LLMs Learn New Skills in RL by Composing Old Ones
active 2025-09-26 → 2026-05-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 242 days from 2025-09-26 to 2026-05-25. Pushes: 4 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 6 total, peak 1 in a day. Comments: 6 total, peak 2 in a day. Stars: 21 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 |
|---|---|---|---|---|
| chenweize1998 | 8 | 4 | 0 | 3 |
| XinXU-USTC | 3 | 0 | 0 | 1 |
| isXinLiu | 2 | 0 | 0 | 1 |
| shizhl | 1 | 0 | 0 | 0 |
| forthelostthings | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#6XinXU-USTC2025-11-10 03:34About the reward score
- Issue#6XinXU-USTC2025-11-10 03:34About the reward score
- Issue comment#8isXinLiu2025-11-07 11:35Question about stage2 rl level1 training
- Issue comment#8chenweize19982025-11-07 09:05Question about stage2 rl level1 training
- Issue#8isXinLiu2025-11-06 13:47Question about stage2 rl level1 training
- Issue#7forthelostthings2025-10-31 18:20Reward Functio Choosing Error
- Issue comment#5chenweize19982025-10-27 07:05OSError: [Errno 16] Device or resource busy
- Issue#4XinXU-USTC2025-10-23 09:08Question about RL stage 1 training data
- Issue#3shizhl2025-10-20 09:09Are the implementation of the anonymous functions provided to LLMs?
- Issue comment#1NielsRogge2025-10-17 15:30Release synthetic datasets for RL-Compositionality on Hugging Face
- Issue#1chenweize19982025-10-17 13:12Release synthetic datasets for RL-Compositionality on Hugging Face
- Issue comment#1chenweize19982025-10-17 13:12Release synthetic datasets for RL-Compositionality on Hugging Face
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 21 stars here means stars gained during the window, not the repo's star count.