ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.
arXiv preprint arXiv:2502.11435
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.
citing papers explorer
-
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.
-
ToolRL: Reward is All Tool Learning Needs
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.