arXiv cs.CLPaperClaude Watch
Robust Function Calling for LLM Agents Under Interface Drift
Tool drift is a real production problem nobody talks about enough, and this is the first practical solution that works without retraining. The gains are substantial: BFCL accuracy climbs from 58% to 80%. For anyone running agent systems in production where tool schemas or availability changes, this is the kind of lightweight repair you should plug in immediately. For Claude users building agents, this becomes table stakes.