HCL-GP learns parameterized policies and reuses extracted components to achieve 98% accuracy on AppWorld benchmark tasks for LLM agents, outperforming static synthesis by 15.8 points on challenges.
You can implement new components based on the task at hand
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents
HCL-GP learns parameterized policies and reuses extracted components to achieve 98% accuracy on AppWorld benchmark tasks for LLM agents, outperforming static synthesis by 15.8 points on challenges.