verltool-agentic-rl-tool-use

【设计与创意】Train agents to leverage external tools across domains using VerlTool's unified RL framework. Coordinate code execution, search, SQL queries, and vision utilities in multi-turn interactions without domain-specific redesign. 2× faster asynchronous rollouts on mathematical reasoning, knowledge QA, and software engineering tasks.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准