EMNLP MAIN 2025 StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization
active 2025-05-23 → 2026-04-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 315 days from 2025-05-23 to 2026-04-02. Pushes: 11 total, peak 6 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 9 total, peak 3 in a day. Comments: 15 total, peak 7 in a day. Stars: 30 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| zxh20001117 | 20 | 7 | 0 | 10 |
| Zillwang | 4 | 4 | 0 | 0 |
| CarnegieBin | 4 | 0 | 0 | 4 |
| wxt625 | 1 | 0 | 0 | 0 |
| sunhaonlp | 1 | 0 | 0 | 0 |
| boardman0 | 1 | 0 | 0 | 0 |
| ZijunSong | 1 | 0 | 0 | 0 |
| dawson-chen | 1 | 0 | 0 | 0 |
| luxuriance19 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#7zxh200011172025-12-05 09:30Question about the “support_docs” field in data processing for step reward
- Issue#9wxt6252025-11-06 16:33Question about retrive
- Issue#7ZijunSong2025-10-30 03:29Question about the “support_docs” field in data processing for step reward
- Issue comment#6luxuriance192025-09-28 08:12Why are your model’s test results even weaker than Search-R1?
- Issue comment#6CarnegieBin2025-09-27 13:44Why are your model’s test results even weaker than Search-R1?
- Issue comment#6CarnegieBin2025-09-27 07:21Why are your model’s test results even weaker than Search-R1?
- Issue comment#6zxh200011172025-09-26 09:52Why are your model’s test results even weaker than Search-R1?
- Issue comment#6zxh200011172025-09-26 09:13Why are your model’s test results even weaker than Search-R1?
- Issue comment#6CarnegieBin2025-09-26 08:45Why are your model’s test results even weaker than Search-R1?
- Issue comment#6zxh200011172025-09-26 08:45Why are your model’s test results even weaker than Search-R1?
- Issue comment#6CarnegieBin2025-09-26 08:21Why are your model’s test results even weaker than Search-R1?
- Issue comment#6zxh200011172025-09-26 04:50Why are your model’s test results even weaker than Search-R1?
- Issue comment#6zxh200011172025-09-26 04:42Why are your model’s test results even weaker than Search-R1?
- Issue#5zxh200011172025-09-22 17:48qusetion of train.sh
- Issue#4zxh200011172025-09-22 17:48论文里的r_overall是不是少写了一个部分？
- Issue#3zxh200011172025-09-22 17:48Is the dataset prepared for open-sourcing?
- Issue comment#5zxh200011172025-09-22 17:47qusetion of train.sh
- Issue#5boardman02025-09-20 03:24qusetion of train.sh
- Issue comment#4zxh200011172025-09-11 13:38论文里的r_overall是不是少写了一个部分？
- Issue#4Victoriaheiheihei2025-07-25 03:22论文里的r_overall是不是少写了一个部分？
- Issue#2sunhaonlp2025-06-19 08:41Concerns regarding ZeroSearch Reproduction Setup
- Issue comment#2zxh200011172025-06-18 08:59Concerns regarding ZeroSearch Reproduction Setup
- Issue comment#1zxh200011172025-05-29 09:34关于图5a中的一点疑问
- Issue#1dawson-chen2025-05-27 06:12关于图5a中的一点疑问
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 30 stars here means stars gained during the window, not the repo's star count.