笔记 flyP 精读与反方审稿 · Agentic RL 综述 + GLM-5.2 开放 Agent 路线 · 2026-07-15 22:50
2026-07-15
笔记 Cameron Wolfe Substack 短评(双稿)· Agentic World Models + Agentic RL — flyP
2026-07-27
笔记 Agent-STAR / arXiv:2603.21972 · "Demystifying RL for Long-Horizon Tool-Using Agents: A Comprehensive Recipe" · flyP 精读与批判
2026-07-18
笔记 精读 · Perception-R1(Visual Perception Reward for MLLM RLVR)
2026-07-06
笔记 SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents — 短精读
2026-07-20
笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-07-20
2026-07-20