Building AIs with adaptive behaviors in human-AI cooperation stands as a pivotal focus in AGI research. Current methods for developing cooperative agents predominantly rely on learning-based methods, where policy generalization heavily hinges on past interactions with specific teammates. These approaches constrain the agent's capacity to recalibrate its strategy when confronted with novel teammates. We propose \textbf{ProAgent}, a novel framework that harnesses large language models (LLMs) to fashion a \textit{pro}active \textit{agent} empowered with the ability to anticipate teammates' forthcoming decisions and formulate enhanced plans for itself. ProAgent excels at cooperative reasoning with the capacity to dynamically adapt its behavior to enhance collaborative efforts with teammates. Moreover, the ProAgent framework exhibits a high degree of modularity and interpretability, facilitating seamless integration to address a wide array of coordination scenarios. Experimental evaluations conducted within the framework of \textit{Overcook-AI} unveil the remarkable performance superiority of ProAgent, outperforming five methods based on self-play and population-based training in cooperation with AI agents. Further, when cooperating with human proxy models, its performance exhibits an average improvement exceeding 10\% compared to the current state-of-the-art, COLE. The advancement was consistently observed across diverse scenarios involving interactions with both AI agents of varying characteristics and human counterparts. These findings inspire future research for human-robot collaborations. For a hands-on demonstration, please visit \url{https://pku-proagent.github.io}.

翻译：在人类与人工智能的协作中构建具有自适应行为的人工智能，是通用人工智能（AGI）研究的关键焦点。当前开发协作代理的方法主要依赖基于学习的策略，这些策略的泛化能力高度依赖于过往与特定队友的交互经验。当面对新队友时，此类方法限制了代理重新调整策略的能力。我们提出**ProAgent**——一种新颖的框架，通过利用大语言模型（LLMs）打造一个具备预见队友后续决策并制定优化自身规划的**主动式代理**。ProAgent在协作推理方面表现出色，能够动态调整自身行为以增强与队友的协同效果。此外，该框架具有高度的模块化与可解释性，便于无缝集成以应对多种协作场景。在*Overcook-AI*框架下的实验评估显示，ProAgent在与基于自博弈和种群训练的五个AI代理方法的协作中展现出显著性能优势。进一步地，在与人类代理模型协作时，其性能相比当前最先进方法COLE平均提升超过10%。这一进步在与不同特征的AI代理及人类同伴交互的多样化场景中均得到持续验证。这些发现为未来人机协作研究提供了启示。实操演示请访问\url{https://pku-proagent.github.io}。