OctoTools framework reports 9.3% average accuracy gain over GPT-4o across 16 tasks by adding tool cards, planner, and executor to LLMs in a training-free setup.
Title resolution pending
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
-
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
OctoTools framework reports 9.3% average accuracy gain over GPT-4o across 16 tasks by adding tool cards, planner, and executor to LLMs in a training-free setup.