面向长时程终端智能体的规模化智能体数据

AI 摘要

该论文提出 TerminalHorizon，一个面向长时程终端智能体的全自动数据合成引擎，通过独立执行识别环境构建中被省略的关键工作，并据此重建环境，同时在同一目标下逐步扩展任务以延续智能体行为模式。研究构建了 1.5K 任务环境，并对 Qwen3.5-27B 进行监督微调得到 TerminalHorizon-27B，在涵盖编码智能体、真实生产环境智能体任务和通用推理的 12 个基准上均取得显著性能提升。多个 RSI 案例研究（每个预算 12 小时）进一步显示模型能在初始方案之外持续实验、根据反馈改进方法并保留有效改进。

正文节选

Scaling Agentic Data for Long-Horizon Terminal Intelligence 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

发布时间：—

抓取时间：2026-10-13 11:22

来源机构：Hugging Face