Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration
"可验证奖励" 相关文章
SimKO: Simple Pass@K Policy Optimization
SimKO: Simple Pass@K Policy Optimization
Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
拒绝“熵崩塌”和“熵爆炸”，这项研究让大模型学会“精确探索”，推理成绩飙升
On the optimization dynamics of RLVR: Gradient gap and step size thresholds
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
Quantile Advantage Estimation for Entropy-Safe Reasoning
Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning
攻克AI过度思考难题！美团新研究让通过“可验证”过程奖励激活LRM的高效推理
DCPO: Dynamic Clipping Policy Optimization
Writing-Zero: 打破 AI 写作天花板, 让 AI 写作更像"人"
Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning
CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment
