Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents

Computer Science > Artificial Intelligence [Submitted on 7 May 2026] Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents Shirin Sohrabi, Haritha Ananthakrishnan, Harsha Kokel, Kavitha Srinivas, Michael Katz We present a dynamic policy-learning approach that combines generalized planning and hierarchical task decomposition for LLM-based agents. Our method, Hierarchical Component Learning for Generalized Policies (HCL-GP ), learns parameterized policies that generalize across task instances and automatically extracts reusable components from successful executions, organizing them into a component library for compositional policy generation. We address three challenges: (1) learning components through automated decomposition, (2) generalizing components to maximize reuse, and (3) efficient retrieval via semantic search. Evaluated on the AppWorld benchmark, our approach achieves 98.2% accuracy on normal tasks and 97.8% on challenge tasks with unseen applications, improving 15.8 points over static synthesis on challenging scenarios. For open-source models, dynamic reuse enables 62.5% success versus near-zero without reuse. This demonstrates that classical planning concepts can be effectively integrated with LLM agents for improved accuracy and efficiency. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2605.06957 [cs.AI]   (or arXiv:2605.06957v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.06957 Focus to learn more Submission history From: Michael Katz [view email] [v1] Thu, 7 May 2026 21:22:33 UTC (156 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)