Tags

122 个页面

Reading

GEPA：REFLECTIVE PROMPT EVOLUTION CAN OUTPERFORM REINFORCEMENT LEARNING

SIMURA：Towards General Goal-Oriented Agent via Simulative Reasoning Architecture with LLM-Based World Model

LAPO：INTERNALIZING REASONING EFFICIENCY VIA LENGTH-ADAPTIVE POLICY OPTIMIZATION

Good Learners Think Their Thinking：Generative PRM Makes Large Reasoning Model More Efficient Math Learne

ProRL：Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

RLVMR：Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents

Thinking vs. Doing：Agents that Reason by Scaling Test-Time Interaction

UloRL：An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models’ Reasoning Abilities

AGENTIC REINFORCED POLICY OPTIMIZATION

VAPO：Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks