Search papers, labs, and topics across Lattice.
4
0
7
8
StepGuard slashes attack success rates by over 77% while maintaining nearly all utility, setting a new standard for safety in LLM-based agents.
Achieving a 93.3% collision avoidance success rate, this framework redefines how robots can safely navigate among fragile transparent objects in real-time.
AgentDoG 1.5 proves you can achieve GPT-5.4-level agent safety with open-source models trained on just 1k samples, slashing deployment overhead by two orders of magnitude.
LLM agents can achieve 3x faster web search and higher accuracy by dynamically routing between multiple context management strategies.
