A Framework for LLM-based Multi-Agent Reinforced Training and Inference
active 2025-05-27 → 2026-05-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 359 days from 2025-05-27 to 2026-05-20. Pushes: 29 total, peak 6 in a day. Pull requests: 7 total, peak 1 in a day. Issues: 11 total, peak 3 in a day. Comments: 19 total, peak 3 in a day. Stars: 218 total, peak 21 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 |
|---|---|---|---|---|
| iseesaw | 26 | 14 | 1 | 8 |
| XiaoTiank | 10 | 10 | 0 | 0 |
| Yutongzhang20080108 | 9 | 2 | 2 | 4 |
| a-F1 | 6 | 0 | 0 | 3 |
| jackjyzhang | 4 | 0 | 1 | 2 |
| zengsihang | 3 | 1 | 2 | 0 |
| Yi-Eaaa | 2 | 0 | 0 | 1 |
| kkkjz | 1 | 0 | 0 | 0 |
| lpf992 | 1 | 1 | 0 | 0 |
| ltjed | 1 | 0 | 0 | 1 |
| ZXJC-niusile | 1 | 0 | 1 | 0 |
| Biqing-Qi | 1 | 1 | 0 | 0 |
| atanu2531 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#21ZXJC-niusile2026-04-08 13:29
- Issue#15Yutongzhang200801082025-12-20 15:52Lora
- Issue comment#15Yutongzhang200801082025-12-20 15:52Lora
- Issue#16Yi-Eaaa2025-12-13 08:53Training Problems (No outputs found for the agent)
- Issue comment#16Yi-Eaaa2025-12-13 08:53Training Problems (No outputs found for the agent)
- Issue comment#14iseesaw2025-12-12 10:03Request for ReviewRL Eval Code
- Issue comment#16iseesaw2025-12-12 10:03Training Problems (No outputs found for the agent)
- Issue#15kkkjz2025-12-11 03:00Lora
- Issue comment#13ltjed2025-10-28 17:29docker support/setup?
- Issue comment#9iseesaw2025-10-27 14:03Faced below issues during usage with scoop on windows
- Issue comment#7Yutongzhang200801082025-10-03 13:57Fix testnew, add ninja, ray[default] and minor moderation
- Pull request#7Yutongzhang200801082025-10-03 13:57
- Issue comment#8Yutongzhang200801082025-09-21 09:07Example bugs
- Issue comment#9Yutongzhang200801082025-09-21 06:48Faced below issues during usage with scoop on windows
- Issue#9atanu25312025-09-14 05:46Faced below issues during usage with scoop on windows
- Pull request#7Yutongzhang200801082025-08-10 14:37
- Issue comment#2iseesaw2025-08-05 14:36Resource Efficiency and LoRA Compatibility Inquiry
- Issue#1iseesaw2025-08-05 14:34Support hierarchical multi-agent training?
- Issue comment#4iseesaw2025-08-05 14:32Generative RMs
- Issue#4iseesaw2025-08-05 14:32Generative RMs
- Issue#3iseesaw2025-08-05 14:31Training Script for `chain-of-agents`
- Issue comment#5iseesaw2025-08-05 14:19fix colocate_actor_ref vllm engine still colocated bug
- Pull request#5iseesaw2025-08-05 14:19
- Pull request#6zengsihang2025-08-03 15:32
- Pull request#6zengsihang2025-08-02 19:49
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 218 stars here means stars gained during the window, not the repo's star count.