DTDR dynamically retrieves relevant tools by modeling dependencies from demonstrations and conditioning on the evolving agent plan, improving function calling success rates by 23-104% over static retrievers across benchmarks.
P.; Tianjun, Z.; Ion, S.; and Joseph, E
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamic Tool Dependency Retrieval for Lightweight Function Calling
DTDR dynamically retrieves relevant tools by modeling dependencies from demonstrations and conditioning on the evolving agent plan, improving function calling success rates by 23-104% over static retrievers across benchmarks.