learn Global Understanding?
Sep 28, 2026Alexander Detkov, Matt ThomsonLLM World Models World Model Learning
California Institute of Technology Pasadena, CA 91125, USA
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Sep 23, 2026Shuang Sun, Guoxin Chen, Fanzhe Meng +6LLM World Models World Models
Gaoling School of Artificial Intelligence, Renmin University of China
Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs
Sep 21, 2026Kohsei Matsutani, Gouki Minegishi, Core Francisco Park +3LLM World Models In-Context Learning
The University of Tokyo · Harvard University · Prior Computers
SerenAI: State-transition system inspired by text-based world AI models
Sep 6, 2026Elvin Babayev, Artem Sinitsa, Arash Hajisharifi +1LLM World Models Causal Reasoning in Language Models
Collision Technologies S.R.L.S. Societa Benefit Trieste, Italy
MemWM: Memory-Augmented Text-Based World Model
Aug 7, 2026Yujun Wang, Tao Zhang, Jinhe Bi +9LLM World Models World Model Learning
LMU Munich · Munich Center for Machine Learning (MCML) · Huawei Heisenberg Research Center +4
Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking
Aug 7, 2026Devin Pereira, Willem ZuidemaLLM World Models LLM Planning
1Artificial Intelligence Program, University of Amsterdam · ELLIS Unit Amsterdam · Institute for Logic Language and Computation, University of Amsterdam
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Aug 6, 2026Zishan Xu, Zhiyuan Yao, Yuxin Chen +9LLM World Models Agentic RL
Shanghai Jiao Tong University · Zhejiang University · National University of Singapore +4
DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
Aug 6, 2026Wenhao Lin, Chenyu Yu, Xingwei Lin +6LLM World Models LLM Guardrails
Zhejiang University · Nanjing University of Posts and Telecommunications · Sun Yat-sen University
Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models
Jul 18, 2026Seanie Lee, Sanjoy Chowdhury, Chao Jiang +5LLM World Models Synthetic Data Generation
Apple
When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models
Jul 15, 2026Javier Aguilar MartínLLM World Models World Models
AGILabs (javieraguilar.ai)
From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond
Jun 26, 2026Paul DuboisLLM World Models World Models
Qwen-AgentWorld: Language World Models for General Agents
Jun 23, 2026Yuxin Zuo, Zikai Xiao, Li Sheng +30LLM World Models Agentic RL
Qwen Team
NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama
Jun 16, 2026Logan Mann, Abdur Rahman, Mohammad Saifullah +2LLM World Models Multilingual Language Model Evaluation
University of California, Santa Barbara · Pocket FM
Bridging the Agent-World Gap: Text World Models for LLM-based Agents
Jun 8, 2026Yixia Li, Hongru Wang, Peng Lai +13LLM World Models World Models
Southern University of Science and Technology · University of Edinburgh · Peking University +5
CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Jun 1, 2026Youwei Liu, Jian Wang, Hanlin Wang +1LLM World Models LLM Agent Training
Central South University · College of Computer Science, Sichuan University · Department of Computing, The Hong Kong Polytechnic University
Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
May 27, 2026Zhikai Pan, Chih-Ting Liao, Chunrui Liu +5LLM World Models Multilingual Language Model Evaluation
University of New South Wales · Essential Energy · University of Alabama at Birmingham +3
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
May 9, 2026Giridhar Ganapavarapu, Dhaval PatelLLM World Models World Models
IBM, New York
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
May 7, 2026Darshan DeshpandeLLM World Models World Models
Patronus AI
Do LLMs Build Spatial World Models? Evidence from Grid-World Maze Tasks
Apr 12, 2026Weijiang Li, Yilin Zhu, Rajarshi Das +1Spatial Reasoning in Language Models LLM World Models
University of Notre Dame · Columbia University · MQube Cognition
World Properties without World Models: Distributional Associations and the Interpretation of Decoding Results from Language Models
Mar 4, 2026Elan BarenholtzLLM World Models Word Embeddings
Department of Psychology & Center for Complex Systems and Brain Sciences Florida Atlantic University

Oct 21, 2026J/K move · Enter open · S save

From Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?

Juntong Ni, Zewen Liu, Bohan Wang, Lige Zhang+1

Emory University

LLM World Models World Models

Open paper AskPDF arXiv

World models help agents assess the consequences of their actions before acting. Many real systems, however, involve multiple actors who make their own decisions, can evolve even when the agent takes no action, and are only partially observed through event logs. We formalize these systems as event worlds and ask whether large language models can predict future observations from the log and the agent's proposed actions. We build complementary benchmarks from human Diplomacy games and real Polymarket trades. Our hierarchical framework compares prediction with and without other actors' actions, then tests multi-step rollouts, predictions for actions never taken, and usefulness to agents. Fine-tuning and more data improve prediction when all actors' recorded actions are given. With only the agent's action, models struggle when other actors strongly affect the outcome, and larger models and longer histories help little. This gap also limits multi-step prediction and agent decisions, with models overestimating plan success. Yet imagined experience and initialization from world models can still improve policy learning. Anticipating other actors' actions remains a central challenge for event world modeling.