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

Hoang Tran Vuong; Ngoc Quan Pham; Hung Bui; Fatih Porikli; Dat Quoc Nguyen

cs.CLNov 5, 2026

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

Authors: Hoang Tran Vuong, Ngoc Quan Pham, Hung Bui, Fatih Porikli, Dat Quoc Nguyen

Organizations: Qualcomm AI Research* · Qualcomm Vietnam Company Limited

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.

Figures & tables

Figure 1: Overview of CORE. Coarse retrieval and fine-grained reranking select a broad selection of passages and fine-grained evidence as passage snippets within such selection. The agent can request more thorough context via context expansion, while cross-search deduplication replaces repeated snippets with compact references. The gathered context allows the agent to decide, whether to continue the search, or to finalize the answer to the original question. The current sub-query can also be input directly into the context expansion to find more information in the previously visited passages without triggering the search tool.

(a) BrowseComp-Plus
Agent model	Harness	Answer accuracy $\uparrow$	Evidence recall $\uparrow$	Peak context $\downarrow$	Tokens/search $\downarrow$	Search calls
GPT-5.4	Tongyi DeepResearch	84.70	81.53	93,500	26,316	4.5
	OpenResearcher	91.45	89.55	35,323	3,690	12.1
	CORE (ours)	94.94	94.47	42,732	3,365	16.8
Tongyi-DeepResearch- 30B-A3B	Tongyi DeepResearch	65.66	68.74	80,771	15,259	5.2
	OpenResearcher	79.88	83.99	41,912	1,447	20.6

Table 1: Main comparison results. Answer accuracy and evidence recall are in percent. Peak context is the median, over questions, of the maximum context length in tokens. Tokens/search is the mean number of tokens returned per search call, summed over all subqueries. Search calls is the mean number of search calls per question. Token counts are comparable only within the same agent model. Arrows show the preferred direction, and bold marks the best value in each of these columns within each model–benchmark group. We find that Tongyi-DeepResearch-30B-A3B, using the original Tongyi DeepResearch harness with document-level retrieval based on AgentIR-4B, achieves 63.13% on BrowseComp-Plus, which is lower than the 65.66% achieved by our current passage-level retrieval setup. On BrowseComp-Plus, Jiang et al. (2026) report an evidence recall of 38.1% for Tongyi-DeepResearch-30B-A3B, whereas their Harness-1 (20B) reported the evidence recall at 58.4%.

Configuration	Answer accuracy (%) $\uparrow$
No tools	4.58
Coarse retrieval only	62.61
Coarse-to-fine search tool only	70.84
Full CORE	80.12

Table 2: Component analysis on BrowseComp-Plus with Tongyi-DeepResearch-30B-A3B. All tool-enabled configurations share the AgentIR-4B passage index, inference settings, and context budget.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Agent model
Answer accuracy (%) $\uparrow$
Tongyi-DeepResearch-30B-A3B	80.12
OpenResearcher-30B-A3B	62.41

Appendix

Table 3: Deep research agents evaluated with CORE on BrowseComp-Plus. Accuracy is computed over all 830 questions; empty answers receive no credit. Bold marks the higher accuracy.

Agentic Retrieval

Agentic retrieval lets AI agents iteratively search, inspect, and verify evidence to answer complex information needs.

See all 103 papers

Argus: Evidence Assembly for Scalable Deep Research Agents
May 15, 2026Zhen Zhang, Liangcai Su, Zhuo Chen +7Multi-Agent LLM Systems Tool-Augmented Language Model Agents
MiroMind AI
AgentIR: Reasoning-Aware Retrieval for Deep Research Agents
Mar 4, 2026Zijian Chen, Xueguang Ma, Shengyao Zhuang +3Agentic Retrieval Dense Retrieval
University of Waterloo · University of Queensland · Carnegie Mellon University
QRAE: Query-Relevant Attention Entropy for Context Compression in DeepSearch Agents
Nov 5, 2026Yingjie Tan, Haiquan Qiu, Quanming Yao +3LLM Context Compression Context Compaction for LLM Agents
Tsinghua University · Huawei Technologies Ltd.

May 15, 2026J/K move · Enter open · S save

Argus: Evidence Assembly for Scalable Deep Research Agents

Zhen Zhang, Liangcai Su, Zhuo Chen, Xiang Lin+6

MiroMind AI

Multi-Agent LLM Systems Tool-Augmented Language Model Agents Deep Research Agents Agentic Search Agentic Reasoning

Open paper AskPDF arXiv

Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel search and aggregation. Yet deep research answers are composed of complementary pieces of evidence, which parallel rollouts often duplicate rather than complete, yielding diminishing returns while pushing the aggregation context toward the model's limit. We propose Argus, an agentic system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces, rather than brute forcing the whole answer in parallel. The Searcher collects evidence traces for a given sub-query through ReAct-style interaction. The Navigator maintains a shared evidence graph, verifying which pieces are still missing, dispatching Searchers to gather them, and reasoning over the completed graph to produce a source-traced final answer. We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent. The resulting Navigator supports rollouts with a single Searcher or many in parallel without retraining. With both Searcher and Navigator built on a 35B-A3B MoE backbone, Argus gains 5.5 points with a single Searcher and 12.7 points with 8 parallel Searchers, averaged over eight benchmarks. With 64 Searchers it reaches 86.2 on BrowseComp, surpassing every proprietary agent we benchmark, while the Navigator's reasoning context stays under 21.5K tokens.

Abstract

Agentic Retrieval

Explore similar work

Argus: Evidence Assembly for Scalable Deep Research Agents

AgentIR: Reasoning-Aware Retrieval for Deep Research Agents

QRAE: Query-Relevant Attention Entropy for Context Compression in DeepSearch Agents