What the Trace Shows and What the Label Says: Auditing Behavioral Detectors in Agent Evaluation

arXiv:2610.30491v1 Announce Type: new Abstract: LLM agents are often evaluated by reducing execution traces to labels such as final-answer correctness, tool verification, and fault propagation. These labels are measurements produced by parsers, behavioral detectors, and harness rules, and they may n

arXiv cs.AIFreitag 06:00 · 23.10.1 Min. Lesezeit