Language Agents Meet Causality -- Bridging LLMs and Causal World Models

TL;DR

This paper introduces a framework combining causal representation learning with large language models to improve causally-aware reasoning and planning, especially for complex and long-horizon tasks.

Contribution

It presents a novel integration of causal world models with LLMs, enabling flexible, causally-informed reasoning and planning in natural language.

Findings

Outperforms LLMs in causal inference tasks

Enhances planning accuracy over longer horizons

Demonstrates effectiveness across diverse environments

Abstract

Large Language Models (LLMs) have recently shown great promise in planning and reasoning applications. These tasks demand robust systems, which arguably require a causal understanding of the environment. While LLMs can acquire and reflect common sense causal knowledge from their pretraining data, this information is often incomplete, incorrect, or inapplicable to a specific environment. In contrast, causal representation learning (CRL) focuses on identifying the underlying causal structure within a given environment. We propose a framework that integrates CRLs with LLMs to enable causally-aware reasoning and planning. This framework learns a causal world model, with causal variables linked to natural language expressions. This mapping provides LLMs with a flexible interface to process and generate descriptions of actions and states in text form. Effectively, the causal world model acts as a simulator that the LLM can query and interact with. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities. Our experiments demonstrate the effectiveness of the approach, with the causally-aware method outperforming LLM-based reasoners, especially for longer planning horizons.