Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy

2024-07-09 · Zhenyu Guan, Xiangyu Kong, Fangwei Zhong, Yizhou Wang

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.

📄 PDF Abstract BibTeX arXiv:2407.06813

Code (1)

todexter3/richelieu 공식 구현 pytorch

No Press Diplomacy: Modeling Multi-Agent Gameplay

2019-09-04 · Philip Paquette, Yuchen Lu, Steven Bocco, Max O. Smith 외

Diplomacy is a seven-player non-stochastic, non-cooperative game, where agents acquire resources through a mix of teamwork and betrayal. Reliance on trust and coordination makes Diplomacy the first non-cooperative multi-…

Reinforcement Learning Reinforcement Learning (RL)

No-Press Diplomacy: Modeling Multi-Agent Gameplay

2019-12-01 · NeurIPS 2019 12 · Philip Paquette, Yuchen Lu, Seton Steven Bocco, Max Smith 외

Reinforcement Learning Reinforcement Learning (RL)

No-Press Diplomacy from Scratch

2021-10-06 · NeurIPS 2021 12 · Anton Bakhtin, David Wu, Adam Lerer, Noam Brown

Prior AI successes in complex games have largely focused on settings with at most hundreds of actions at each decision point. In contrast, Diplomacy is a game with more than 10^20 possible actions per turn. Previous atte…

Starcraft

Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy

2025-12-20 · Wenkai Li, Lynnette Hui Xian Ng, Andy Liu, Daniel Fried arxiv

The study of negotiation styles dates back to Aristotle's ethos-pathos-logos rhetoric. Prior efforts primarily studied the success of negotiation agents. Here, we shift the focus towards the styles of negotiation strateg…

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

2022-10-11 · Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray 외

No-press Diplomacy is a complex strategy game involving both cooperation and competition that has served as a benchmark for multi-agent AI research. While self-play reinforcement learning has resulted in numerous success…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)