Search papers, labs, and topics across Lattice.
Affiliation:
3
0
7
10
LLM agents exhibit a staggering ninefold difference in performance when navigating the complexities of a simulated marketplace, yet still fall short of human-designed strategies.
Agentic models can learn to trust their "gut" and rely less on external tools, leading to faster and more accurate reasoning.
Diffusion language models can achieve up to 3.4x faster inference without sacrificing quality by committing stable token prefixes instead of scattering accepted tokens.
