Terminal-Universe: turning agent trajectories into scalable terminal environments
Reconstructs executable terminal training environments retroactively from existing agent trajectories: it replays recorded file operations to restore the pre-agent workspace, fills gaps with a completion agent, and synthesizes new tasks along breadth (cross-codebase queries) and depth (multi-round sessions with a user simulator). Applied to public trajectories it produces 37.3k task-sufficient environments.
Why it matters
223 upvotes on HF Daily Papers. Fine-tuning Qwen3.5-27B on the reconstructed corpus gains +11.9 points on Terminal-Bench 2.1 and +13.8 on multi-round EvoCode-Bench v2 — environments, not more demonstrations, are the bottleneck for agent post-training, and this makes them cheap to manufacture at scale.
Importance: 4/5
Notable paper + 223 upvotes on HF Daily Papers