developer tools
A Frozen Agent Trace Became a Reusable World
Terminal-Universe replays file operations backward, fills missing dependencies and turns one demonstration into many executable tasks.
Summary
Terminal-Universe replays file operations backward, fills missing dependencies and turns one demonstration into many executable tasks.
The framework reconstructs the partial workspace behind a terminal trajectory by restoring files to their pre-agent states, then uses a completion agent for missing pieces. It synthesizes original and new tasks, crosses related workspaces and extends single turns into sessions with simulated user refinement. Applied to public trajectories, the authors report 37,300 task-sufficient environments; fine-tuning Qwen3.5-27B on them improved Terminal-Bench 2.1 by 11.9 points and a multi-round EvoCode-Bench measure by 13.8 points.
Why it matters
Terminal-Universe replays file operations backward, fills missing dependencies and turns one demonstration into many executable tasks.
Limits and context
No additional limitation was separately recorded.
Key claims
Terminal-Universe replays file operations backward, fills missing dependencies and turns one demonstration into many executable tasks.
Evidence: source-2026-09-04-009
Sources
- arXiv preprint 2609.04148arXiv · primary research
Corrections
No corrections have been recorded for this story.