Multi-agent planning and execution on MAT2-THOR Overall Tasks
78TCRScale Plan
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Scale PlanBackbone=GPT-5.22026.03 | 78 | 85 | 94 | |
| LaMMA-P (LLM corrected)Backbone=GPT-5.22026.03 | 53 | 69 | 85 | |
| LLM+P (PDDL based)Backbone=GPT-5.22026.03 | 39 | 50 | 67 | |
| LLM as a PlannerBackbone=GPT-5.22026.03 | 37 | 51 | 77 | |
| LaMMA-P (PDDL plan only)Backbone=GPT-5.22026.03 | 33 | 51 | 74 |