PulseAugur
中
实时 11:34:14
English(EN) Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA

KnowForge系统通过专用代理增强多模态文档问答能力

研究人员推出 KnowForge,这是一个专为开放域多模态文档问答设计的新型流水线系统。KnowForge 将任务分解为专用代理:用于搜索的定位器 (Locator),用于分析内容的深度阅读器 (Deep Reader),以及用于汇编答案的合成器 (Synthesizer)。这种利用知识点索引的角色专用方法,在 M3DocVQA 和 MMLongBench-Doc 等基准测试中显著提高了性能,优于现有的检索增强生成系统,并在某些任务上达到了 GPT-4o 的能力。 AI

影响 这种专用代理方法可能导致在复杂文档分析任务中实现更高效、更准确的信息检索和综合。

排序理由 该集群包含一篇详细介绍新系统及其在基准测试中性能的学术论文。

在 arXiv cs.IR (Information Retrieval) 阅读 →

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

KnowForge系统通过专用代理增强多模态文档问答能力

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
该集群包含一篇详细介绍新系统及其在基准测试中性能的学术论文。
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
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.AI TIER_1 English(EN) · Wenlin Lin, Fanzhe Wei ·

    定位、判断、阅读:基于知识点索引的领域开放多模态文档问答的专业化工具代理

    arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. …

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Fanzhe Wei ·

    定位、判断、阅读:基于知识点索引的领域开放多模态文档问答的专业化工具代理

    Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by jo…