LLM代理相互协作时难以有效探索，新框架MACE显著提升探索能力。
Multi-Agent LLMs Fail to Explore Each Other
- 设计MACE框架，通过结构化同伴选择促进代理主动探索。
- 在多种场景下，MACE使探索行为和任务表现显著提升。
- 发现代理多样性越高，探索价值越大，适合多智能体系统研究者。
探索对多智能体系统的可靠自主至关重要，但当前大型语言模型（LLM）代理在相互交互时是否能有效探索仍不明确。我们发现现代LLM代理在此方面表现不佳，常呈现短视且极化的互动模式，导致协调效果差并增加后悔值。我们将此问题形式化为多智能体探索问题，将其建模为部分可观测随机博弈（POSG），要求代理通过探测同伴来推断其能力并识别有效交互策略。为此，我们提出轻量级框架MACE，通过结构化同伴选择显式促进探索。在上下文与参数多样性设置下，MACE均显著改善了探索行为和下游任务性能。我们进一步从理论上证明，探索价值随代理多样性增加而上升。总体而言，结果揭示了当前LLM代理的根本局限，并强调了显式引导探索对可靠多智能体自主的重要性。代码将发布于https://github.com/deeplearning-wisc/mace。
原文摘要 · Abstract (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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。