Search papers, labs, and topics across Lattice.
4
63
7
3
Training agents in deep, evolving environments can dramatically enhance their performance, with a 9B model achieving a 30.6% accuracy increase through targeted design.
A 4B parameter SLM can now rival frontier agent performance in complex tool-use environments, thanks to a novel reinforcement finetuning framework that teaches it how to strategically acquire context and execute actions.
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.
