让大模型自动学会任务分解方法，减少调用次数并提升规划效率。
Online Learning of HTN Methods for integrated LLM-HTN Planning
- 基于聊天大模型生成的分解方案，在线学习通用任务方法。
- 实验显示调用大模型次数减少，解决问题数量不降反增。
- 适合需要高效智能规划的交互式系统开发者。
我们提出在集成HTN规划与基于大语言模型的聊天机器人背景下，对层次化任务网络（HTN）方法进行在线学习。方法用于决定何时以及如何将任务分解为子任务。本方法基于ChatHTN规划器构建：当无适用方法时，ChatHTN会调用ChatGPT生成任务到基本任务的分解方案。本文扩展了ChatHTN，使其在获得分解方案后可从中学习，类似记忆化，但不同于传统记忆化，它能提取出可泛化的通用方法，不仅适用于当前实例，还可应用于同类型其他任务。我们在两个领域上进行了实验，结果表明该在线学习机制显著减少了对ChatGPT的调用次数，同时至少解决了同样数量的问题，在某些情况下甚至解决了更多问题。
原文摘要 · Abstract (English)
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.
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。