In-Context Reinforcement Learning under Non-Stationarity: A Survey

• URL: http://arxiv.org/abs/2607.11906v1
• Date: Wed, 01 Jul 2026 12:55:17 GMT
• Title: In-Context Reinforcement Learning under Non-Stationarity: A Survey
• Abstract summary: In-context reinforcement learning is the ability of a pretrained or fine-tuned decision model to infer latent task rules.<n>In changing environments, accumulated context is not merely more evidence about a fixed task.<n>We survey non-stationary ICRL as the problem of adapting through context while deployed policy parameters remain fixed.
• Score: 7.522032549330931
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The development of decision-pretrained transformers, algorithm distillation, long-context meta-RL, and retrieval-augmented agents has renewed interest in in-context reinforcement learning (ICRL): the ability of a pretrained or fine-tuned decision model to infer latent task rules and improve future behavior from interaction context, without test-time parameter updates. This line of work asks when trial-and-error evidence, rewards, transitions, demonstrations, feedback, or retrieved experience can make learning-like computation happen inside the context window. However, existing surveys of ICRL mainly organize the field around pretraining objectives, architectures, context formats, evaluation protocols, and theoretical mechanisms, while the non-stationary setting remains comparatively underexamined. In changing environments, accumulated context is not merely more evidence about a fixed task: the reward specification, transition kernel, observation channel, action interface, constraint model, or demonstration and memory distribution can fall out of alignment with the current regime. Previously useful context can therefore become stale, misleading, or useful again when an old regime returns. We survey non-stationary ICRL as the problem of adapting through context while deployed policy parameters remain fixed: the policy must infer both the current decision rule and which parts of its accumulated evidence still support that rule. We define non-stationary ICRL, relate it to meta-RL, decision sequence modeling, retrieval-augmented RL, value- and model-aware ICRL, and reward-feedback agents, and organize the literature along three questions: what changes, how the change unfolds, and how observable the change is to the agent.

Related papers

• SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning [38.54413500261524]
  Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions.<n>We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills.
  arXiv  Detail & Related papers  (2026-07-16T09:57:18Z)
• The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning [65.67266333751569]
  Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.<n>We propose a self-supervised reinforcement learning framework that targets the internal reasoning process without requiring ground-truth annotations.<n>We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.
  arXiv  Detail & Related papers  (2026-06-10T10:50:06Z)
• OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents [74.20327254615854]
  Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks.<n>Existing inference-time adaptation methods for LLM agents mainly rely on prompting or retrieval.<n>We propose OLIVIA, an inference-time action adaptation framework for ReAct-style agents.
  arXiv  Detail & Related papers  (2026-05-11T19:28:20Z)
• Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning [79.88942231770629]
  Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs)<n>We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR)<n>We synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement.
  arXiv  Detail & Related papers  (2026-04-08T00:53:29Z)
• Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers [55.33468902405567]
  We propose a new learning paradigm, In-Context Preference-based Reinforcement Learning (ICPRL), in which both pretraining and deployment rely solely on preference feedback.<n>ICPRL enables strong in-context generalization to unseen tasks, achieving performance comparable to ICRL methods trained with full reward supervision.
  arXiv  Detail & Related papers  (2026-02-09T03:42:16Z)
• Towards Monotonic Improvement in In-Context Reinforcement Learning [18.67894044930047]
  In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks.<n>Recent approaches train large sequence models on monotonic policy improvement data from online RL, aiming to a continue improved testing time performance.<n>We propose two methods for estimating Context Value at both training and testing time.
  arXiv  Detail & Related papers  (2025-09-27T09:42:19Z)
• Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization [6.408943565801689]
  Capturing latent variations ("contexts") is key to deploying reinforcement-learning (RL) agents beyond their training regime.<n>We recast context-based RL as a dual inference-control problem and formally characterize two properties and their hierarchy.<n>We derive a contextual evidence lower bound(ELBO)-style objective that cleanly separates representation learning from policy learning.
  arXiv  Detail & Related papers  (2025-07-25T17:08:16Z)
• Scalable In-Context Q-Learning [68.9917436397079]
  We propose textbfScalable textbfIn-textbfContext textbfQ-textbfLearning (textbfSICQL) to steer in-context reinforcement learning.<n>textbfSICQL harnesses dynamic programming and world modeling to steer ICRL toward efficient reward and task generalization.
  arXiv  Detail & Related papers  (2025-06-02T04:21:56Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• Context Shift Reduction for Offline Meta-Reinforcement Learning [28.616141112916374]
  The context shift problem arises due to the distribution discrepancy between the contexts used for training and testing. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. We propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets.
  arXiv  Detail & Related papers  (2023-11-07T03:50:01Z)
• Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization [29.61829620717385]
  Key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime. DaCoRL learns a context-conditioned policy using progressive contextualization. DaCoRL features consistent superiority over existing methods in terms of the stability, overall performance and generalization ability.
  arXiv  Detail & Related papers  (2022-09-01T10:26:58Z)
• Contextualize Me -- The Case for Context in Reinforcement Learning [49.794253971446416]
  Contextual Reinforcement Learning (cRL) provides a framework to model such changes in a principled manner. We show how cRL contributes to improving zero-shot generalization in RL through meaningful benchmarks and structured reasoning about generalization tasks.
  arXiv  Detail & Related papers  (2022-02-09T15:01:59Z)

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.