Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely primarily on learning-based methods, whose policy generalization depends heavily on the diversity of teammates they interact with during the training phase. Such reliance, however, constrains the agents' capacity for strategic adaptation when cooperating with unfamiliar teammates, which becomes a significant challenge in zero-shot coordination scenarios. To address this challenge, we propose ProAgent, a novel framework that harnesses large language models (LLMs) to create proactive agents capable of dynamically adapting their behavior to enhance cooperation with teammates. ProAgent can analyze the present state, and infer the intentions of teammates from observations. It then updates its beliefs in alignment with the teammates' subsequent actual behaviors. Moreover, ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various of coordination scenarios. Experimental evaluations conducted within the Overcooked-AI environment unveil the remarkable performance superiority of ProAgent, outperforming five methods based on self-play and population-based training when cooperating with AI agents. Furthermore, in partnered with human proxy models, its performance exhibits an average improvement exceeding 10% compared to the current state-of-the-art method. For more information about our project, please visit~\url{https://pku-proagent.github.io}.

翻译：在协作任务中构建具有自适应行为的智能体，是多智能体系统领域的核心目标。当前开发协作智能体的方法主要依赖基于学习的范式，其策略泛化能力高度依赖于训练阶段交互队友的多样性。然而，这种依赖性限制了智能体在与陌生队友协作时的策略适应能力，成为零样本协作场景中的重大挑战。针对该问题，我们提出ProAgent——一种利用大型语言模型（LLMs）构建主动型智能体的创新框架，使其能够动态调整行为以增强与队友的协作能力。ProAgent能够分析当前状态，从观测中推断队友的意图，并根据队友后续的实际行为更新自身信念。此外，ProAgent具备高度的模块化与可解释性，易于集成至多种协作场景中。在Overcooked-AI环境中的实验评估表明，ProAgent在与基于自博弈和种群训练的五种方法协作时展现出显著的性能优势。当与人类代理模型配合时，其性能相比当前最优方法平均提升超过10%。更多项目信息请访问~\url{https://pku-proagent.github.io}。