多智能體LLM未能相互探索

摘要

探索對於多智能體系統中可靠的自動化至關重要，然而目前尚不清楚大型語言模型（LLM）智能體在彼此互動時能否有效地進行探索。我們發現，現代LLM智能體在這方面表現不佳，經常呈現短視且極化的互動模式，導致協調不佳並增加遺憾。我們將此挑戰正式定義為「多智能體探索問題」，將其建模為部分可觀測隨機博弈（POSG）問題，其中智能體必須探測同伴以推斷其能力並找出有效的互動策略。為了解決這個問題，我們提出了「多智能體情境探索」（MACE），這是一個輕量級框架，通過結構化的同伴選擇明確促進探索。在情境多樣性和參數多樣性兩種設定下，MACE顯著改善了探索行為與下游任務表現。我們進一步從理論上證明，探索的價值隨著智能體多樣性增加而提升。總體而言，我們的結果凸顯了當前LLM智能體的基本限制，並強調了明確引導的探索對於可靠的多智能體自動化的重要性。程式碼將於 https://github.com/deeplearning-wisc/mace 發布。

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