AI RESEARCH
Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use
arXiv CS.CL
•
ArXi:2605.15041v1 Announce Type: cross Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict structural validity. We approach this problem from a case-based perspective to present CAST, a case-driven framework that treats historical execution trajectories as structured cases. Instead of reusing raw exemplar outputs, CAST extracts case-derived signals to identify complexity profiles for estimating optimal reasoning strategies, alongside failure profiles to map likely structural breakdowns.