Institution profile

Salesforce

Industry researchnorthamerica · us
Official website
Research library112linked papers
Opportunities0open roles
Selected work

Representative Papers

Agentic Confidence Calibration

Jan 22, 2026

Existing AI agents often fail in complex tasks due to overconfidence, and static calibration methods struggle to address compounded errors, tool uncertainty, and opaque failures along execution trajectories. This work formalizes the agent confidence calibration problem for the first time and introduces the Holistic Trajectory Calibration (HTC) framework, which models both macro-level dynamics and micro-level stability of execution trajectories to enable interpretable, cross-domain, and generalizable process-level calibration. The proposed General Agent Calibrator (GAC) consistently outperforms strong baselines across eight benchmarks, diverse large language models, and agent architectures, achieving state-of-the-art performance in Expected Calibration Error (ECE) and discrimination ability—particularly excelling on the cross-domain GAIA benchmark.

1 citationsRead paper
Recent publications

Latest Papers