Multi-agent planning and execution on MAT2-THOR Simple Tasks
92TCRScale Plan
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Scale PlanBackbone=GPT-5.22026.03 | 92 | 95 | 98 | |
| LaMMA-P (LLM corrected)Backbone=GPT-5.22026.03 | 76 | 84 | 91 | |
| LLM+P (PDDL based)Backbone=GPT-5.22026.03 | 48 | 57 | 74 | |
| LLM as a PlannerBackbone=GPT-5.22026.03 | 44 | 56 | 79 | |
| LaMMA-P (PDDL plan only)Backbone=GPT-5.22026.03 | 36 | 56 | 79 |