Risk-Aware Online Conformal State Probing

2026-09-22

AI Summary

研究提出在线一致性状态探测(OCSP)方法，解决AI自主代理在安全关键场景下的状态不确定性问题，控制未查询错误并最小化探测率。

Abstract

AI-based autonomous agents, typically hosted at data centers, must acquire state information from robots or edge devices in order to issue informed control decisions. Managing uncertainty about the state is particularly consequential in safety-critical settings, in which average-case guarantees are insufficient. In this context, we study a sequential decision maker process that jointly decides which actions to take and when to probe given access to an arbitrary state prediction model. We propose online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions. OCSP is designed to provably control the missed query error (MQE), i.e., the fraction of instances where probing would have been beneficial, while minimizing the probing rate. OCSP can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning. We validate OCSP through numerical simulations to verify theoretical guarantees and to assess performance trade-offs as a function of the calibration of the state predictor.

Problem

• Risk-Aware
• State Probing
• Autonomous Agents
• Safety-Critical
• Uncertainty Management

Innovation

• Online Conformal State Probing
• Worst-Case Reliability
• Missed Query Error (MQE)
• Probing Rate Minimization