PulseAugur
中
实时 01:51:37
English(EN) D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding

D2-ScaleAgent 框架增强长文档理解能力

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员推出 D2-ScaleAgent，一个旨在增强对长篇幅且富含视觉信息的文档理解能力的新型框架。该智能体系统采用双维度缩放范式，根据查询难度动态调整检索和推理过程。它包含一个 Verifier 智能体，负责管理一个持续更新的证据库，从而实现外向缩放以进行扩展检索，以及内向缩放以进行细粒度推理，并具备自适应剪枝和子智能体选择功能。实验表明 D2-ScaleAgent 在 MMLongBench-Doc 和 LongDocURL 等基准测试中表现有效。 AI

影响 该框架有望改进 AI 系统处理和推理长篇幅复杂文档的方式，从而增强在研究和信息检索领域的应用。

排序理由 该集群包含一篇详细介绍新文档理解框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

D2-ScaleAgent 框架增强长文档理解能力

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
Tool
该集群包含一篇详细介绍新文档理解框架的研究论文。[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, other
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
87 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 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Hao Zhang, Longrong Yang, Lunhao Duan, Ziyang Wang, Qing-Guo Chen, Shanshan Zhao ·

    D2-ScaleAgent：用于长文档理解的双维度缩放

    arXiv:2608.16417v1 Announce Type: new Abstract: Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent systems: they first retrieve relevant…

相关实体

相关话题