# Risk-Aware Online Conformal State Probing

arXiv: https://arxiv.org/abs/2609.25889 · HTML: https://mlsanity.com/paper/2609.25889/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [Conformal Inference for Online Prediction with Arbitrary Distribution Shifts](https://mlsanity.com/paper/2208.08401/) (2022)
- [Towards a Science of AI Agent Reliability](https://mlsanity.com/paper/2602.16666/) (2026)
- [Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions](https://mlsanity.com/paper/2310.05921/) (2023)
- [Timely and Massive Communication in 6G: Pragmatics, Learning, and Inference](https://mlsanity.com/paper/2306.17580/) (2023)
- [Distilling Calibration via Conformalized Credal Inference](https://mlsanity.com/paper/2501.06066/) (2025)
- [Prediction-Powered Communication with Distortion Guarantees](https://mlsanity.com/paper/2509.24373/) (2025)
- [Pragmatic Communication for Remote Control of Finite-State Markov Processes](https://mlsanity.com/paper/2405.10672/) (2024)
- [Strategic Decision Support for AI Agents](https://mlsanity.com/paper/2606.12587/) (2026)

## Abstract (arXiv)

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.