Search papers, labs, and topics across Lattice.
2
0
6
Frontier search agent performance does not require complex multi-agent swarms or test-time search verifiers: a single ReAct policy trained via iterative SFT-RL climbing hits 56.4% on Humanity's Last Exam and 92.9% on DeepSearchQA.
MOCAP slashes LLM inference latency by over 76% while boosting throughput more than threefold, redefining efficiency for long-context processing on wafer-scale chips.
