PulseAugur
中
实时 10:29:50
English(EN) Self-Supervised Scaling of Terminal Environments for Scientific Domains

新框架使用科学软件训练AI代理

研究人员开发了一个名为软件回路重建(SWR)的自监督框架,用于训练科学领域的终端代理。该方法利用现有的科学软件工作流来生成参考输出和验证目标,减少了手动工程的需求。通过执行多个输入配置和划分案例,SWR使代理能够在不直接访问源代码的情况下构建可编辑程序,然后根据工作流输出来评估这些程序。该框架已在六个领域的500个工作流中实现,并使用SWR生成的数据对Qwen3.8-27B模型进行微调,提高了其在Terminal-Bench基准测试上的性能。 AI

影响 这种方法可以通过利用现有的代码库,实现更有效地训练用于专业科学任务的AI代理。

排序理由 该集群包含一篇详细介绍新框架和实验结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新框架使用科学软件训练AI代理

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍新框架和实验结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Zhongzhi Li, Yucheng Shi, Zongxia Li, Junyao Yang, Ruhan Wang, Yu Wang, Jingyuan Huang, Jichao Yu, Ninghao Liu, Haitao Mi, Leowei Liang ·

    面向科学领域的终端环境的自监督扩展

    arXiv:2610.02710v1 Announce Type: cross Abstract: Terminal agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference behavior and a domain-specific verifier that distingu…