Search papers, labs, and topics across Lattice.
5
0
10
Evolving safety harnesses using trajectory data can reduce agent safety risks by over 3x while enhancing overall utility.
OrthoPilot outperformed seasoned orthopaedic experts in diagnostic reasoning, achieving a 10.6% increase in management success for complex musculoskeletal cases.
Self-evolving knowledge graphs can dramatically enhance multimodal reasoning by continuously adapting to new information and correcting errors in real-time.
A unified framework reveals that existing LLM policy optimization methods often overlook compound failures that require simultaneous adjustments to both trajectory and reward components.
LLMs are still far from being able to generate expert-level clinical guidelines, despite advances in deep research systems.
