Cover Image

Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hao, Zhezheng, Wang, Hong, Liu, Haoyang, Luo, Jian, Yu, Jiarui, Dong, Hande, Lin, Qiang, Wang, Can, Chen, Jiawei
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ReCreate: Reasoning and Creating Domain Agents Driven by Experience
by: Hao, Zhezheng, et al.
Published: (2026)

LEPO: Latent Reasoning Policy Optimization for Large Language Models
by: Zhou, Yuyan, et al.
Published: (2026)

Scheduling Your LLM Reinforcement Learning with Reasoning Trees
by: Wang, Hong, et al.
Published: (2025)

Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
by: Hao, Zhezheng, et al.
Published: (2026)

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
by: Chen, Peter, et al.
Published: (2025)

Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective
by: Chen, Kun, et al.
Published: (2026)

GAPO: Robust Advantage Estimation for Real-World Code LLMs
by: Zhang, Jianqing, et al.
Published: (2025)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
by: Xu, Huimin, et al.
Published: (2026)

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
by: Liu, Zhanyu, et al.
Published: (2026)

Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR
by: Gu, Hengrui, et al.
Published: (2026)

Accelerating IC Thermal Simulation Data Generation via Block Krylov and Operator Action
by: Wang, Hong, et al.
Published: (2025)

SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning
by: Wang, Xuan, et al.
Published: (2026)

VL Norm: Rethink Loss Aggregation in RLVR
by: He, Zhiyuan, et al.
Published: (2025)

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
by: Miao, Rui, et al.
Published: (2024)

Rethinking Entropy Regularization in Large Reasoning Models
by: Jiang, Yuxian, et al.
Published: (2025)

UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
by: Li, Jinke, et al.
Published: (2025)

SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training
by: Wen, Xin-Cheng, et al.
Published: (2026)

DSO: Dual-Scale Neural Operators for Stable Long-term Fluid Dynamics Forecasting
by: Dong, Huanshuo, et al.
Published: (2026)

Rethinking GSPO: The Perplexity-Entropy Equivalence
by: Liu, Chi
Published: (2025)

Spurious Rewards: Rethinking Training Signals in RLVR
by: Shao, Rulin, et al.
Published: (2025)

Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective
by: Chen, Haoyang, et al.
Published: (2025)

Structural Entropy Guided Probabilistic Coding
by: Huang, Xiang, et al.
Published: (2024)

Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
by: Wang, Weixin, et al.
Published: (2025)

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
by: Huang, Wei-Ping, et al.
Published: (2026)

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
by: Agarwal, Shivam, et al.
Published: (2025)

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
by: Yang, Weiqin, et al.
Published: (2024)

EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy
by: Huang, Yihong, et al.
Published: (2024)

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
by: Zhan, Guojian, et al.
Published: (2025)

Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
by: Guan, Yunchuan, et al.
Published: (2025)

Maximum Entropy Reinforcement Learning with Diffusion Policy
by: Dong, Xiaoyi, et al.
Published: (2025)

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
by: Li, Zeping, et al.
Published: (2026)

Enter the Void - Planning to Seek Entropy When Reward is Scarce
by: Sundar, Ashish, et al.
Published: (2025)

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
by: Jia, Weitao, et al.
Published: (2025)

Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective
by: Xu, Zhijian, et al.
Published: (2024)

NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems
by: Yu, Xiaowei, et al.
Published: (2023)

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding
by: Li, Jipeng, et al.
Published: (2025)

Merino: Entropy-driven Design for Generative Language Models on IoT Devices
by: Zhao, Youpeng, et al.
Published: (2024)

Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration
by: Wei, Longxuan, et al.
Published: (2026)

Improving Entropy-Based Test-Time Adaptation from a Clustering View
by: Lin, Guoliang, et al.
Published: (2023)

Probing RLVR training instability through the lens of objective-level hacking
by: Dong, Yiming, et al.
Published: (2026)