CAHL jointly optimizes hierarchical policies for tool-augmented LLMs via RLVR and reports improved results on API-Bank, BFCL, and Bamboogle.
arXiv preprint arXiv:2509.14718 , year=
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
-
Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs
CAHL jointly optimizes hierarchical policies for tool-augmented LLMs via RLVR and reports improved results on API-Bank, BFCL, and Bamboogle.