Search papers, labs, and topics across Lattice.
2
63
5
4
Agentic LLMs can be taught to refuse harmful actions with up to 50% greater success, even zero-shot across diverse models and tasks, by explicitly learning when *not* to act.
Forget brittle, hand-engineered tool use: ARTIST uses reinforcement learning to teach LLMs to *autonomously* decide when and how to use external tools, leading to a 22% performance boost.
