用大模型生成启发式规则，让任务规划更高效
Hierarchical Task Network Planning with LLM-Generated Heuristics
- 用大模型根据领域提示生成任务分解启发式
- 在6个基准测试中覆盖率达顶尖规划器水平
- 83%的问题减少搜索开销，适合复杂任务规划
HTN规划是一种经典规划的变体，不直接搜索动作序列，而是通过方法库将高层任务逐层分解直至生成可执行动作。该方法可引入领域知识加速求解，但也带来超越传统状态空间搜索的新挑战。尽管已有多种启发式与新算法提升HTN规划效率，其启发式信息仍不及经典规划算法。本文探究大语言模型（LLMs）是否能为HTN规划生成有效启发式，拓展Corrêa、Pereira和Seipp（2025）从经典规划到层次化规划的方法。在六组标准总序HTN基准域上，使用Pytrich规划器评估九个LLM在领域特定提示下的启发式表现，对比了TDG和LMCount等无领域依赖基线及PANDA规划器。结果表明，LLM生成的启发式几乎达到最优HTN规划器的覆盖范围，同时在83%的共用问题上显著降低搜索开销。
原文摘要 · Abstract (English)
HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tasks using a method library until only executable actions remain. On one hand, this allows one to introduce domain knowledge that can speed up the search for a solution through the method library. On the other hand, it creates challenges that go beyond those of classical state-space search. While recent research produced a number of heuristics and novel algorithms that speed up HTN planning, these heuristics are not yet as informative as those available in classical planning algorithms. We investigate whether large language models (LLMs) can generate effective search heuristics for HTN planning, extending the methodology of Corrêa, Pereira, and Seipp (2025) from classical to hierarchical planning. Using the Pytrich planner on six standard total-order HTN benchmark domains, we evaluate heuristics generated by nine LLMs under domain-specific prompting and compare them against the TDG and LMCount domain-independent baselines and the PANDA planner. Our results show that LLM-generated heuristics nearly match the coverage of the best available HTN planner, while substantially reducing search effort on 83% of shared problems.
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。