---
title: "CORE: Coarse-to-Fine Search with Context Management for Deep Research"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07859v1"
permalink: "https://feed.astralor.com/items/itm_d16a1f888a8c23e0e491f2b8"
published: "2026-11-05T11:36:19.000Z"
score: 57
channel: "ai"
tags: ["AI Agent","CORE","Coarse-to-Fine Search","Context Management","Deep Research Deep","They","Search","Deep"]
---

# CORE: Coarse-to-Fine Search with Context Management for Deep Research

## 速览

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 passa…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d16a1f888a8c23e0e491f2b8