Circle Packing on CirclePacking T
2.636Best ScoreThetaEvolve (w/ RL)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ThetaEvolve (w/ RL)Model=Distill-Qwen3-8B, Step=652025.11 | 2.636 | 2.636 | |
| ThetaEvolve (w/o RL late)Model=Distill-Qwen3-8B, Step=1002025.11 | 2.636 | 2.636 | |
| ThetaEvolve (w/o RL early)Model=Distill-Qwen3-8B, Step=652025.11 | 2.636 | 2.6354 | |
| ThetaEvolve (w/ RL)Model=ProRL-1.5B-v2, Step=2002025.11 | 2.5225 | 2.3498 | |
| ThetaEvolve (w/o RL late)Model=ProRL-1.5B-v2, Step=6002025.11 | 2.2491 | 2.0991 | |
| ThetaEvolve (w/o RL early)Model=ProRL-1.5B-v2, Step=2002025.11 | 2.1343 | 2.0265 | |
| InitialModel=ProRL-1.5B-v2, Step=02025.11 | 0.9598 | — | |
| InitialModel=Distill-Qwen3-8B, Step=02025.11 | 0.9598 | — |