Exploration Hacking: Can LLMs Learn to Resist RL Training?

• URL: http://arxiv.org/abs/2604.28182v1
• Date: Thu, 30 Apr 2026 17:58:39 GMT
• Title: Exploration Hacking: Can LLMs Learn to Resist RL Training?
• Abstract summary: Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs)<n>In this paper we study this behavior, called exploration hacking.<n>First, we create model organisms of selective RL resistance by fine-tuning LLMs to follow specific underperformance strategies.<n>These models can successfully resist our RL-based capability elicitation in agentic biosecurity and AI R&D environments while maintaining performance on related tasks.
• Score: 10.715721930948504
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during training, which creates a potential failure mode: a model could strategically alter its exploration during training to influence the subsequent training outcome. In this paper we study this behavior, called exploration hacking. First, we create model organisms of selective RL resistance by fine-tuning LLMs to follow specific underperformance strategies; these models can successfully resist our RL-based capability elicitation in agentic biosecurity and AI R&D environments while maintaining performance on related tasks. We then use our model organisms to evaluate detection and mitigation strategies, including monitoring, weight noising, and SFT-based elicitation. Finally, we show that current frontier models can exhibit explicit reasoning about suppressing their exploration when provided with sufficient information about their training context, with higher rates when this information is acquired indirectly through the environment. Together, our results suggest exploration hacking is a possible failure mode of RL on sufficiently capable LLMs.

Related papers

• Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs [52.129885179495226]
  This study systematically explores the merging behavior of RL-trained large language models (LLMs) compared to those trained with traditional SFT.<n>We find that RL significantly reduces task conflicts and results in less performance degradation after merging.
  arXiv  Detail & Related papers  (2026-07-24T07:08:57Z)
• SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models [51.99912169291891]
  Reinforcement learning (RL) has emerged as a promising paradigm for training reasoning-oriented models.<n>We propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL)<n>Our findings suggest that alternating between RL and IRL offers an effective pathway toward extending the exploration capacity of reasoning-oriented large language models.
  arXiv  Detail & Related papers  (2026-04-18T13:49:47Z)
• A Survey of Reinforcement Learning for Large Reasoning Models [98.58081012669369]
  Review of recent advances in Reinforcement Learning for reasoning with Large Language Models.<n>Further scaling of RL for LRMs now faces challenges not only in computational resources but also in algorithm design, training data, and infrastructure.
  arXiv  Detail & Related papers  (2025-09-10T17:59:43Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [93.00629872970364]
  Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks.<n>We introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions.<n>We study whether difficult problems -- those yielding no RL signals and mixed-quality reasoning traces -- can still be effectively used for training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models [89.37819814048288]
  We introduce ProRL, a novel training methodology that incorporates KL divergence control, reference policy, and a diverse suite of tasks.<n>Our empirical analysis reveals that RL-trained models consistently outperform base resetting models across a wide range of pass@k evaluations.<n>These findings offer new insights into the conditions under which RL meaningfully expands reasoning boundaries in language models.
  arXiv  Detail & Related papers  (2025-05-30T17:59:01Z)
• Improving RL Exploration for LLM Reasoning through Retrospective Replay [45.00643118030677]
  We propose a novel algorithm named Retrospective Replay-based Reinforcement Learning (RRL), which introduces a dynamic replay mechanism throughout the training process.<n>RRL enables the model to revisit promising states identified in the early stages, thereby improving its efficiency and effectiveness in exploration.
  arXiv  Detail & Related papers  (2025-04-19T17:40:04Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework [1.5802986215292307]
  Language Model Guided reward Tuning (LMGT) is a novel, sample-efficient framework for Reinforcement Learning.<n>We show that LMGT adeptly balances exploration and exploitation, thereby guiding the agent's exploratory behavior.<n>Our results suggest that LMGT can substantially reduce the computational resources required during the RL training phase.
  arXiv  Detail & Related papers  (2024-09-07T07:40:43Z)
• Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization [0.0]
  We introduce a method to address goal misgeneralization in reinforcement learning (RL) Goal misgeneralization occurs when an agent retains its capabilities out-of-distribution yet pursues a proxy rather than the intended one. This study demonstrates how the Large Language Model can efficiently supervise RL agents.
  arXiv  Detail & Related papers  (2024-01-14T01:09:48Z)

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.