PulseAugur
中
实时 01:33:33
English(EN) Self-Supervised Scaling of Terminal Environments for Scientific Domains

新框架使用科学软件训练AI终端代理

研究人员开发了一个名为软件在环重建(SWR)的自监督框架,用于在科学领域创建终端代理的训练环境。该方法利用现有的科学软件工作流程生成参考行为和验证目标,减少了手动工程的需求。当应用于Qwen3.8-Max时,该框架促进了838个任务的解决,并产生了1400多个已验证的轨迹。使用这些数据对Qwen3.8-27B进行进一步微调,显著提高了在Terminal-Bench 2基准测试上的性能,表明了来自科学软件的可扩展监督的潜力。 AI

影响 通过利用现有软件,能够对科学任务的AI代理进行可扩展训练,有可能加速AI在研究中的应用。

排序理由 该集群描述了一篇研究论文,其中详细介绍了一个用于训练AI代理的新框架和基准,包括特定模型的性能结果。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新框架使用科学软件训练AI终端代理

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇研究论文,其中详细介绍了一个用于训练AI代理的新框架和基准,包括特定模型的性能结果。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
7 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  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…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    面向科学领域的终端环境的自监督扩展

    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 distinguishes semantic correctness from superficially plau…