对话智能体协作求解旅行商难题，提升人机协同效率
Collaborative Problem-Solving in an Optimization Game
- 设计双人旅行商博弈，结合大模型与符号推理追踪状态
- 自对弈中45%情况下找到最优解，具备强泛化能力
- 可有效与人类合作，适配陌生图结构场景
近期，支持人类解决复杂任务的对话智能体受到广泛关注。许多此类任务属于NP难优化问题，需在解空间中进行精细协作探索。本文提出一种新型对话博弈，由智能体协作求解双人旅行商问题，并引入一个结合大语言模型提示与符号机制的状态追踪和语义定位智能体。最佳智能体在自对弈中45%的情况下实现最优解；同时展现出与人类用户成功协作的能力，并可推广至未见过的图结构。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。