Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization
cs.AI, cs.LG
Submitted: 2026-09-30
Updated: 2026-10-03
Code: https://github.com/LiveCodeBench/LiveCodeBench
Terminology
Sources
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- Reasoning with Exploration: An Entropy Perspective
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction
- Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
- Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
- FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
- ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning
- GRPO-$\lambda$: Credit Assignment improves LLM Reasoning
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
- Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems