多智能体语言模型无法相互探索
Multi-Agent LLMs Fail to Explore Each Other
- University of Wisconsin–Madison（威斯康星大学麦迪逊分校）
- University of California, Santa Barbara（加州大学圣巴巴拉分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究多智能体系统中LLM智能体相互探索的问题，提出轻量级框架MACE，通过结构化同伴选择促进探索，改善了探索行为和任务性能，凸显当前LLM智能体局限，强调明确引导探索对多智能体自主性的重要性。
AI中文摘要：
在多智能体系统中，探索对于可靠的自主性至关重要，但尚不清楚大语言模型（LLM）智能体在相互交互时能否有效探索。我们发现现代LLM智能体无法做到这一点，常表现出短视和两极分化的交互模式，导致次优协调和遗憾增加。我们将此挑战形式化为多智能体探索问题，建模为部分可观测随机博弈（POSG）问题，其中智能体必须探测同伴以推断其能力并识别有效交互策略。为解决此问题，我们引入多智能体上下文探索（MACE），一个通过结构化同伴选择明确促进探索的轻量级框架。在上下文和参数多样性设置中，MACE显著改善探索行为和下游任务性能。我们还从理论上表明探索的价值随智能体多样性增加。总体而言，我们的结果凸显了当前LLM智能体的一个基本限制，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。代码将在这个https网址发布。
英文摘要：
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
