English(EN) CORE: Coarse-to-Fine Search with Context Management for Deep Research

新的CORE机制通过上下文管理提高了AI研究代理的准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员开发了CORE，一种新颖的无需训练的机制，旨在提高深度研究代理的准确性和效率。CORE通过采用粗粒度到细粒度的搜索策略，解决了全面搜索与有限代理上下文之间平衡的挑战。它首先使用密集检索器检索相关段落，然后使用后期交互重排序器将这些段落精炼成最相关的片段。此外，CORE还结合了上下文管理来扩展相关信息并抑制冗余片段，在多个基准测试和大型文档语料库上的准确性和召回率方面优于Tongyi DeepResearch和OpenResearcher等现有机制。 AI

影响提高了执行复杂研究任务的AI代理的效率和准确性。

排序理由研究论文，详细介绍了一种用于AI研究代理的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种用于AI研究代理的新方法。[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, 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Hoang Tran Vuong, Ngoc Quan Pham, Hung Bui, Fatih Porikli, Dat Quoc Nguyen · 2026-11-06 05:00

CORE：具有上下文管理的粗粒度搜索，用于深度研究

arXiv:2611.07859v1 Announce Type: cross Abstract: Deep research agents answer complex questions through repeated search. They rely on a harness that runs their tool calls and returns evidence to their context. This creates a trade-off: Search works best over long passages, which …

本文如何被排名

报道来源 [1]

CORE：具有上下文管理的粗粒度搜索，用于深度研究

相关实体

相关话题