Skip to content

feat: [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English#1368

Merged
couragec merged 6 commits intomicrosoft:mainfrom
couragec:pr/from-d0f5-upstream
Mar 19, 2026
Merged

feat: [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English#1368
couragec merged 6 commits intomicrosoft:mainfrom
couragec:pr/from-d0f5-upstream

Conversation

@couragec
Copy link
Collaborator

@couragec couragec commented Mar 19, 2026

Summary

This PR updates AutoRL-Bench on top of the latest main in two parts:

  1. Keep the DeepSearchQA local protocol update introduced in the fork.
  2. Translate the AutoRL-Bench task instruction file into English.

Changes

  • DeepSearchQA

    • preserve the 100/200 local split update from commit d0f5b715
  • Documentation

    • translate rdagent/scenarios/rl/autorl_bench/core/instructions.md into English
    • keep the original task contract, API usage, and workspace constraints unchanged

Notes

  • This branch starts from fork commit d0f5b715 and merges in the latest upstream/main.
  • No additional benchmark logic changes are introduced beyond the existing DeepSearchQA split update.

📚 Documentation preview 📚: https://RDAgent--1368.org.readthedocs.build/en/1368/

@XianBW XianBW changed the title [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English feat(AutoRL-Bench): Update DeepSearchQA split and translate task instructions to English Mar 19, 2026
@XianBW XianBW changed the title feat(AutoRL-Bench): Update DeepSearchQA split and translate task instructions to English feat: [AutoRL-Bench] Update DeepSearchQA split and translate task instructions to English Mar 19, 2026
@couragec couragec merged commit 471eb30 into microsoft:main Mar 19, 2026
5 of 6 checks passed
afanty2021 added a commit to afanty2021/RD-Agent that referenced this pull request Mar 20, 2026
- Update timestamp to 2026-03-20 14:45:00
- Add Web UI server features (PR microsoft#1345)
- Add AutoRL-Bench framework (PR microsoft#1348)
- Add LLM finetune scenario (PR microsoft#1314)
- Add DeepSearchQA updates (PR microsoft#1368)
- Add dependency updates and security fixes
- Add Apple Silicon MPS support
- Update core features and application scenarios
- Update changelog with latest upstream changes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants