AI RESEARCH
Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents
arXiv CS.AI
•
ArXi:2605.06957v1 Announce Type: new 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.