Tsinghua and Qwen Rebuild Code Environments from Agent Trajectories to Train Better Agents
A new paper from Tsinghua and Qwen, "Terminal-Universe," converts existing agent trajectories into reusable executable environments for training, beating trajectory imitation and lifting Terminal-Bench performance to 58.1%.
2026-09-10 ~ 2026-09-10 · 2 related posts
- Tsinghua + Qwen paper: rebuilding agent workspaces beats imitating trajectories, lifts Terminal-Bench to 58.1% — rohanpaul_ai · 2026-09-10
- Tsinghua and Qwen team's Terminal-Universe turns agent trajectories into scalable terminal environments — rohanpaul_ai · 2026-09-10