Tencent / Tencent/digitalhuman

Question about baselines of RLVMR (ReAct implementation and evaluation code)

Open
#24 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
361
Forks
52
PR merge metrics
No merged PRs in 30d

Description

Hello, thank you for the great work on the RLVMR. I'm particularly interested in the ReAct results mentioned in the experiments (Qwen-1.5B/7B ReAct).

I noticed that your experimental setup and evaluation environment likely differ from the official ReAct implementation. Could you please clarify if the code for the prompting ReAct (without any fine-tuning) and its evaluation pipeline are included in this repository?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Review the repository's experiment and evaluation materials, then compare them with the official ReAct implementation. Determine whether prompting-only ReAct for Qwen-1.5B/7B and its evaluation pipeline are included, and document the relevant locations or clarify their absence.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.