Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University, *Equal Core Contributions, #Project Lead
4
0
7
Forget dumb context stuffing: LongSeeker shows that strategically *editing* its own memory lets agents solve web search tasks with far greater reliability.
Forget resource-intensive pipelines: a purely academic team achieves SOTA search agent performance with just 10.6k SFT data points, outperforming models trained with CPT+SFT+RL.
EvoMaster achieves unprecedented performance in autonomous scientific discovery, outperforming traditional frameworks by up to 316%.
OpenSeeker proves that frontier-level search agents can be achieved with surprisingly little data, outperforming even heavily optimized industrial systems.
