Making Large Language Models into World Models with Precondition and Effect Knowledge
This work addresses the challenge of modeling real-world dynamics for intelligent agents, though it is incremental as it adapts existing LLMs rather than introducing a new paradigm.
The paper tackled the problem of enabling Large Language Models (LLMs) to function as world models by fine-tuning separate models for precondition and effect prediction using synthetic data, and validated through human studies that the generated knowledge aligns with human understanding of world dynamics.
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.