Metraipolis › archive › dc_ebf0377e027f

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments — arXiv:2609.04148

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04148
License (as archived)
CC0-1.0
Archived
2026-10-17T01:11:35.396Z
SHA-256 of the archived text
201b668d2bdfb9261dbbd408ca7d79f181d040c87cc4bc8eb58956e3d65eea7c
Stable URL of this page
https://metraipolis.com/documento/dc_ebf0377e027f

How to cite

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments — arXiv:2609.04148 — arXiv (en), https://arxiv.org/abs/2609.04148 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebf0377e027f (Metraipolis archive dc_ebf0377e027f, sha256 201b668d2bdfb9261dbbd408ca7d79f181d040c87cc4bc8eb58956e3d65eea7c)
BibTeX
@misc{dcebf0377e027f,
  title = {Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments — arXiv:2609.04148},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04148},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebf0377e027f; sha256 201b668d2bdfb9261dbbd408ca7d79f181d040c87cc4bc8eb58956e3d65eea7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04148. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedback, whereas a trajectory is a single frozen demonstration. Rather than generating environments from scratch, we observe that the tool-execution history in existing trajectories exposes the structure and contents of the environments in which they ran, making it possible to reconstruct those environments from the trajectories themselves. Thus, we introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment and explores it for synthesizing new tasks and continued interactions. Specifically, Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the agent modified it, yielding a partial workspace; a completion agent then supplies the missing files and dependencies. On this recovered workspace, we both reconstruct the original intent task and synthesize entirely new ones. Besides, we also scale the tasks along two complementary axes: breadth and depth. For breadth, we mine directional dependency relations between related environments and synthesize cross-workspace queries spanning multiple codebases, as developers routinely do in real-world development. For depth, we extend the initial single-turn query into a multi-round session that captures iterative user feedback and requirement refinement via a user agent. Applied to public terminal agent trajectories, Terminal-Universe produces 37.3k task-sufficient environments. Supervised fine-tuning of Qwen3.5-27B on this corpus improves single-round performance on Terminal-Bench 2.1 by 11.9 points and multi-round performance on EvoCode-Bench v2 MT@4 by 13.8 points.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.04148 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:28:02.914Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).