Diplomacy is one of the most sophisticated activities in human society, involving complex interactions among multiple parties that require skills in social reasoning, negotiation, and long-term strategic planning. Previous AI agents have demonstrated their ability to handle multi-step games and large action spaces in multi-agent tasks. However, diplomacy involves a staggering magnitude of decision spaces, especially considering the negotiation stage required. While recent agents based on large language models (LLMs) have shown potential in various applications, they still struggle with extended planning periods in complex multi-agent settings. Leveraging recent technologies for LLM-based agents, we aim to explore AI's potential to create a human-like agent capable of executing comprehensive multi-agent missions by integrating three fundamental capabilities: 1) strategic planning with memory and reflection; 2) goal-oriented negotiation with social reasoning; and 3) augmenting memory through self-play games for self-evolution without human in the loop.

翻译：外交是人类社会最复杂的活动之一，涉及多方之间的复杂互动，需要社会推理、谈判和长期战略规划等技能。以往的AI智能体已证明其能够处理多智能体任务中的多步博弈和巨大行动空间。然而，外交涉及决策空间的惊人复杂性，尤其是在考虑必要的谈判阶段时。尽管近期基于大型语言模型（LLM）的智能体在多种应用中展现出潜力，但在复杂多智能体环境中进行长期规划仍面临困难。借助基于LLM智能体的最新技术，我们旨在探索AI的潜力，通过整合三项核心能力构建类人智能体以执行综合性多智能体任务：1）具备记忆与反思能力的战略规划；2）基于社会推理的目标导向型谈判；3）通过自我博弈增强记忆以实现无需人工干预的自进化。