Example for training on SWE (agentic software-engineering) tasks?

[dipta007]

Checklist / 检查清单

• I have searched existing issues, and this is a new question or discussion topic. / 我已经搜索过现有的 issues，确认这是一个新的问题与讨论。

Question Description / 问题描述

Is there an example/recipe for grpo training on multi-turn SWE-style tasks (SWE-bench / SWE-Gym)?

Looking for:

• Multi-turn agentic rollouts with tool calls (shell, file edits, tests)
• How environment/reward is wired (e.g. tests-passing as reward)
• Setup for long trajectories / large context
• Setup for how docker/podman is handled efficiently during rollout

If nothing SWE-specific exists, a pointer to the closest multi-turn example to adapt would help. Happy to contribute one back.

Thanks!

[hjh0119]

We are planning to implement a similar example — contributions would be greatly appreciated

[dipta007]

We are planning to implement a similar example — contributions would be greatly appreciated

is it supported yet? or on the implementation stage?