pivotrl-efficient-agentic-training

【效率与协作】Achieve high-accuracy agentic post-training with 4x fewer rollout turns and 5.5x less wall-clock time than end-to-end RL. Identify informative intermediate turns via pivot filtering and use verifier-based functional rewards for precise credit assignment.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准