Agentic RL

This section covers agentic reinforcement learning with RLinf, including reasoning RL training, multi-agent systems, and tool integration.

For end-to-end examples, see the Agentic Examples gallery, which includes reasoning, coding online RL, Search-R1, rStar2, and WideSeek-R1 workflows.

Note

This section is a stub. Agentic RL tutorial content is being developed. For now, see the Agentic Examples gallery for end-to-end workflows including reasoning, coding online RL, Search-R1, rStar2, and WideSeek-R1.