arXiv cs.CL· Hoang Tran Vuong, Ngoc Quan Pham, Hung Bui, Fatih Porikli, Dat Quoc Nguyen·· 11 小时前AI 评分38
CORE：面向深度研究的粗到细搜索与上下文管理框架
CORE: Coarse-to-Fine Search with Context Management for Deep Research
AI 导读
CORE 是一个免训练框架，将粗到细搜索与上下文管理结合，在 Tongyi DeepResearch 和 OpenResearcher 的受控闭集对比中，跨三个智能体模型和三个基准（BrowseComp-Plus、BrowseComp-Wikipedia、BrowseComp-Plus-CM）取得 SOTA 答案准确率与证据召回率，语料规模最高达 553M 文档。
正文 · 原文
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 give enough context for reliable semantic matching. But the returned evidence should be short, because every observation stays in the agent's context for the rest of the trajectory. We introduce CORE, a training-free harness that combines coarse-to-fine search with context management. CORE retrieves passages with a dense retriever. It then reuses the token-level similarities from a late-interaction reranker to return only the most relevant snippet from each passage. Context management lets the agent expand the context around sources it has already retrieved and suppresses repeated snippets. In controlled closed-search comparisons with the Tongyi DeepResearch and OpenResearcher harnesses, CORE achieves state-of-the-art answer accuracy and evidence recall across three agent models and three benchmarks (BrowseComp-Plus, BrowseComp-Wikipedia and BrowseComp-Plus-CM), on corpora containing up to 553M documents.
| Comments: | 24 pages |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2611.07859 [cs.CL] |
| (or arXiv:2611.07859v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07859 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hoang Tran Vuong [view email]
[v1]
Thu, 5 Nov 2026 11:36:19 UTC (952 KB)
来源：arXiv cs.CL · arxiv.org