Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities
arXiv:2610.03894v1 Announce Type: new Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier chat APIs hide the model's token probabilities; the agent's stated confidence barely beats chance on th…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-06 04:00 · arXiv cs.AI
Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities