Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control

• URL: http://arxiv.org/abs/2605.11775v2
• Date: Thu, 14 May 2026 14:02:12 GMT
• Title: Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
• Abstract summary: Empirically, we show that entropy polarity reliably predicts entropy changes.<n>We propose Polarity-Aware Policy Optimization (PAPO), which preserves both polarity branches and implements entropy control through advantage reweighting.
• Score: 77.8471519867791
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existing entropy-aware methods mainly regulate entropy through global objectives, while the token-level mechanism by which sampled policy updates reshape policy entropy remains underexplored. In this work, we develop a theoretical framework of entropy mechanics in RLVR. Our analysis yields a first-order approximation of the entropy change, giving rise to entropy polarity, a signed token-level quantity that predicts how much a sampled update expands or contracts entropy. This analysis further reveals a structural asymmetry: reinforcing frequent high-probability tokens triggers contraction tendencies, whereas expansive tendencies typically require lower-probability samples or stronger distributional correction. Empirically, we show that entropy polarity reliably predicts entropy changes, and that positive and negative polarity branches play complementary roles in preserving exploration while strengthening exploitation. Building on these insights, we propose Polarity-Aware Policy Optimization (PAPO), which preserves both polarity branches and implements entropy control through advantage reweighting. With the empirical entropy trajectory as an online phase signal, PAPO adaptively reallocates optimization pressure between entropy-expanding and entropy-contracting updates. Experiments on mathematical reasoning and agentic benchmarks show that PAPO consistently outperforms competitive baselines, while delivering superior training efficiency and substantial reward improvements.

Related papers

• Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization [53.75029276020459]
  We propose an adaptive entropy flow balancing mechanism that rescales entropy-increasing and entropy-decreasing updates according to their contributions to entropy change.<n>Experiments on six mathematical reasoning benchmarks demonstrate that OPEFO improves training and final performance.
  arXiv  Detail & Related papers  (2026-05-12T04:08:17Z)
• Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy Modulation [33.15281300187744]
  Reinforcement learning with rewards has advanced the reasoning capabilities of large language models.<n>It faces a limitation termed textitrestricted exploration, where the policy rapidly converges to a narrow set of solutions.<n>We propose textbfAsymGRPO, an exploratory framework that explicitly decouples the modulation of positive and negative rollouts.
  arXiv  Detail & Related papers  (2026-04-06T17:42:38Z)
• On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models [54.61810451777578]
  Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models.<n>Recent studies increasingly focus on monitoring and adjusting entropy to better balance exploration and exploitation in reinforcement fine-tuning.
  arXiv  Detail & Related papers  (2026-02-03T11:14:58Z)
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models [54.96908589622163]
  We investigate the entropy dynamics of large language models trained withReinforcement learning with verifiable rewards (RLVR)<n>Our findings reveal that the number of off-policy updates, the diversity of training data, and the clipping thresholds in the optimization objective are critical factors influencing the entropy of LLMs trained with RLVR.
  arXiv  Detail & Related papers  (2025-11-08T12:50:41Z)
• Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL [56.085103402298905]
  We propose a trajectory entropy-constrained reinforcement learning (TECRL) framework to address these two challenges.<n>Within this framework, we first separately learn two Q-functions, one associated with reward and the other with entropy, ensuring clean and stable value targets unaffected by temperature updates.<n>We develop a practical off-policy algorithm, DSAC-E, by extending the state-of-the-art distributional soft actor-critic with three refinements.
  arXiv  Detail & Related papers  (2025-10-25T09:17:47Z)
• Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective [11.65148836911294]
  entropy collapse is a rapid loss of policy diversity, stemming from the exploration-exploitation imbalance and leading to a lack of generalization.<n>Recent entropy-intervention methods aim to prevent coloredtextentropy collapse, yet their underlying mechanisms remain unclear.<n>We introduce an entropy-change-aware reweighting scheme, namely Stabilizing Token-level Entropy-changE via Reweighting (STEER)
  arXiv  Detail & Related papers  (2025-10-11T10:17:38Z)
• Arbitrary Entropy Policy Optimization: Entropy Is Controllable in Reinforcement Fine-tuning [36.00460460149206]
  We propose Arbitrary Entropy Policy Optimization (AEPO), which eliminates entropy collapse by replacing entropy bonuses with REINFORCE policy gradient on temperature-adjusted distributions.<n>AEPO integrates three key designs: policy gradient as regularization, distribution as regularization, and REINFORCE as regularization, enabling precise entropy control without distorting optimization.
  arXiv  Detail & Related papers  (2025-10-09T12:24:08Z)
• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models [99.98293908799731]
  This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy.<n>In practice, we establish a transformation equation R=-a*eH+b between entropy H and downstream performance R.<n>We propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively.
  arXiv  Detail & Related papers  (2025-05-28T17:38:45Z)

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.