PulseAugur
中
实时 03:33:54
English(EN) IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

IQuest-Q1:面向CLI系统的开源代理式基础模型发布

研究人员发布了IQuest-Q1,一个专为命令行界面(CLI)系统设计的开源代理式基础模型。该模型采用了稀疏专家混合(MoE)架构,拥有3200亿个总参数,每次激活150亿个。其开发过程包括三个阶段:使用特定的归一化技术和课程学习进行稳定预训练,通过扩展数据混合和上下文长度进行细粒度中期训练,以及结合监督微调和强化学习的多支架后期训练。最终模型在编码和通用任务方面均表现出色。 AI

影响 IQuest-Q1的此次开源发布可能会加速代理式CLI系统和基础模型领域的研究与开发。

排序理由 该集群描述了一个新的开源AI模型的发布,该模型在arXiv论文和Hugging Face上进行了详细介绍。

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 →

IQuest-Q1:面向CLI系统的开源代理式基础模型发布

本文如何被排名

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一个新的开源AI模型的发布,该模型在arXiv论文和Hugging Face上进行了详细介绍。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
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
3 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.CL TIER_1 English(EN) · A. Jian Yang, An Huang, Bo Dan, Chen Mu, Chengran Yang, Chuan Shi, Feng Chang, Hongxin Li, Hongyuan Tao, Jinxing Zhang, Jujie He, Kun Wang, Lin Jing, Ming Yang, Qicheng Hu, Renyuan Li, Shark Liu, Shawn Guo, Shi Qing, Shi Zhong, Tianyu Zheng, Wei Liu, Wei… ·

    IQuest-Q1:推进 Agentic CLI 系统的基础能力

    arXiv:2610.30949v1 Announce Type: new Abstract: We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and efficient pre-training, combining Stab…

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

    IQuest-Q1:推进 Agentic CLI 系统的基础能力

    IQuest-Q1 is a sparse Mixture-of-Experts foundation model trained via multi-stage pre-training, mid-training, and post-training to achieve strong agentic coding and general capabilities.