Search papers, labs, and topics across Lattice.
University of Science and Technology of China
3
0
5
TabClaw transforms spreadsheet analysis from a manual, opaque process into an interactive, self-evolving workflow that adapts to user needs and preferences.
Claw-R1 transforms agentic RL by treating interaction data as valuable assets, enabling real-time inspection and curation for optimized training.
StepPO reveals that aligning policy optimization with agent decision-making steps can lead to superior performance in multi-turn interactions, outperforming traditional RL methods.
