Search papers, labs, and topics across Lattice.
Affiliation:
4
0
8
11
LLM distillation can achieve 18.55% higher math accuracy and 13.8 points better ALFWorld success by intelligently branching student trajectories at uncertain decision points, not just at turn starts.
Transition supervision can dramatically boost LLM agent performance, outperforming standard policy optimization by leveraging environmental feedback.
Kimi K3's innovative architecture achieves a 2.5x scaling efficiency improvement, enabling robust performance across diverse long-horizon tasks.
A unified evaluation framework that simplifies the assessment of LLM-based agents could drastically enhance reproducibility and accelerate research breakthroughs.
