SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Model

TL;DR

This paper introduces SOM, a two-stage structured opponent modeling framework using Structural Causal Models to improve prediction accuracy and adaptability of LLM-based agents in multi-agent environments.

Contribution

SOM distinctly separates opponent model construction from prediction, employing SCM for explicit dependency modeling to enhance LLM reasoning in dynamic multi-agent settings.

Findings

SOM outperforms state-of-the-art LLM-based reasoning baselines.

SOM improves prediction accuracy and stability in multi-agent interactions.

SOM enables more adaptable strategic decision-making.

Abstract

Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and game-theoretic environments. Existing approaches often entangle opponent modeling with prediction, relying on implicit contextual reasoning and limiting adaptability in dynamic interactions. To this end, we propose Structured Opponent Modeling (SOM), a two-stage opponent modeling framework that distinctly separates opponent model construction and opponent prediction. At the construction stage, SOM employs a Structural Causal Model (SCM), a graph-based formalism for representing dependencies among variables, to capture directed links between opponents' observations and actions, yielding an explicit and structured opponent representation. At the prediction stage, the LLM performs structured reasoning along clear pathways derived from the SCM, improving both prediction accuracy and stability. Extensive experiments on diverse multi-agent benchmarks demonstrate that SOM consistently outperforms state-of-the-art LLM-based reasoning baselines, enabling more accurate and adaptable strategic decision-making in complex and dynamic multi-agent interactions.