assessment_design
Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities
Yikai Zhao, Saurabh Pandey, Pradeep Kumar Misra · arXiv (2026) · doi:10.48550/arxiv.2610.03894 · gemini-3.1-flash-lite
Yikai Zhao, Saurabh Pandey, Pradeep Kumar Misra · arXiv (2026) · doi:10.48550/arxiv.2610.03894 · gemini-3.1-flash-lite