Search papers, labs, and topics across Lattice.
4
0
6
8
FACET achieves unprecedented task synthesis quality by preserving source intent and ensuring executable state consistency, leading to more reliable terminal agents.
LLM agents struggle to juggle multiple tasks when tool use involves realistic delays, revealing critical weaknesses in temporal reasoning and coordination.
Unlock long-context reasoning in LLMs by turning agent trajectories into gold-standard QA pairs, outperforming models 8x larger on challenging reasoning tasks.
Even the best LLMs struggle to effectively discover, refine, and reuse skills over a lifetime of experience, suggesting current benchmarks significantly overestimate real-world agentic capabilities.
