mlsanityData to 14 Oct 2026

Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints

arXiv 2510.08549 ↗First posted 9 Oct 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonstrates broad effectiveness across different domains: 1) for large language models(LLMs), boosting the AIME 2025 score for Qwen2.5-Math-7B by 37.4%; 2) for continuous control reinforcement learning agents, improving performance by more than 30% over strong baselines such as SAC on the challenging HumanoidBench; 3) for image classification, enhancing ImageNet top-1 accuracy by 0.69% for ResNet-50. These gains are achieved with a computational overhead of less than 7%. Our work validates output activation as a powerful tool for entropy control, opening a new direction for designing simpler and more robust algorithms.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 45 of its 60 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

45 of 60 references.

References · 45

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2016Layer Normalizationcited by 5,669
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  10. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  11. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  12. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
33 more
  1. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  4. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  5. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  6. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  7. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  8. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  9. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  10. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  11. 2018DeepMind Control Suitecited by 956
  12. 2025Group Sequence Policy Optimizationcited by 835
  13. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 669
  14. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 559
  15. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wildcited by 511
  16. 2025Process Reinforcement through Implicit Rewardscited by 504
  17. 2025The Entropy Mechanism of Reinforcement Learning for Reasoning Language Modelscited by 485
  18. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 461
  19. 2025Demystifying Long Chain-of-Thought Reasoning in LLMscited by 326
  20. 2025Reasoning with Exploration: An Entropy Perspectivecited by 281
  21. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 211
  22. 2017Bridging the Gap Between Value and Policy Based Reinforcement Learningcited by 182
  23. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 112
  24. 2024Common 7B Language Models Already Possess Strong Math Capabilitiescited by 109
  25. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 97
  26. 2025Efficient Online Reinforcement Learning for Diffusion Policycited by 71
  27. 2025DIME:Diffusion-Based Maximum Entropy Reinforcement Learningcited by 58
  28. 2025FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Controlcited by 44
  29. 2024Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flowcited by 26
  30. 2025HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulationcited by 14
  31. 2024Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RLcited by 10
  32. 2025A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Controlcited by 9
  33. 2024Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026MemPO: Self-Memory Policy Optimization for Long-Horizon Agentscited by 12
  2. 2025MOA: Multi-Objective Alignment for Role-Playing Agentscited by 5
  3. 2026QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuningcited by 3
  4. 2026FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Controlcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026A Comparative Theoretical Analysis of Entropy Control Methods in Reinforcement Learning
  2. 2025EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
  3. 2026Entropy-Preserving Reinforcement Learning
  4. 2025The Role of Entropy in Visual Grounding: Analysis and Optimization
  5. 2026On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
  6. 2024Controlling Large Language Model Agents with Entropic Activation Steering
  7. 2026Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control
  8. 2026Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective