PulseAugur
中
实时 13:29:37
English(EN) LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

LENS框架为LLM代理提供无需索引的上下文内搜索

研究人员开发了LENS(潜在证据探索与搜索),一个用于动态原始文档上下文内搜索的新框架。与依赖预先物化证据的传统检索增强方法不同,LENS无需持久索引即可运行。它在候选证据单元上维护一个查询条件信念,并使用LLM相关性预言机和互补的提议策略在受控预算内迭代地改进此信念。这种方法使LENS能够适应文档变化,并与现有基线相比提供更强的支持事实定位和答案基础。 AI

影响 这种无需索引的方法可以通过减少对昂贵且过时的证据索引的依赖来简化LLM代理的操作。

排序理由 该集群描述了一篇关于用于上下文内搜索的新颖框架的详细研究论文。

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 →

LENS框架为LLM代理提供无需索引的上下文内搜索

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
该集群描述了一篇关于用于上下文内搜索的新颖框架的详细研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, infra
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
52 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) · Xingjun Wang, Gongsheng Li, Qi Fan, Yunlin Mao, Luyan Su, Yingda Chen ·

    LENS:通过动态原始文档的潜在证据探索进行上下文内搜索

    arXiv:2608.16185v1 Announce Type: cross Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmente…

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

    LENS:通过动态原始文档的潜在证据探索进行上下文内搜索

    LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed ch…