arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.12901cs.AI
收藏

用于集成LLM-HTN规划的HTN方法在线学习

Online Learning of HTN Methods for integrated LLM-HTN Planning

Computer Science \& Engineering, Lehigh University;Bethlehem, PA 18015-3084 USA

Yuesheng Xu, Hector Munoz-Avila

AI总结:

本研究针对集成LLM-HTN规划的需求,提出在线学习HTN方法的机制,扩展ChatHTN规划器以从ChatGPT生成的任务分解中学习广义方法,减少LLM调用次数并提升规划性能。

摘要:

我们提出在集成层次任务网络(HTN)规划与基于大语言模型(LLM)的聊天机器人语境下,对HTN方法进行在线学习。HTN方法指示何时以及如何将任务分解为子任务。我们的方法学习器构建在ChatHTN规划器之上。当任务没有可用的适用方法时,ChatHTN会查询ChatGPT生成该任务到原语任务的分解。本研究中,我们扩展了ChatHTN:当ChatGPT生成任务分解时,ChatHTN会从中学习,类似于记忆化;但与记忆化不同的是,它学习的是广义方法,不仅适用于遇到的特定实例,还适用于同一任务的其他实例。我们在两个领域进行实验,结果表明,该在线学习过程减少了对ChatGPT的调用次数,同时解决的问题数量至少相同,在某些情况下甚至更多。

英文摘要:

We present online learning of Hierarchical Task Network (HTN) methods in the context of integrated HTN planning and LLM-based chatbots. Methods indicate when and how to decompose tasks into subtasks. Our method learner is built on top of the ChatHTN planner. ChatHTN queries ChatGPT to generate a decomposition of a task into primitive tasks when no applicable method for the task is available. In this work, we extend ChatHTN. Namely, when ChatGPT generates a task decomposition, ChatHTN learns from it, akin to memoization. However, unlike memoization, it learns a generalized method that applies not only to the specific instance encountered, but to other instances of the same task. We conduct experiments on two domains and demonstrate that our online learning procedure reduces the number of calls to ChatGPT while solving at least as many problems, and in some cases, even more.

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。

↑