Targeted Exploration via Unified Entropy Control for Reinforcement Learning

• URL: http://arxiv.org/abs/2604.14646v2
• Date: Fri, 17 Apr 2026 11:31:53 GMT
• Title: Targeted Exploration via Unified Entropy Control for Reinforcement Learning
• Abstract summary: We propose Unified Entropy Control for Reinforcement Learning (UEC-RL), a framework that provides targeted mechanisms for exploration and stabilization.<n>UEC-RL activates more exploration on difficult prompts to search for potential and valuable reasoning trajectories.<n>In parallel, a stabilizer prevents entropy from growing uncontrollably, thereby keeping training stable as the model consolidates reliable behaviors.
• Score: 9.478028848430572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO) consistently suffers from entropy collapse, causing the policy to converge prematurely and lose diversity. Existing exploration methods introduce additional bias or variance during exploration, making it difficult to maintain optimization stability. We propose Unified Entropy Control for Reinforcement Learning (UEC-RL), a framework that provides targeted mechanisms for exploration and stabilization. UEC-RL activates more exploration on difficult prompts to search for potential and valuable reasoning trajectories. In parallel, a stabilizer prevents entropy from growing uncontrollably, thereby keeping training stable as the model consolidates reliable behaviors. Together, these components expand the search space when needed while maintaining robust optimization throughout training. Experiments on both LLM and VLM reasoning tasks show consistent gains over RL baselines on both Pass@1 and Pass@$k$. On Geometry3K, UEC-RL achieves a 37.9\% relative improvement over GRPO, indicating that it sustains effective exploration without compromising convergence and underscoring UEC-RL as a key for scaling RL-based reasoning in large models. Our code is available at https://github.com/597358816/UEC-RL.

Related papers

• ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples [65.74946647574696]
  Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs)<n>In this work, we investigate a critical source of this instability: over-optimization.<n>We propose ARMOR, a framework that shifts the paradigm from passive penalty to active sample stabilization.
  arXiv  Detail & Related papers  (2026-07-11T21:22:46Z)
• Survival Reinforcement Learning: Toward Scalable Self-Supervised RL [10.768601219140153]
  Self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities.<n>We introduce Survival Reinforcement Learning (SRL), an online classification-based alternative that extends the survival value learning framework.
  arXiv  Detail & Related papers  (2026-05-29T13:05:08Z)
• 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)
• Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning [26.103428215400697]
  We find that simple Sequential Fine-Tuning (Seq. FT) with low-rank adaptation (LoRA) is remarkably strong.<n>Our results position Sequential Fine-Tuning as a powerful method for continual RL with Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2026-03-12T08:22:39Z)
• Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning [88.42566960813438]
  CalibRL is a hybrid-policy RLVR framework that supports controllable exploration with expert guidance.<n>CalibRL increases policy entropy in a guided manner and clarifies the target distribution.<n>Experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements.
  arXiv  Detail & Related papers  (2026-02-22T07:23:36Z)
• The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling [39.65138471548881]
  Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs)<n>We propose SESA, a novel SEquential SAmpling framework that generates diverse solution sketches sequentially before expanding them into full reasoning paths.<n>Our experiments on a synthetic task show that sequential sampling consistently outperforms traditional RL methods in terms of path diversity and recovery from collapse.
  arXiv  Detail & Related papers  (2025-10-17T10:15:11Z)
• Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning [55.59724323303857]
  We propose a framework that balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.<n>Experiments on multiple mathematical reasoning benchmarks show that AER consistently outperforms baselines, improving both reasoning accuracy and exploration capability.
  arXiv  Detail & Related papers  (2025-10-13T03:10:26Z)
• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [111.1749164063616]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training [121.5858973157225]
  We investigate the effects of prolonged reinforcement learning on a small language model across a diverse set of reasoning domains.<n>We introduce controlled KL regularization, clipping ratio, and periodic reference policy resets as critical components for unlocking long-term performance gains.<n>Our model achieves significant improvements over strong baselines, including +14.7% on math, +13.9% on coding, and +54.8% on logic puzzle tasks.
  arXiv  Detail & Related papers  (2025-07-16T17:59:24Z)
• 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)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.96848846966087]
  Training large language models (LLMs) as interactive agents presents unique challenges.<n>While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored.<n>We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)

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.