ResearchBenchmarksRobot Task Planning on AI2-THOR Elemental tasksFollow100Success RateSMART-LLM93.7695.389798.62Dec 19, 2025Evaluation ResultsMethodMethodLinksSuccess RateSMART-LLMBackbone=Llama2-70bBackbone=Llama2-70b2025.12100RecipeMasterLLM2025.1294