多智能体大语言模型无法相互探索

摘要

探索对于多智能体系统的可靠自主性至关重要，然而当前尚不明确大语言模型（LLM）智能体在相互交互时能否有效进行探索。研究表明，现代LLM智能体在此方面表现不佳，常呈现出短视和两极化的交互模式，导致协调欠佳及遗憾值增加。我们将这一挑战形式化为多智能体探索问题，并将其建模为部分可观测随机博弈（POSG）问题，其中智能体需探测同伴以推断其能力并识别有效交互策略。为此，我们提出多智能体上下文探索（MACE）框架，这是一种通过结构化同伴选择显式促进探索的轻量级方法。在上下文多样性与参数多样性两类设定下，MACE显著改善了探索行为及下游任务性能。理论上我们进一步证明，探索的价值随智能体多样性增加而提升。总体而言，我们的结果凸显了当前LLM智能体的根本局限，并强调了明确引导探索对于可靠多智能体自主性的重要性。代码将发布在 https://github.com/deeplearning-wisc/mace。

English

Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively when interacting with one another. We show that modern LLM agents fail to do so, often exhibiting myopic and polarized interaction patterns that lead to suboptimal coordination and increased regret. We formalize this challenge as the Multi-Agent Exploration problem, modeling it as a partially observable stochastic game (POSG) problem in which agents must probe peers to infer their capabilities and identify effective interaction strategies. To address this, we introduce Multi- Agent Contextual Exploration (MACE), a lightweight framework that explicitly promotes exploration through structured peer selection. Across both contextual and parametric diversity settings, MACE substantially improves exploration behavior and downstream task performance. We further show theoretically that the value of exploration increases with agent diversity. Overall, our results highlight a fundamental limitation of current LLM agents and underscore the importance of explicitly guided exploration for reliable multi-agent autonomy. Code will be released in https://github.com/deeplearning-wisc/mace