Interest in a verl-based training pipeline alongside SkyRL?

未关闭
#80 5 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
20/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
python

调研方向

The issue describes a proposed verl training path but names no repository files or tests to start from. First read the existing SkyRL pipeline and ask maintainers whether they want this work and which scope they prefer; the thread has not recorded a decision. Done means an agreed scope and an accepted implementation, with the synchronous-trainer limitation documented.

由索引模型根据 Issue 内容生成。

描述

Summary

We completed a full port of the CodeScout agentic RL training pipeline (issue → file localization) from SkyRL to verl (v0.9.1), preserving task, reward, and evaluation semantics. Before investing in a large PR, we'd like to check whether you're interested in accepting a verl-based training path alongside the current SkyRL pipeline.

What the port includes

  • A verl agent-loop adapter for the CodeScout multi-turn rollout: terminal search tools, localization_finish, prompt/tool-schema plumbing, and workspace isolation, wired into verl's multi-turn rollout and training loop.
  • Reward bridging to multilevel_localization_f1_reward (file/module/entity F1, sum over 0–3), with the private-label boundary kept out of the actor's visible inputs.
  • ~3,300 lines of tests, including:
    • loss/gradient/advantage numerical alignment against SkyRL fixed tensors (10 layered checks),
    • a 15-case reward contract suite,
    • adapter unit + CLI end-to-end tests.
  • Data prep / training / evaluation entry scripts and environment setup scripts.

Reproduction evidence

All numbers below are on the localization versions of SWE-bench Verified (500 tasks) / Lite / Pro, sum-F1 macro average on a 0–3 scale, starting from Qwen/Qwen3-4B-Instruct-2507 with GRPO advantage + GSPO policy loss, 200 updates on 8×H100.

  • Under the official 15-turn protocol with official ground truth, our verl-trained reproduction reaches or slightly exceeds the released official CodeScout-4B reference model under the same pipeline (same-pipeline comparison against the released model, not the paper tables):
    • Verified: 0.815 / 0.783 (two rollout seeds) vs. official 0.730
    • Lite: 0.636 / 0.552 vs. official 0.497
    • Pro: 0.084 / 0.078 vs. official 0.070
  • Under our frozen internal protocol, the untrained base scores 0.262 → 0.762 / 0.733 after training (mean paired difference +0.486, task-paired bootstrap 95% CI [0.407, 0.565]).

Known deviation from the original pipeline

Our current trainer is synchronous (staleness = 0), whereas the original SkyRL pipeline is fully async. We treat this as a documented limitation rather than a silent change; migrating to verl's async trainer would require redoing a matched baseline.

Questions for maintainers

  1. Would you be open to a PR adding a verl training path (e.g., under an opt-in directory or flag, keeping SkyRL as the default)?
  2. If yes, what scope would you prefer?
    • (a) adapter + tests only,
    • (b) adapter + tests + entry scripts + user-facing docs,
    • (c) something narrower — we're happy to split into smaller incremental PRs.
  3. Any requirements we should know about (license headers, supported verl versions, CI)?

Happy to provide per-task audit data or the full experiment records if useful.

主要语言
Python
星标
93
派生
16
平均合并
9 小时 57 分钟
30 天内合并 PR
1

环境准备

这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

OpenHands/codescout 的其他 Issue

查看 OpenHands/codescout 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。