Reading - 分类 - vllbc02's blogs

Reading

2026

RSI：Recursive Self-Improvement 分类图谱 08-31

GRPO训练排查：策略坍塌 vs 训练崩溃 08-31

MOPD：Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training 07-29

Review：自进化Agent的RL Memory与Skill方法批判 07-23

2025

ReasoningBank：Scaling Agent Self-Evolving with Reasoning Memor 10-17

GVPO：Group Variance Policy Optimization for Large Language Model Post-Training 10-17

Skywork-R1V3 Technical Report 10-13

ToolRM：Outcome Reward Models for Tool-Calling Large Language Models 09-23

Tool-R1：Sample-Efficient Reinforcement Learning for Agentic Tool Use 09-23

Single-stream Policy Optimization 09-23

1
2
3
14