Cover Image

Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Kun, Shi, Peng, Liu, Fanfan, Qiu, Haibo, Zeng, Zhixiong, Yang, Siqi, Mao, Wenji
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
by: Chen, Kun, et al.
Published: (2025)

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR
by: Liu, Fanfan, et al.
Published: (2026)

Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
by: Hao, Zhezheng, et al.
Published: (2025)

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

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

Generalization of RLVR Using Causal Reasoning as a Testbed
by: Lu, Brian, et al.
Published: (2025)

APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
by: Chen, Kun, et al.
Published: (2026)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
by: Ju, Yiming, et al.
Published: (2024)

DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
by: Wang, Minzheng, et al.
Published: (2024)

MobileDreamer: Generative Sketch World Model for GUI Agent
by: Cao, Yilin, et al.
Published: (2026)

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
by: Khalifa, Muhammad, et al.
Published: (2026)

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
by: Chen, Zhipeng, et al.
Published: (2026)

RLPR: Extrapolating RLVR to General Domains without Verifiers
by: Yu, Tianyu, et al.
Published: (2025)

GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control
by: Simoni, Marco, et al.
Published: (2025)

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
by: Su, Zhenpeng, et al.
Published: (2025)

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
by: Zhong, Yufeng, et al.
Published: (2025)

The Invisible Leash: Why RLVR May or May Not Escape Its Origin
by: Wu, Fang, et al.
Published: (2025)

CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
by: Cui, Sijia, et al.
Published: (2026)

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
by: Lee, Chanuk, 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)

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
by: Duo, Jiangshan, et al.
Published: (2026)

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
by: Yang, Junyao, et al.
Published: (2026)

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
by: Xie, Pei-Xi, et al.
Published: (2026)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
by: Yang, Ziyu, et al.
Published: (2026)

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
by: Meng, Haoming, et al.
Published: (2026)

Exploring Lightweight Large Language Models for Court View Generation
by: Hou, Zhitian, et al.
Published: (2026)

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

CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
by: Yuan, Zirui, et al.
Published: (2025)

A State-of-the-Art SQL Reasoning Model using RLVR
by: Ali, Alnur, et al.
Published: (2025)

PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
by: Oh, Jihwan, et al.
Published: (2026)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
by: Miao, Yuchun, et al.
Published: (2026)

PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR
by: Burgess, James, et al.
Published: (2026)

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR
by: Kim, Soeun, et al.
Published: (2026)

Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoning
by: Lan, Xiaohan, et al.
Published: (2025)

UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions
by: Han, Wenkang, et al.
Published: (2025)

Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs
by: Ren, Yanwei, et al.
Published: (2025)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
by: Li, Changming, et al.
Published: (2026)

Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
by: Qiu, Haibo, et al.
Published: (2025)

Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR
by: Zhuang, Haomin, et al.
Published: (2025)

Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
by: Ren, Yanwei, et al.
Published: (2026)