Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Ranking
Overall
88
Content
95
Popularity
71
Observed public metrics from 1 member.
Merged summary
TL;DR - Terminal-Universe reconstructs reusable, executable coding environments from recorded terminal-agent trajectories, then generates new single- and multi-round tasks from them. The resulting 37.3k environments substantially improved a fine-tuned Qwen3.5-27B on two coding-agent benchmarks.
- Replays recorded file operations to recover files as they existed before agent modifications, producing a partial workspace.
- Uses a completion agent to supply missing files and dependencies, then reconstructs original tasks and synthesizes new ones.
- Expands task breadth with cross-codebase queries and task depth with iterative, multi-round user feedback.
- Fine-tuning improved Terminal-Bench 2.1 by 11.9 points and EvoCode-Bench v2 MT@4 by 13.8 points.
Sources (1)
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Public signals
Hugging Face upvotes 244
TL;DR - Terminal-Universe reconstructs reusable, executable coding environments from recorded terminal-agent trajectories, then generates new single- and multi-round tasks from them. The resulting 37.3k environments substantially improved a fine-tuned Qwen3.5-27B on two coding-agent benchmarks.
- Replays recorded file operations to recover files as they existed before agent modifications, producing a partial workspace.
- Uses a completion agent to supply missing files and dependencies, then reconstructs original tasks and synthesizes new ones.
- Expands task breadth with cross-codebase queries and task depth with iterative, multi-round user feedback.
- Fine-tuning improved Terminal-Bench 2.1 by 11.9 points and EvoCode-Bench v2 MT@4 by 13.8 points.