Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
7
ArchAgent v2 outperforms hand-designed solutions by achieving a 3.8% IPC speedup through innovative multi-level data prefetching strategies.
AI-generated C++ code incurs 5-8% more compute costs and increased review efforts due to its distinct quality profile, but targeted feedback can substantially improve its performance.
Autonomous research agents are surprisingly unreliable, with existing systems hallucinating references 21% of the time and failing to align methods with code as often as 80%, but a new "Chain-of-Evidence" approach can fix this.
