Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems

• URL: http://arxiv.org/abs/2508.17403v2
• Date: Mon, 01 Sep 2025 15:43:01 GMT
• Title: Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems
• Authors: Yinsong Wang, Quan Zeng, Xiao Liu, Yu Ding,
• Abstract summary: We introduce Mutual Information Surprise (MIS), a new framework that redefines surprise as a signal of epistemic growth.<n>MIS quantifies the impact of new observations on mutual information, enabling autonomous systems to reflect on their learning progression.<n>We show that MISRP-governed strategies significantly outperform classical surprise-based approaches in stability, responsiveness, and predictive accuracy.
• Score: 9.92363495932515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent breakthroughs in autonomous experimentation have demonstrated remarkable physical capabilities, yet their cognitive control remains limited--often relying on static heuristics or classical optimization. A core limitation is the absence of a principled mechanism to detect and adapt to the unexpectedness. While traditional surprise measures--such as Shannon or Bayesian Surprise--offer momentary detection of deviation, they fail to capture whether a system is truly learning and adapting. In this work, we introduce Mutual Information Surprise (MIS), a new framework that redefines surprise not as anomaly detection, but as a signal of epistemic growth. MIS quantifies the impact of new observations on mutual information, enabling autonomous systems to reflect on their learning progression. We develop a statistical test sequence to detect meaningful shifts in estimated mutual information and propose a mutual information surprise reaction policy (MISRP) 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 MISRP-governed strategies significantly outperform classical surprise-based approaches in stability, responsiveness, and predictive accuracy. By shifting surprise from reactive to reflective, MIS offers a path toward more self-aware and adaptive autonomous systems.

Related papers

• Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection [4.514361164656055]
  We introduce a taxonomy of ten categories of hidden intentions, organised by intent, mechanism, context, and impact.<n>We systematically assess detection methods, including reasoning and non-reasoning LLM judges.<n>We find that detection collapses in realistic open-world settings, particularly under low-prevalence conditions.
  arXiv  Detail & Related papers  (2026-01-26T14:59:17Z)
• From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM [52.64097278841485]
  Review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions.<n>Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques.
  arXiv  Detail & Related papers  (2025-09-25T14:15:43Z)
• Mutual Information Tracks Policy Coherence in Reinforcement Learning [0.0]
  Reinforcement Learning (RL) agents face degradation from sensor faults, actuator wear, and environmental shifts.<n>We present an information-theoretic framework that reveals both the fundamental dynamics of RL and provides practical methods for diagnosing deployment-time anomalies.
  arXiv  Detail & Related papers  (2025-09-12T17:24:20Z)
• Preliminary Investigation into Uncertainty-Aware Attack Stage Classification [81.28215542218724]
  This work addresses the problem of attack stage inference under uncertainty.<n>We propose a classification approach based on Evidential Deep Learning (EDL), which models predictive uncertainty by outputting parameters of a Dirichlet distribution over possible stages.<n>Preliminary experiments in a simulated environment demonstrate that the proposed model can accurately infer the stage of an attack with confidence.
  arXiv  Detail & Related papers  (2025-08-01T06:58:00Z)
• Designing Robust Software Sensors for Nonlinear Systems via Neural Networks and Adaptive Sliding Mode Control [2.884893167166808]
  This paper presents a novel approach to designing software sensors for nonlinear dynamical systems.<n>Unlike traditional model-based observers that rely on explicit transformations or linearization, the proposed framework integrates neural networks with adaptive Sliding Mode Control (SMC)<n>The training methodology leverages the system's governing equations as a physics-based constraint, enabling observer synthesis without access to ground-truth state trajectories.
  arXiv  Detail & Related papers  (2025-07-09T13:06:58Z)
• Confidence Adjusted Surprise Measure for Active Resourceful Trials (CA-SMART): A Data-driven Active Learning Framework for Accelerating Material Discovery under Resource Constraints [7.188573079798082]
  A surrogate machine learning (ML) model mimics the scientific discovery process of a human scientist.<n>The concept of surprise (capturing the divergence between expected and observed outcomes) has demonstrated significant potential to drive experimental trials.<n>We propose the Confidence-Adjusted Surprise Measure for Active Resourceful Trials (CA-), a novel Bayesian active learning framework tailored for optimizing data-driven experimentation.
  arXiv  Detail & Related papers  (2025-03-27T02:21:42Z)
• OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting [4.71781133841068]
  Provenance-based Intrusion Detection Systems (PIDSes) have been widely used for endpoint threat analysis.<n>Due to the evolution of attack techniques, rules cannot dynamically model all the characteristics of attackers.<n>Anomaly-based detection systems face a massive false positive problem because they cannot distinguish between changes in normal behavior and real attack behavior.
  arXiv  Detail & Related papers  (2025-03-05T02:08:12Z)
• Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Review of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems [0.0]
  This paper presents a comprehensive review on navigating uncertainties in machine learning (ML) It lists uncertainty-aware approaches into probabilistic methods and non-probabilistic methods. The review aims to assist researchers and practitioners in making informed decisions when utilizing ML techniques to address uncertainties in structural dynamic problems.
  arXiv  Detail & Related papers  (2024-08-16T09:43:01Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• A Neural Active Inference Model of Perceptual-Motor Learning [62.39667564455059]
  The active inference framework (AIF) is a promising new computational framework grounded in contemporary neuroscience. In this study, we test the ability for the AIF to capture the role of anticipation in the visual guidance of action in humans. We present a novel formulation of the prior function that maps a multi-dimensional world-state to a uni-dimensional distribution of free-energy.
  arXiv  Detail & Related papers  (2022-11-16T20:00:38Z)
• Sparsity in Continuous-Depth Neural Networks [2.969794498016257]
  We study the influence of weight and feature sparsity on forecasting and on identifying the underlying dynamical laws. We curate real-world datasets consisting of human motion capture and human hematopoiesis single-cell RNA-seq data.
  arXiv  Detail & Related papers  (2022-10-26T12:48:12Z)
• The Unreasonable Effectiveness of Deep Evidential Regression [72.30888739450343]
  A new approach with uncertainty-aware regression-based neural networks (NNs) shows promise over traditional deterministic methods and typical Bayesian NNs. We detail the theoretical shortcomings and analyze the performance on synthetic and real-world data sets, showing that Deep Evidential Regression is a quantification rather than an exact uncertainty.
  arXiv  Detail & Related papers  (2022-05-20T10:10:32Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)
• Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift [62.997667081978825]
  Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise.
  arXiv  Detail & Related papers  (2020-01-13T13:54:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.