LATS

Researchers introduced GATS, a planning framework that eliminates LLM calls during inference, achieving a 100% success rate on synthetic tasks and outperforming LATS and ReAct. GATS uses a layered wor…

Researchers introduced GATS (Graph-Augmented Tree Search), a planning framework that uses UCB1-based tree search with a layered world model to eliminate LLM calls during inference. GATS achieved 100% …