ReTerm: Recovery Training for Self-Improving Terminal Agents
ReTerm: Recovery Training for Self-Improving Terminal Agents
ReTerm 是一款透過學習復原自身失敗任務來自我改進的終端智能體,旨在提升長時間執行任務時從錯誤中恢復的能力。研究團隊以 Qwen3.5-9B 為基礎構建 ReTerm-9B,在 Terminal-Bench 2.0 的 Pass@1 得分為 34.8%,較基礎模型高 14.6 個百分點。團隊亦發布 ReTerm-10K 數據集及 ReTerm-GRPO 在線強化學習算法。
Published on Oct 13
Authors:
,
,
,
,
Abstract
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty implementations), eventually leading to task failures. To this end, we present ReTerm, a self-improving terminal agent trained by learning how to recover from its own failed terminal tasks. To support its training, we construct a customized data pipeline and produce ReTerm-10K, a high-quality dataset that provides effective recovery demonstrations for SFT cold start. Furthermore, we propose ReTerm-GRPO, an online RL algorithm that forks from the agent's own failure states to generate multiple independent self-recovery attempts. By learning from whether these attempts successfully complete the task, the agent self-improves through its own recovery experience. Built on Qwen3.5-9B, our ReTerm-9B achieves 34.8% Pass@1 on Terminal-Bench 2.0, improving over the base model by 14.6 points. Further analysis shows that our method achieves consistently higher recovery rates across diverse error categories compared with standard GRPO training. All code, data and model are released at https://github.com/twothsnd/ReTerm.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.18484
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Image-Text-to-Text • 9B • Updated 7 minutes agotwothsnd/ReTerm-9B
Datasets citing this paper 1
twothsnd/ReTerm-10K
Viewer • Updated 7 minutes ago • 9.71k • 7
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.18484 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co