Can In-Context Learning Support Intrinsic Curiosity?

• URL: http://arxiv.org/abs/2606.19476v1
• Date: Wed, 17 Jun 2026 18:11:06 GMT
• Title: Can In-Context Learning Support Intrinsic Curiosity?
• Abstract summary: We investigate whether the emergent in-context learning capabilities of sequence models can eliminate this bottleneck.<n>Specifically, we evaluate whether an exploration policy can be trained to maximize learning progress.<n>We prove a positive result for a broad subclass of non-temporal settings.
• Score: 25.43664318918942
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated data selection, or "intrinsic curiosity", remains a significant challenge. Classic approaches incentivize exploration by rewarding an agent based on its "learning progress", which measures how much a newly acquired observation improves a world model's predictive ability. However, evaluating these rewards traditionally requires expensive inner loops of gradient descent updates within each trajectory, rendering them computationally impractical at scale. In this work, we investigate whether the emergent in-context learning (ICL) capabilities of sequence models can eliminate this bottleneck by serving as immediate, update-free world models. Specifically, we evaluate whether an exploration policy can be trained to maximize learning progress, using solely the prediction errors and counterfactual context manipulations of an in-context learner. We first prove that in general Markov decision processes, this is in fact impossible in an unbiased way: the resulting intrinsic rewards either suffer from nuisance terms that bias their estimation of true learning progress, or they cannot be implemented using an in-context learner's prediction errors. Conversely, we prove a positive result for a broad subclass of non-temporal settings, encompassing active learning and Bayesian Experimental Design: here, ICL-derived rewards successfully bound and asymptotically converge to the true learning progress. We corroborate our theory with controlled experiments across continuous and symbolic environments, demonstrating that our ICL-driven framework successfully trains curious data-collection policies that explore optimally.

Related papers

• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models [31.865100130203317]
  We propose a compatibility prediction Latent World Model (LWM) for robot navigation.<n>Our key insight is that spatial proximity correlates with latent feature similarity, enabling action consequences to be evaluated directly in latent space.<n>Our approach significantly outperforms prior world model and imitation learning methods in prediction accuracy, policy learning, and real-world navigation performance.
  arXiv  Detail & Related papers  (2026-08-23T11:58:42Z)
• How Far Can Unsupervised RLVR Scale LLM Training? [57.44753418846446]
  Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck.<n>Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear.<n>We classify URLVR methods into intrinsic versus external based on reward sources, then establish a unified theoretical framework.
  arXiv  Detail & Related papers  (2026-03-09T17:38:11Z)
• Learning-Augmented Moment Estimation on Time-Decay Models [55.06256430461023]
  We use an oracle for the heavy-hitters of datasets to give learning-augmented algorithms for a number of fundamental problems.<n>We complement our theoretical results with a number of empirical evaluations that demonstrate the practical efficiency of our algorithms on real and synthetic datasets.
  arXiv  Detail & Related papers  (2026-03-03T00:42:34Z)
• Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement [19.883973457999282]
  Imitation Learning from Observation (IfO) offers a powerful way to learn behaviors at large-scale.<n>This paper investigates idealized scenarios with mostly bimodal-quality data distributions and introduces a method to learn from such data.<n>Our method adapts RL-based imitation learning to action-free demonstrations, using a value function to transfer information between expert and non-expert data.
  arXiv  Detail & Related papers  (2025-07-09T09:55:23Z)
• Continuous Visual Autoregressive Generation via Score Maximization [69.67438563485887]
  We introduce a Continuous VAR framework that enables direct visual autoregressive generation without vector quantization.<n>Within this framework, all we need is to select a strictly proper score and set it as the training objective to optimize.
  arXiv  Detail & Related papers  (2025-05-12T17:58:14Z)
• An Information Theoretic Approach to Machine Unlearning [43.423418819707784]
  To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important.<n>In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data given only a trained model and the data to be forgotten.<n>We derive a simple but principled zero-shot unlearning method based on the geometry of the model.
  arXiv  Detail & Related papers  (2024-02-02T13:33:30Z)
• Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes [72.75421975804132]
  Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting. We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem. Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
  arXiv  Detail & Related papers  (2023-09-11T14:16:37Z)
• Reinforcement Learning from Passive Data via Latent Intentions [86.4969514480008]
  We show that passive data can still be used to learn features that accelerate downstream RL. Our approach learns from passive data by modeling intentions. Our experiments demonstrate the ability to learn from many forms of passive data, including cross-embodiment video data and YouTube videos.
  arXiv  Detail & Related papers  (2023-04-10T17:59:05Z)
• A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning [8.188575923130662]
  We argue that notable lessons from open set recognition, the identification of statistically deviating data outside of the observed dataset, and the adjacent field of active learning, are frequently overlooked in the deep learning era. Our results show that this not only benefits each individual paradigm, but highlights the natural synergies in a common framework.
  arXiv  Detail & Related papers  (2020-09-03T16:56:36Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.