🛰️ Daily AI Frontier
‹ back to 2026-09-04

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Research LLM Agents

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

arXiv cs.AI Jie Wu, Zhenru Zhang, Beichen Zhang, Xuwu Wang, Yuhui Su, Mouxiang Chen, Peng Wang, Zhihai Wang, Que Shen, Hao Zhou, An Yang, Fei Huang, Yujiu Yang, Dayiheng Liu 2026-09-03 arXiv:2609.04148
Public signals Hugging Face upvotes 244
Providers: Hugging Face · Upvotes 244 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-25 14:24:04.721128 UTC

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.
item →