Group Entropy-Controlled Policy Optimization

• URL: http://arxiv.org/abs/2607.16850v1
• Date: Sat, 18 Jul 2026 15:13:33 GMT
• Title: Group Entropy-Controlled Policy Optimization
• Abstract summary: Group Entropy-Controlled Policy Optimization (GEPO) is a lightweight extension to GRPO that uses group entropy to perform entropy-conditioned asymmetric advantage shaping.<n>GEPO attenuates positive advantages in low-entropy groups to reduce over-exploitation, and negative advantages in high-entropy groups to preserve exploration.
• Score: 38.44352203898131
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm is often conducted on mixtures of heterogeneous tasks, which induce distinct entropy regimes under the same policy, making global or token-level entropy regulation insufficient to corresponding heterogeneous needs of exploration. This heterogeneity further makes GRPO-style normalized advantages induce an entropy-dependent bias, making advantage signals across prompt groups statistically non-comparable. To address this issue, we propose Group Entropy-Controlled Policy Optimization (GEPO), a lightweight extension to GRPO that uses group entropy, estimated from existing grouped samples to perform entropy-conditioned asymmetric advantage shaping. GEPO attenuates positive advantages in low-entropy groups to reduce over-exploitation, and negative advantages in high-entropy groups to preserve exploration, with adaptive thresholds derived from historical entropy statistics. Extensive experiments on two base models across thirteen benchmarks spanning mathematics, physics, science, code generation, and instruction following show that GEPO consistently outperforms GRPO and recent entropy-controlled methods, delivering balanced cross-task improvements while preserving task-specific exploration levels throughout training.

Related papers

• STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability [78.63876433996107]
  We conduct a first-order gradient analysis of token-level entropy dynamics under GRPO.<n>We propose STARE, which identifies entropy-critical token subsets via batch-internal surprisal quantiles.<n>On AIME24 and AIME25, STARE outperforms DAPO and other competitive baselines by 4%-8% in average accuracy.
  arXiv  Detail & Related papers  (2026-06-17T16:13:42Z)
• Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control [77.8471519867791]
  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.
  arXiv  Detail & Related papers  (2026-05-12T08:47:05Z)
• EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance [3.463914032107119]
  We propose Entropy-Progress Aligned GRPO, a framework that mines the model's intrinsic information flow for dense, self-supervised guidance.<n>EP- GRPO achieves superior accuracy and efficiency compared to GRPO and its variants.
  arXiv  Detail & Related papers  (2026-05-06T14:21:54Z)
• 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)
• From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation [53.759125791348396]
  Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation.<n>We present a systematic entropy-based analysis that yields three key insights.<n>We propose Entropy-Guided Group Relative Policy Optimization (EG-GRPO), a fine-tuning strategy that reallocates optimization budget by uncertainty.
  arXiv  Detail & Related papers  (2026-03-12T12:49:26Z)
• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models [54.56296715999545]
  Reinforcement learning from human feedback shows promise for aligning diffusion and flow models.<n>Policy optimization methods such as GRPO suffer from inefficient and static sampling strategies.<n>We propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy.
  arXiv  Detail & Related papers  (2026-02-06T16:09:50Z)
• ESPO: Entropy Importance Sampling Policy Optimization [7.2000276975120014]
  Entropy Importance Sampling Policy Optimization reconciles fine-grained control with training stability.<n> ESPO decomposes sequences into groups based on predictive entropy.<n>Experiments on mathematical reasoning benchmarks demonstrate that ESPO achieves convergence and state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-29T14:09:38Z)
• 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)

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.