Cite
Notes
Only stored in your browser.
Attribution
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
arXiv 2026
Rethinking Expert Trajectory Utilization in LLM Post-training
arXiv 2025
from 2 papers
Fei Mi
Lifeng Shang
Baiyu Huang
Bowen Ding
Boyu Zhu
Chao Chen
Dantong Zhu
Futing Wang
Jiayang Lv
Jiyao Yuan