Not All Entropy Is Equal: Reward-Conditioned Entropy Allocation in Reinforcement Learning with Verifiable Rewards
cs.LG, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control
- Solving math word problems with process- and outcome-based feedback
- Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
- Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
- SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning