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

TL;DR

This paper demonstrates that large language models can be fine-tuned to serve as world models by predicting action preconditions and effects, validated through human studies and analysis of their planning capabilities.

Contribution

It introduces a method to induce LLMs to function as world models by fine-tuning for precondition and effect prediction using synthetic data.

Findings

LLMs can predict action preconditions and effects accurately.

Human studies show alignment with human understanding.

The trained models support action chaining for planning.

Abstract

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.