Search papers, labs, and topics across Lattice.
Peking University
5
0
7
ToolAtlas achieves up to 21.61% better performance in tool utilization by shifting memory management from agents to tool providers, revolutionizing how LLMs interact with external tools.
Dynamic rubrics that evolve with the policy can significantly enhance reinforcement learning performance, even without external supervision.
ScaffoldAgent's utility-guided approach ensures that outlines evolve dynamically, leading to superior long-form report generation and improved factual accuracy.
The $\ell_2$ norm of hidden states serves as a powerful indicator of reasoning intensity in LLMs, enabling new techniques that boost reasoning performance without extra training.
LLMs can reason far better on clinical records when demonstrations are selected using a graph-guided approach that combines patient data with LLM-estimated information gain.
