Long-horizon Reasoning on Checkers Jumping
100Performance (n=11)Lookahead-Enhanced Atomic Decomposition
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Lookahead-Enhanced Atomic DecompositionModel=o4-mini, Voting=true, k=8, h=32026.03 | 100 | 52 | 80 | |
| Atomic DecompositionModel=o4-mini, Voting=true2026.03 | 76 | 16 | 0 | |
| Atomic DecompositionModel=o4-mini, Voting=false2026.03 | 14 | 0 | 0 |