跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-09AI 評分43

TerminalHorizon:擴展長時程終端智能體數據

Scaling Agentic Data for Long-Horizon Terminal Intelligence

AI 導讀

研究提出 TerminalHorizon,一套為長時程終端智能體合成數據的全自動引擎,並據此構建 1.5K 個任務環境。以所得數據監督式微調 Qwen3.5-27B 後,得到 TerminalHorizon-27B;該模型在涵蓋編碼智能體、真實生產環境智能體及一般推理的 12 項基準測試中均取得顯著提升。

正文

Abstract

Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and turn intermediate results into final deliverables. High-quality long-horizon trajectories capture these agentic behavioral patterns and their connections within a single problem-solving process, providing richer experience for sustained autonomous work. However, environment synthesis may complete or simplify the key work underlying these patterns in advance and thus remove the need for exploration, implementation, and verification that the agent was meant to perform. To address this, we introduce TerminalHorizon, a fully automated data synthesis engine for long-horizon terminal agents. Starting from real-world professional work, it uses independent execution to identify key work omitted during construction and uses the resulting evidence to guide environment reconstruction. To extend these patterns across stages, it progressively expands tasks under the same goal, introducing new requirements that build on prior results and call for further exploration and improvement. Using this engine, we construct 1.5K task environments and perform supervised fine-tuning of Qwen3.5-27B on the resulting dataset to obtain TerminalHorizon-27B. We achieve substantial performance gains on all 12 benchmarks spanning coding-agent tasks, agentic tasks in real-world production settings, and general reasoning. Multiple RSI case studies, each with a 12-hour research budget, further demonstrate the model's ability to continue experimenting beyond an initial solution, improve its methods based on feedback, and retain effective improvements in its final deliverables.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.13166

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 3

shunzou05/TerminalHorizon-27B

Image-Text-to-Text •

3.05M •

Updated 1 day ago

•

47

•

2

shunzou05/TerminalHorizon-35B-A3B

Image-Text-to-Text •

5.58M •

Updated 1 day ago

•

938

shunzou05/TerminalHorizon-122B-A10B

Image-Text-to-Text •

123B •

Updated about 22 hours ago

•

68

Datasets citing this paper 2

shunzou05/TerminalHorizon-Environment

Viewer •

Updated 1 day ago

•

1.54k

•

287

•

1

shunzou05/TerminalHorizon-3K

Viewer •

Updated 1 day ago

•

2.85k

•

106

•

1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.13166 in a Space README.md to link it from this page.

Collections including this paper 1

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co