评估 LLMs（如 GPT-4o、LLaMA-3.3）在经典博弈中的表现，包括 Prisoner’s Dilemma、Ultimatum Game 和 Public Goods Game。 我们提出了一种多智能体路由框架 PRIME-Router，可在重复交互中提升策略适应性和角色一致性。
May 21, 2025
Evaluating LLMs (e.g., GPT-4o, LLaMA-3.3) in classic games such as Prisoner’s Dilemma, Ultimatum Game, and Public Goods Game. We propose a multi-agent routing framework PRIME-Router that improves strategic adaptability and persona consistency across repeated interactions.
May 21, 2025