Multi-agent planning and execution on MAT2-THOR Vague Tasks
71Task Completion Rate (TCR)Scale Plan
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Scale PlanBackbone=GPT-5.22026.03 | 71 | 71 | 82 | |
| LLM as a PlannerBackbone=GPT-5.22026.03 | 57 | 57 | 88 | |
| LaMMA-P (PDDL plan only)Backbone=GPT-5.22026.03 | 57 | 64 | 77 | |
| LLM+P (PDDL based)Backbone=GPT-5.22026.03 | 43 | 52 | 58 | |
| LaMMA-P (LLM corrected)Backbone=GPT-5.22026.03 | 43 | 50 | 85 |