Tsinghua and Qwen team's Terminal-Universe turns agent trajectories into scalable terminal environments

rohanpaul_ai · x · 2026-09-10

A new Tsinghua + Qwen team paper flips the usual agent-data recipe: instead of imitating original runs, reconstruct the actual code workspace from a trajectory's tool-execution history and re-solve it.

Result: training on re-solved reconstructed workspaces yields better coding agents than imitating the original trajectories, easing the scarcity of executable environments for agent post-training.

Related event: Tsinghua and Qwen Rebuild Code Environments from Agent Trajectories to Train Better Agents(2 posts)→

Original post →

More from coding & agent

coding & agent channel →