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

CORE 改进了深度研究代理的上下文管理准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 11:36

研究人员开发了 CORE，一种用于深度研究代理的新型框架，它解决了检索全面搜索结果与保持简洁代理上下文之间的权衡。CORE 采用粗粒度到细粒度的搜索策略，首先使用密集检索器检索段落，然后使用后期交互重排序器提取最相关的片段。这种方法结合上下文管理来扩展相关来源并抑制重复项，在多个代理模型和基准测试中展示了最先进的准确性和证据召回率，其性能优于 Tongyi DeepResearch 和 OpenResearcher 等现有框架。 AI

影响 CORE 在上下文管理和证据检索方面的方法可以显著提高复杂问答系统的效率和准确性。

排序理由该条目描述了一篇介绍深度研究代理新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一篇介绍深度研究代理新方法的论文。[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, 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: 5 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]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-11-05 11:36

CORE：具有上下文管理的粗粒度到细粒度搜索，用于深度研究

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 give enough context for reliable semantic matching…

本文如何被排名

报道来源 [1]

CORE：具有上下文管理的粗粒度到细粒度搜索，用于深度研究

相关实体

相关话题