Search papers, labs, and topics across Lattice.
3
0
6
5
Multi-iteration experience learning in LLMs can lead to capability collapse, but strategic adjustments in experience granularity and injection patterns can stabilize and enhance performance.
SIRI allows LLM agents to autonomously develop and internalize skills, achieving up to a 2.2% performance boost without external dependencies.
Stop uniformly distilling your LLMs: SCOPE selectively amplifies teacher guidance on incorrect trajectories and reinforces student uncertainty on correct ones, leading to significant gains in reasoning performance.
