Proactive Autonomy on TongSim
17.08Cumulative Value (ΔV)ValuePlanner
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ValuePlanner2026.04 | 17.08 | 80 | 16.07 | |
| D2A2026.04 | 11.91 | 75 | 10.1 | |
| Plan-and-Solve2026.04 | 11.8 | 79 | 10.6 | |
| Reflexion2026.04 | 11.48 | 76 | 10.5 | |
| ReAct2026.04 | 7.6 | 81 | 7.27 |