METRO：面向非协作对话的专家对话 transcripts 中的策略诱导
METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues
AI总结：
METRO 通过大规模语言模型从原始 transcripts 自动诱导策略动作和规划逻辑，提出策略森林结构，实验显示其在两个基准上性能优越，具有跨任务迁移能力。
摘要：
传统非协作对话代理开发需要手动编码专家策略，难以扩展。我们提出 METRO，利用大规模语言模型从原始 transcripts 自动诱导策略动作和规划逻辑。METRO 将专家知识形式化为策略森林，一种分层结构，捕捉短期响应（节点）和长期战略预见（分支）。实验结果显示，METRO 在两个基准上表现优异，比现有方法平均高出 9%-10%。进一步分析揭示了 METRO 的成功原因（战略行为多样性与预见性），并展示了其跨任务迁移能力。这为以低成本、可扩展方式构建非协作代理提供了新见解。代码可在 https://github.com/Humphrey-0125/METRO 获取。
英文摘要：
Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codification of expert strategies. We propose \ours, a method that leverages large language models to autonomously induce both strategy actions and planning logic directly from raw transcripts. METRO formalizes expert knowledge into a Strategy Forest, a hierarchical structure that captures both short-term responses (nodes) and long-term strategic foresight (branches). Experimental results across two benchmarks show that METRO demonstrates promising performance, outperforming existing methods by an average of 9%-10%. Our further analysis not only reveals the success behind METRO (strategic behavioral diversity and foresight), but also demonstrates its robust cross-task transferability. This offers new insights into building non-collaborative agents in a cost-effective and scalable way. Our code is available at https://github.com/Humphrey-0125/METRO.
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。
