Economics Arena for Large Language Models

TL;DR

This paper introduces an economics-based dynamic game environment to evaluate large language models' rationality, strategic reasoning, and rule-following abilities, revealing differences among models like GPT-4 in convergence and performance.

Contribution

It proposes a novel dynamic evaluation framework using competitive economic games to assess LLMs' strategic and rational capabilities beyond static benchmarks.

Findings

Most LLMs exhibit rational strategies that increase payoffs.

GPT-4 converges faster to Nash Equilibria than other models.

Winning rates correlate with reasoning ability and rule-following skills.

Abstract

Large language models (LLMs) have been extensively used as the backbones for general-purpose agents, and some economics literature suggest that LLMs are capable of playing various types of economics games. Following these works, to overcome the limitation of evaluating LLMs using static benchmarks, we propose to explore competitive games as an evaluation for LLMs to incorporate multi-players and dynamicise the environment. By varying the game history revealed to LLMs-based players, we find that most of LLMs are rational in that they play strategies that can increase their payoffs, but not as rational as indicated by Nash Equilibria (NEs). Moreover, when game history are available, certain types of LLMs, such as GPT-4, can converge faster to the NE strategies, which suggests higher rationality level in comparison to other models. In the meantime, certain types of LLMs can win more often when game history are available, and we argue that the winning rate reflects the reasoning ability with respect to the strategies of other players. Throughout all our experiments, we observe that the ability to strictly follow the game rules described by natural languages also vary among the LLMs we tested. In this work, we provide an economics arena for the LLMs research community as a dynamic simulation to test the above-mentioned abilities of LLMs, i.e. rationality, strategic reasoning ability, and instruction-following capability.