mlsanityData to 7 Oct 2026

Text2World: Benchmarking Large Language Models for Symbolic World Model Generation

arXiv 2502.13092 ↗First posted 18 Feb 2025cs.CL cs.AIcited by 25

On the map: World models → World models for language agents

Abstract (arXiv)

Recently, there has been growing interest in leveraging large language models (LLMs) to generate symbolic world models from textual descriptions. Although LLMs have been extensively explored in the context of world modeling, prior studies encountered several challenges, including evaluation randomness, dependence on indirect metrics, and a limited domain scope. To address these limitations, we introduce a novel benchmark, Text2World, based on planning domain definition language (PDDL), featuring hundreds of diverse domains and employing multi-criteria, execution-based metrics for a more robust evaluation. We benchmark current LLMs using Text2World and find that reasoning models trained with large-scale reinforcement learning outperform others. However, even the best-performing model still demonstrates limited capabilities in world modeling. Building on these insights, we examine several promising strategies to enhance the world modeling capabilities of LLMs, including test-time scaling, agent training, and more. We hope that Text2World can serve as a crucial resource, laying the groundwork for future research in leveraging LLMs as world models. The project page is available at https://text-to-world.github.io/.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 28 of its 57 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

28 of 57 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Making Large Language Models into World Models with Precondition and Effect Knowledge18 Sep
  2. 2024Evaluating the World Model Implicit in a Generative Model6 Jun
  3. 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search24 May
  4. 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment19 Feb
  5. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought22 Jun
  6. 2023Reasoning with Language Model is Planning with World Model24 May
  7. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning24 May
  8. 2023ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games24 May

Other references · 20

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  5. 2018World Modelscited by 1,444
  6. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  7. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  8. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  9. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 319
  10. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226
  11. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  12. 2024Large Language Models Meet NLP: A Surveycited by 102
8 more
  1. 2024AnalogCoder: Analog Circuit Design via Training-Free Code Generationcited by 82
  2. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  3. 2024World Models for Autonomous Driving: An Initial Surveycited by 79
  4. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thoughtcited by 56
  5. 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 55
  6. 2024Can Language Models Serve as Text-Based World Simulators?cited by 50
  7. 2023Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Modelscited by 35
  8. 2020Can Transformers Reason About Effects of Actions?cited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 11.

25 papers.

Sort:

By area:

  1. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2025Vid2World: Crafting Video Diffusion Models to Interactive World Modelscited by 67
  4. 20253D and 4D World Modeling: A Surveycited by 64
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  6. 2025From Word to World: Can Large Language Models be Implicit Text-based World Models?cited by 40
  7. 2026Qwen-AgentWorld: Language World Models for General Agentscited by 22
  8. 2025WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planningcited by 19
  9. 2025AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learningcited by 18
  10. 2025TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Modelcited by 14
  11. 2025Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Modelscited by 13
  12. 2025Environment Scaling for Interactive Agentic Experience Collection: A Surveycited by 13
13 more
  1. 2025Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesiscited by 10
  2. 2026PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environmentscited by 5
  3. 2026MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hintscited by 4
  4. 2025Unifying Inference-Time Planning Language Generationcited by 3
  5. 2025Learning Hierarchical Domain Models Through Environment-Grounded Interactioncited by 1
  6. 2026Model Space Reasoning as Search in Feedback Space for Planning Domain Generationcited by 1
  7. 2025Autonomous Assessment of Generalizability of AI Agent Capabilitiescited by 0
  8. 2026Robust Asynchronous Planning via Auto-Formalizationcited by 0
  9. 2026SCOPE: Evolving Symbolic World for Planning in Open-Ended Environmentscited by 0
  10. 2026PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planningcited by 0
  11. 2026WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modelingcited by 0
  12. 2026World Agent: Can Language Models Keep a World Running?cited by 0
  13. 2026When Do Causal World Models Help Modular LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agents
  2. 2026Reinforcement World Model Learning for LLM-based Agents
  3. 2025WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
  4. 2025R-WoM: Retrieval-augmented World Model For Computer-use Agents
  5. 2024Language-Guided World Models: A Model-Based Approach to AI Control
  6. 2026HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models
  7. 2025Generating Symbolic World Models via Test-time Scaling of Large Language Models
  8. 2024LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed