Sequential Experimental Design on Minerva/Olympus (matched replay)
88.5Final Best ScoreCARE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CARE2026.06 | 88.5 | 84.4 | 0.7 | |
| Public incumbent2026.06 | 80 | 73.4 | 9.2 | |
| TPE-style BO2026.06 | 77.6 | 68.3 | 11.6 | |
| LMABO-style LLM-BO2026.06 | 76.6 | 66.5 | 12.6 | |
| BayBE/BoFire-style mixed BO2026.06 | 75.3 | 67.7 | 14 | |
| Ungated LLM-evolving policy2026.06 | 68.8 | 61.4 | 20.4 | |
| Non-evolving LLM policy2026.06 | 63.3 | 58.8 | 25.9 |