Building Open LLM Web Agents with Self-Evolving Online Curriculum RL
active 2025-03-28 → 2026-06-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 443 days from 2025-03-28 to 2026-06-13. Pushes: 2 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 9 total, peak 2 in a day. Comments: 10 total, peak 3 in a day. Stars: 78 total, peak 3 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 |
|---|---|---|---|---|
| QZH-777 | 14 | 2 | 0 | 7 |
| miridih-jyjang | 3 | 0 | 0 | 1 |
| HancCui | 1 | 0 | 0 | 0 |
| yuleiqin | 1 | 0 | 0 | 0 |
| lihaoxin2020 | 1 | 0 | 0 | 1 |
| gongyifeiisme | 1 | 0 | 0 | 1 |
| tonystark262 | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#56miridih-jyjang2025-07-17 07:10Please find me which part I did wrong
- Issue comment#56miridih-jyjang2025-07-17 04:08Please find me which part I did wrong
- Issue#56miridih-jyjang2025-07-13 11:52Please find me which part I did wrong
- Issue comment#45gongyifeiisme2025-06-23 15:35orm数据集什么时候可以公布？
- Issue#55QZH-7772025-06-10 11:46如果可以直接替换为多模态大模型的话，ORM奖励模型该如何使用
- Issue comment#55QZH-7772025-06-09 09:53如果可以直接替换为多模态大模型的话，ORM奖励模型该如何使用
- Issue#54QZH-7772025-05-26 11:02Why perplexity large than 1?
- Issue#53QZH-7772025-05-26 11:02为什么多模态的例子里，没有一个示例的 mllm_demo.json？
- Issue comment#54QZH-7772025-05-25 05:26Why perplexity large than 1?
- Issue comment#53QZH-7772025-05-25 05:22为什么多模态的例子里，没有一个示例的 mllm_demo.json？
- Issue comment#50QZH-7772025-05-03 16:38How are different trajectories of same intent been collected in SFT training set?
- Issue comment#50lihaoxin20202025-05-02 01:57How are different trajectories of same intent been collected in SFT training set?
- Issue comment#50QZH-7772025-04-30 04:08How are different trajectories of same intent been collected in SFT training set?
- Issue#49QZH-7772025-04-30 03:42What is the expected score on WebArenaLite on the LLAMA3.1-8B SFTed on the released SFT data?
- Issue comment#49QZH-7772025-04-30 03:42What is the expected score on WebArenaLite on the LLAMA3.1-8B SFTed on the released SFT data?
- Issue#51QZH-7772025-04-30 03:35A lost comma in setup.py
- Issue comment#51QZH-7772025-04-30 03:34A lost comma in setup.py
- Pull request#52tonystark2622025-04-20 21:26
- Issue#51HancCui2025-04-18 06:49A lost comma in setup.py
- Issue#49yuleiqin2025-03-30 07:25What is the expected score on WebArenaLite on the LLAMA3.1-8B SFTed on the released SFT data?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 78 stars here means stars gained during the window, not the repo's star count.