Search papers, labs, and topics across Lattice.
4
0
9
2
Evolving runtime guards can slash attack success rates by over 78% while preserving agent performance.
Vanguard not only blocks unsafe actions before they occur but also boosts benign task completion, achieving a remarkable dual improvement in agent safety.
Stop wasting tokens: a novel RL framework slashes LRM token generation by 40% without sacrificing accuracy by adaptively controlling reasoning length.
DeepSight offers an all-in-one open-source toolkit for LLM safety, promising to move beyond black-box evaluations and provide white-box insights into internal mechanisms.
