Search papers, labs, and topics across Lattice.
Department of Gastroenterology, Renmin Hospital, Wuhan University, Wuhan, China
2
0
5
6
LLMs struggle to retrieve the right tools when instructions are vague, but a simple "bridge model" that rephrases instructions can more than double retrieval accuracy.
LLMs can now navigate massive toolsets with a "Try-Check-Retry" loop, boosting tool-calling accuracy by up to 25% and letting smaller models punch above their weight.
