让AI通过提问和积累经验，持续提升任务规划能力。
$How^{2}$: How to learn from procedural How-to questions
- 构建记忆型智能体框架，支持提问、存储并复用如何做事的答案。
- 在Minecraft环境中，抽象且与当前状态解耦的答案最有助于长期学习。
- 适合希望提升AI自主规划能力的研究者和开发者。
面对规划问题的智能体可利用对“如何做某事”问题的回答来减少不确定性、填补知识空白，从而帮助解决当前及未来任务。然而，这类问题的答案形式多样，从可执行动作序列到高层次子目标描述均有，使得AI难以有效提问，专家也难高效作答。为此，我们提出How²，一个记忆型智能体框架，使智能体能在交互环境中提出如何做事的问题，存储答案，并实现终身学习。我们在Plancraft（一个Minecraft Crafting环境）中评估该方法，任务是通过操作物品库存完成装配。使用在不同抽象层次上作答的教师模型——从可执行动作序列到高层次子目标描述——我们发现，长期学习智能体最受益于抽象化且与当前状态解耦的答案。How²为基于大模型的智能体在交互环境中持续提升规划能力提供了新路径。
原文摘要 · Abstract (English)
An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both current and future tasks. However, their open ended nature, where valid answers to "How do I X?" range from executable actions to high-level descriptions of X's sub-goals, makes them challenging for AI agents to ask, and for AI experts to answer, in ways that support efficient planning. We introduce $How^{2}$, a memory agent framework that enables agents to ask how-to questions, store the answers, and reuse them for lifelong learning in interactive environments. We evaluate our approach in Plancraft, a Minecraft crafting environment, where agents must complete an assembly task by manipulating inventory items. Using teacher models that answer at varying levels of abstraction, from executable action sequences to high-level subgoal descriptions, we show that lifelong learning agents benefit most from answers that are abstracted and decoupled from the current state. $How^{2}$ offers a way for LLM-based agents to improve their planning capabilities over time by asking questions in interactive environments.
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。