Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference

• URL: http://arxiv.org/abs/2602.06029v1
• Date: Thu, 05 Feb 2026 18:58:32 GMT
• Title: Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference
• Authors: Yingke Li, Anjali Parashar, Enlu Zhou, Chuchu Fan,
• Abstract summary: Active inference unifies exploration and exploitation by minimizing the Expected Free Energy (EFE)<n>Insufficient curiosity can drive myopic exploitation and prevent uncertainty resolution, while excessive curiosity can induce unnecessary exploration and regret.<n>We establish the first theoretical guarantee for EFE-minimizing agents, showing that a single requirement--sufficient curiosity--simultaneously ensures self-consistent learning and no-regret optimization.
• Score: 20.135421015458817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task performance) through a curiosity coefficient. Yet it has been unclear when this balance yields both coherent learning and efficient decision-making: insufficient curiosity can drive myopic exploitation and prevent uncertainty resolution, while excessive curiosity can induce unnecessary exploration and regret. We establish the first theoretical guarantee for EFE-minimizing agents, showing that a single requirement--sufficient curiosity--simultaneously ensures self-consistent learning (Bayesian posterior consistency) and no-regret optimization (bounded cumulative regret). Our analysis characterizes how this mechanism depends on initial uncertainty, identifiability, and objective alignment, thereby connecting AIF to classical Bayesian experimental design and Bayesian optimization within one theoretical framework. We further translate these theories into practical design guidelines for tuning the epistemic-pragmatic trade-off in hybrid learning-optimization problems, validated through real-world experiments.

Related papers

• Observationally Informed Adaptive Causal Experimental Design [55.998153710215654]
  We propose Active Residual Learning, a new paradigm that leverages the observational model as a foundational prior.<n>This approach shifts the experimental focus from learning target causal quantities from scratch to efficiently estimating the residuals required to correct observational bias.<n> Experiments on synthetic and semi-synthetic benchmarks demonstrate that R-Design significantly outperforms baselines.
  arXiv  Detail & Related papers  (2026-03-04T06:52:37Z)
• Pragmatic Curiosity: A Hybrid Learning-Optimization Paradigm via Active Inference [20.135421015458817]
  "pragmatic curiosity" is a hybrid learning-optimization paradigm derived from active inference.<n>We demonstrate the practical effectiveness and flexibility of pragmatic curiosity on various real-world hybrid tasks.
  arXiv  Detail & Related papers  (2026-02-05T18:42:29Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning [49.28548464288051]
  Composed Image Retrieval (CIR) enables image search by combining a reference image with modification text.<n>In intrinsic noise in CIR triplets incurs intrinsic uncertainty and threatens the model's robustness.<n>This paper introduces a Heterogeneous Uncertainty-Guided (HUG) paradigm to overcome these limitations.
  arXiv  Detail & Related papers  (2026-01-16T16:05:49Z)
• The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents [0.6117371161379209]
  We propose a formal probabilistic framework that provides agents with a non-altruistic motive for bidirectional knowledge exchange.<n>We show how these accumulated belief states serve as verifiable reward signals for Reinforcement Learning from Human Feedback (RLHF) and high-quality data filters for Supervised Fine-Tuning (SFT)<n> Simulation results validate that this uncertainty-driven strategy significantly outperforms random baselines in heterogeneous environments.
  arXiv  Detail & Related papers  (2025-12-24T02:02:25Z)
• Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation [68.106428321492]
  Large language models (LLMs) demonstrate advanced reasoning abilities, enabling robots to understand natural language instructions and generate high-level plans with appropriate grounding.<n>LLMs hallucinations present a significant challenge, often leading to overconfident yet potentially misaligned or unsafe plans.<n>We present Combined Uncertainty estimation for Reliable Embodied planning (CURE), which decomposes the uncertainty into epistemic and intrinsic uncertainty, each estimated separately.
  arXiv  Detail & Related papers  (2025-10-09T10:26:58Z)
• Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning [19.777830269089588]
  Existing work on mitigating catastrophic forgetting during large language models (LLMs) fine-tuning has primarily focused on preserving performance on previously seen data.<n>We formalize the notion of Ignorance Awareness and illustrate that conventional fine-tuning methods can result in substantial activation displacement.<n>We introduce SEAT, a simple and principled fine-tuning approach that not only enables the model to effectively acquire new knowledge instances but also preserves its aligned ignorance awareness.
  arXiv  Detail & Related papers  (2025-06-17T10:33:23Z)
• 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)
• A Learning-Based Optimal Uncertainty Quantification Method and Its Application to Ballistic Impact Problems [1.713291434132985]
  This paper concerns the optimal (supremum and infimum) uncertainty bounds for systems where the input (or prior) measure is only partially/imperfectly known. We demonstrate the learning based framework on the uncertainty optimization problem. We show that the approach can be used to construct maps for the performance certificate and safety in engineering practice.
  arXiv  Detail & Related papers  (2022-12-28T14:30:53Z)
• 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)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)

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.