Travel planning on ChinaTravel Medium
77.82Final Pass RateBehavior Forest
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Behavior Forest2026.04 | 77.82 | 95.41 | 93.98 | 87.23 | 94.15 | 77.82 | — | |
| NeSy Planningreproduced=true2026.04 | 66 | 84.67 | 84.67 | 84.67 | 82.28 | 66 | — | |
| Syn-PlanningBenchTraining Data=Syn-PlanningBench2026.05 | 52.78 | — | — | — | — | — | 90.5 | |
| BaseTraining Data=Base2026.05 | 51.37 | — | — | — | — | — | 87.96 | |
| Human-AuthoredTraining Data=Human-Authored2026.05 | 51.02 | — | — | — | — | — | 87.96 | |
| LLM-Moduloreproduced=true2026.04 | 1.33 | 56.67 | 92.21 | 3.33 | 61.08 | 22.67 | — | |
| ReActreproduced=true2026.04 | 0.67 | 65.33 | 53.95 | 0.67 | 78.64 | 50.67 | — | |
| Actreproduced=true2026.04 | 0 | 71.1 | 32.6 | 0 | 60.3 | 45.1 | — |