优化游戏中的协作问题解决
Collaborative Problem-Solving in an Optimization Game
AI总结：
本文提出了一种新的对话游戏，通过协作解决双人旅行商问题，结合大语言模型与符号机制，实现了在自我对战中45%的最优解率，并展示了与人类用户协作和泛化能力。
摘要：
支持人类用户解决复杂任务的对话代理近年来受到了广泛关注。许多此类任务都是NP难的优化问题，需要仔细地在解空间中进行协作探索。我们介绍了一个新的对话游戏，其中代理们协作解决一个双人旅行商问题，同时还有一个结合大语言模型提示与符号机制进行状态跟踪和基础的代理。我们的最佳代理在自我对战中能够解决45%的游戏最优解。它还展示了成功与人类用户协作以及泛化到不熟悉图结构的能力。
英文摘要：
Dialogue agents that support human users in solving complex tasks have received much attention recently. Many such tasks are NP-hard optimization problems that require careful collaborative exploration of the solution space. We introduce a novel dialogue game in which the agents collaboratively solve a two-player Traveling Salesman problem, along with an agent that combines LLM prompting with symbolic mechanisms for state tracking and grounding. Our best agent solves 45% of games optimally in self-play. It also demonstrates an ability to collaborate successfully with human users and generalize to unfamiliar graphs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
