Search papers, labs, and topics across Lattice.
4
0
7
LLMs exhibit a surprising mechanism-level routing ceiling, with accuracy jumping by over 10% when provided with specific cues, revealing critical misrouting issues in proof-mechanism classification.
Achieving superior accuracy-efficiency trade-offs, ParetoPO redefines how tool-integrated agents can be optimized for real-world applications.
Control-flow hallucination isn't a bug鈥攊t's a feature of probabilistic LLMs, and Agentic Programming offers a robust solution.
Untangling multilayer networks just got easier: T-GINEE uses tensors to explicitly model cross-layer dependencies, outperforming methods that treat layers independently.
