Approximating Human Strategic Reasoning with LLM-Enhanced Recursive Reasoners Leveraging Multi-agent Hypergames

TL;DR

This paper presents a framework using large language models within multi-agent hypergames to simulate and evaluate sophisticated recursive reasoning, outperforming baseline models and approximating human strategic behavior.

Contribution

It introduces a novel multi-agent hypergame environment with LLM-based agents and a new semantic measure of reasoning, advancing the simulation of human-like strategic reasoning.

Findings

LLM-based agents outperform baseline models in recursive reasoning tasks.

Artificial reasoners better approximate human strategic behavior.

The framework demonstrates improved solution quality in game simulations.

Abstract

LLM-driven multi-agent-based simulations have been gaining traction with applications in game-theoretic and social simulations. While most implementations seek to exploit or evaluate LLM-agentic reasoning, they often do so with a weak notion of agency and simplified architectures. We implement a role-based multi-agent strategic interaction framework tailored to sophisticated recursive reasoners, providing the means for systematic in-depth development and evaluation of strategic reasoning. Our game environment is governed by the umpire responsible for facilitating games, from matchmaking through move validation to environment management. Players incorporate state-of-the-art LLMs in their decision mechanism, relying on a formal hypergame-based model of hierarchical beliefs. We use one-shot, 2-player beauty contests to evaluate the recursive reasoning capabilities of the latest LLMs, providing a comparison to an established baseline model from economics and data from human experiments. Furthermore, we introduce the foundations of an alternative semantic measure of reasoning to the k-level theory. Our experiments show that artificial reasoners can outperform the baseline model in terms of both approximating human behaviour and reaching the optimal solution.