AutoThink is a reinforcement learning framework designed to equip R1-style language models with adaptive reasoning capabilities. Instead of always thinking or never thinking, the model learns when to engage in explicit reasoning, balancing performance and efficiency.
active 2025-05-21 → 2026-03-05 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 289 days from 2025-05-21 to 2026-03-05. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 1 total, peak 1 in a day. Comments: 2 total, peak 1 in a day. Stars: 30 total, peak 6 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 |
|---|---|---|---|---|
| TU2021 | 1 | 0 | 0 | 1 |
| CarnegieBin | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#4CarnegieBin2025-10-30 10:52Training is too slow.
- Issue comment#2TU20212025-06-23 07:30GPU requirements
- Issue comment#1NielsRogge2025-06-04 12:28Release AutoThink models individually on Hugging Face
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.