Python · MIT
deep-symbolic-mathematics/LLM-SR
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models
★ 283
Stars
53 forks · 8 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
8.2
Momentum / 100
see the breakdown below
2y ago
Created
last push 15mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.53× the monthly pace |
| Freshness | 15 | 0.0 | last push 15mo ago; decays to zero at 180 days |
| Scale | 15 | 7.1 | 283 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 8.2 | sum of the above |
Detail
| Topics | ai4codeai4mathai4scienceequation-discoverylarge-language-modelsllm-agentprogram-synthesisscientific-discoverysymbolic-regression |
| Matched on | AI Agents (llm-agent) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +7 stars over 26 days = 0.3/day |
| Lifetime average | 0.30 stars/day over 930 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |