ResearchBenchmarksMulti-robot task planning on MACE-THOR Temporal-DependentFollow38SRH-AIM3.6812.5921.530.41Jan 16, 2026Evaluation ResultsMethodMethodLinksSRGCRExecution RateH-AIMLLM Backbone=GPT-4oLLM Backbone=GPT-4o2026.01386271H-AIMLLM Backbone=Claude-3....LLM Backbone=Claude-3.5-Sonnet2026.01335557LaMMA-PLLM Backbone=GPT-4oLLM Backbone=GPT-4o2026.01102683H-AIMLLM Backbone=Qwen-MaxLLM Backbone=Qwen-Max2026.0153149H-AIMLLM Backbone=DeepSeek-...LLM Backbone=DeepSeek-V3.12026.0153349