# Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems

arXiv: https://arxiv.org/abs/2508.17403 · HTML: https://mlsanity.com/paper/2508.17403/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 64 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors](https://mlsanity.com/paper/2203.11070/) (2022)
- [Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations](https://mlsanity.com/paper/1802.00187/) (2018)
- [RePAD: Real-time Proactive Anomaly Detection for Time Series](https://mlsanity.com/paper/2001.08922/) (2020)
- [Concept Drift Monitoring and Diagnostics of Supervised Learning Models via Score Vectors](https://mlsanity.com/paper/2012.06916/) (2020)
- [A taxonomy of surprise definitions](https://mlsanity.com/paper/2209.01034/) (2022)
- [Anomaly Detection at Scale: The Case for Deep Distributional Time Series Models](https://mlsanity.com/paper/2007.15541/) (2020)
- [Null Hypothesis Test for Anomaly Detection](https://mlsanity.com/paper/2210.02226/) (2022)
- [An Augmented Surprise-guided Sequential Learning Framework for Predicting the Melt Pool Geometry](https://mlsanity.com/paper/2401.05579/) (2024)
- [Measuring Surprise in the Wild](https://mlsanity.com/paper/2305.07733/) (2023)
- [Human Inference in Changing Environments With Temporal Structure](https://mlsanity.com/paper/2101.11143/) (2021)
- [Dynamic Exploration-Exploitation Trade-Off in Active Learning Regression with Bayesian Hierarchical Modeling](https://mlsanity.com/paper/2304.07665/) (2023)

## Abstract (arXiv)

A community of researchers appears to think that a machine can be surprised and have introduced various surprise measures, principally the Shannon Surprise and the Bayesian Surprise. The questions of what constitutes a surprise and how to react to one still elicit debates. In this work, we introduce Mutual Information Surprise (MIS), a new framework that redefines surprise not as anomaly measure, but as a signal of epistemic growth. Furthermore, we develop a statistical test sequence that could trigger a surprise reaction and propose a MIS-based reaction policy that dynamically governs system behavior through sampling adjustment and process forking. Empirical evaluations -- on both synthetic domains and a dynamic pollution map estimation task -- show that a system governed by the MIS-based reaction policy significantly outperforms those under classical surprise-based approaches in stability, responsiveness, and predictive accuracy. The important implication of our new proposal is that MIS quantifies the impact of new observations on mutual information, shifts surprise from reactive to reflective, enables reflection on learning progression, and thus offers a path toward self-aware and adaptive autonomous systems. We expect the new surprise measure to play a critical role in further advancing autonomous systems on their ability to learn and adapt in a complex and dynamic environment.