Search papers, labs, and topics across Lattice.
4
0
5
Harness-policy co-evolution can reduce adverse safety responses by 3x while simultaneously boosting benign utility in LLM agents.
Evolving safety harnesses using trajectory data can reduce agent safety risks by over 3x while enhancing overall utility.
Turn messy human expertise into neatly packaged, agent-usable skills with this automated system that distills heterogeneous traces into portable and correctable AI skills.
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.
