# Making Large Language Models into World Models with Precondition and Effect Knowledge

arXiv: https://arxiv.org/abs/2409.12278 · HTML: https://mlsanity.com/paper/2409.12278/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 18 Sep 2024.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling](https://mlsanity.com/paper/2301.12050/) (2023)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [World Model as a Graph: Learning Latent Landmarks for Planning](https://mlsanity.com/paper/2011.12491/) (2020)
- [Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension](https://mlsanity.com/paper/1805.06975/) (2018)
- [Can Language Models Serve as Text-Based World Simulators?](https://mlsanity.com/paper/2406.06485/) (2024)
- [Mastering Memory Tasks with World Models](https://mlsanity.com/paper/2403.04253/) (2024)
- [Learning Knowledge Graph-based World Models of Textual Environments](https://mlsanity.com/paper/2106.09608/) (2021)
- [Explainable Reinforcement Learning via a Causal World Model](https://mlsanity.com/paper/2305.02749/) (2023)
- [Modeling Worlds in Text](https://mlsanity.com/paper/2106.09578/) (2021)
- [PaCo: Preconditions Attributed to Commonsense Knowledge](https://mlsanity.com/paper/2104.08712/) (2021)
- [Modeling Preconditions in Text with a Crowd-sourced Dataset](https://mlsanity.com/paper/2010.02429/) (2020)
- [Learning Action Conditions from Instructional Manuals for Instruction Understanding](https://mlsanity.com/paper/2205.12420/) (2022)
- [PInKS: Preconditioned Commonsense Inference with Minimal Supervision](https://mlsanity.com/paper/2206.07920/) (2022)
- [Toward Diverse Precondition Generation](https://mlsanity.com/paper/2106.07117/) (2021)

## Built on by (most cited first, 22 of 22)

- [From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://mlsanity.com/paper/2512.18832/) (2025)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents](https://mlsanity.com/paper/2410.07484/) (2024)
- [Text2World: Benchmarking Large Language Models for Symbolic World Model Generation](https://mlsanity.com/paper/2502.13092/) (2025)
- [LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed](https://mlsanity.com/paper/2411.08794/) (2024)
- [When Do Neural Networks Learn World Models?](https://mlsanity.com/paper/2502.09297/) (2025)
- [G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration](https://mlsanity.com/paper/2506.09272/) (2025)
- [What Does it Mean for a Neural Network to Learn a "World Model"?](https://mlsanity.com/paper/2507.21513/) (2025)
- [WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents](https://mlsanity.com/paper/2504.15785/) (2025)
- [Self-Improving World Modelling with Latent Actions](https://mlsanity.com/paper/2602.06130/) (2026)
- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [World-State Transformations for Neuro-symbolic Interactive Storytelling](https://mlsanity.com/paper/2605.24719/) (2026)
- [PriorZero: Bridging Language Priors and World Models for Decision Making](https://mlsanity.com/paper/2605.12289/) (2026)
- [Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?](https://mlsanity.com/paper/2509.10875/) (2025)
- [Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI](https://mlsanity.com/paper/2510.14718/) (2025)
- [LOGOS-CA: A Cellular Automaton Using Natural Language as State and Rule](https://mlsanity.com/paper/2602.00036/) (2026)
- [Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities](https://mlsanity.com/paper/2605.09678/) (2026)
- [Agent-driven Long-tail Simulation for Autonomous Driving](https://mlsanity.com/paper/2607.04331/) (2026)
- [Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control](https://mlsanity.com/paper/2607.27914/) (2026)
- [Reconstructing Persistent Worlds from Narratives for Narrative-Grounded Interactive Experiences](https://mlsanity.com/paper/2608.04037/) (2026)
- [STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration](https://mlsanity.com/paper/2608.27225/) (2026)
- [Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents](https://mlsanity.com/paper/2610.04168/) (2026)

## Abstract (arXiv)

World models, which encapsulate the dynamics of how actions affect environments, are foundational to the functioning of intelligent agents. In this work, we explore the potential of Large Language Models (LLMs) to operate as world models. Although LLMs are not inherently designed to model real-world dynamics, we show that they can be induced to perform two critical world model functions: determining the applicability of an action based on a given world state, and predicting the resulting world state upon action execution. This is achieved by fine-tuning two separate LLMs-one for precondition prediction and another for effect prediction-while leveraging synthetic data generation techniques. Through human-participant studies, we validate that the precondition and effect knowledge generated by our models aligns with human understanding of world dynamics. We also analyze the extent to which the world model trained on our synthetic data results in an inferred state space that supports the creation of action chains, a necessary property for planning.