Planning on TravelPlanner Hard
100Delivery RateEvoAgent
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| EvoAgent2026.04 | 100 | 55.42 | 10.1 | 24.17 | 3.33 | 3.33 | |
| Behavior Forest2026.04 | 100 | 96.88 | 90 | 87.92 | 83.33 | 83.33 | |
| PMC2026.04 | 96 | 87.71 | 58.33 | 54.58 | 40 | 26.67 | |
| llm-rwplanning2026.04 | 85 | 85 | 85 | 83.75 | 80 | 80 | |
| ReAct2026.04 | 66.67 | 49.38 | 0 | 1.25 | 0 | 0 |