Search papers, labs, and topics across Lattice.
Lenovo, Beijing, China, Hanhui Li, Xuan Huang, Wanquan Liu, Xiaodan Liang, Chenqiang Gao are with the School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, P.R. China, 518107. Yuhao Cheng, Long Chen, and Yiqiang Yan are with the Lenovo Research Group, Shenzhen, P.R. China, 518038.∗ Hanhui Li and Xuan Huang contribute equally.† Chenqiang Gao is the corresponding author
1
7
2
1
A 7B parameter agent can now rival the performance of models 4-10x larger at autonomous computer operation, thanks to innovations in data generation, reinforcement learning, and model enhancement.