practitioner-guide-multi-turn-agentic-rl

【效率与协作】Train LLM agents via multi-turn reinforcement learning by systematically optimizing environment complexity, reward signals, and policy initialization. Use curriculum learning, dense verified rewards, and domain-specific SFT for reliable agent convergence across TextWorld, ALFWorld, and SWE-Gym benchmarks.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准