Search papers, labs, and topics across Lattice.
Center of Excellence for Generative AI
5
0
6
4
A layered defense can thwart most self-state attacks on AI agents, but a hidden vulnerability persists that challenges current OS security paradigms.
Self-improving agents can evolve autonomously with minimal human input, reshaping our approach to AI adaptability and deployment.
Current memory agents fail to provide reliable governance in shared settings, with no method achieving a balance between utility, access control, and forgetting.
LLM search agents can be easily manipulated, with some models endorsing false claims at alarming rates, revealing a critical gap in their safety evaluation.
FORT-Searcher achieves superior performance by synthesizing training tasks that actively resist shortcut exploitation, transforming how we train deep search agents.
