Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Summary
Terminal-Universe is a framework that reconstructs executable workspaces from agent trajectories to synthesize diverse training tasks, improving AI agent post-training performance through supervised fine-tuning.
View Cached Full Text
Cached at: 09/04/26, 03:57 AM
Paper page - Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Source: https://huggingface.co/papers/2609.04148 Authors:
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
Terminal-Universe reconstructs executable workspaces from agent trajectories to synthesize diverse training tasks and improves post-training performance through supervised fine-tuning.
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 synthesizecross-workspace queriesspanning multiple codebases, as developers routinely do in real-world development. For depth, we extend the initial single-turn query into amulti-round sessionthat captures iterative user feedback and requirement refinement via a user agent. Applied to publicterminal agent trajectories, Terminal-Universe produces 37.3k task-sufficient environments.Supervised fine-tuningof 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.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2609\.04148
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.04148 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.04148 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.04148 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
TerminalTraj is a scalable pipeline that generates high-quality terminal agent trajectories using Dockerized environments, achieving up to 20% improvement on terminal task benchmarks with models like TerminalTraj-32B.
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World introduces a fully automated pipeline that uses agent skills to synthesize high-quality training data for terminal agents, enabling models to outperform baselines with only 1.2% of the training data. The method co-derives task instructions, environments, and teacher trajectories from skill primitives.
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
CLI-Universe is a synthesis engine that generates verifiable terminal-agent tasks via multi-dimensional capability taxonomy and evidence-guided research, producing a distilled dataset of 6,000 trajectories. Fine-tuning Qwen3-32B on this dataset achieves 33.4% on Terminal-Bench 2.0, setting a new state-of-the-art for open-source models at or below 32B parameters.
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
LiteCoder-Terminal-Gen introduces a zero-dependency synthetic pipeline that generates executable terminal training environments, producing SFT and RL datasets that enable language agents to achieve significant performance gains on Terminal Bench benchmarks.
What Makes Interaction Trajectories Effective for Training Terminal Agents?
This paper investigates what makes interaction trajectories effective for training terminal-based AI agents, introducing the Terminal-Lego pipeline and revealing a pedagogical paradox where weaker agents can produce better training data. It finds that environment-grounded supervision, rather than teacher performance, is key for student generalization.