Tool use / function calling

PRefine

Latent Preference Modeling for Cross-Session Personalized Tool Calling

On the frontierfirst seen Apr 20, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.