SAGE: Benchmarking and Improving Retrieval for Deep Research Agents

• URL: http://arxiv.org/abs/2602.05975v2
• Date: Fri, 06 Feb 2026 04:59:37 GMT
• Title: SAGE: Benchmarking and Improving Retrieval for Deep Research Agents
• Authors: Tiansheng Hu, Yilun Zhao, Canyu Zhang, Arman Cohan, Chen Zhao,
• Abstract summary: We introduce SAGE, a benchmark for scientific literature retrieval comprising 1,200 queries across four scientific domains, with a 200,000 paper retrieval corpus.<n>We evaluate six deep research agents and find that all systems struggle with reasoning-intensive retrieval.<n> BM25 significantly outperforms LLM-based retrievers by approximately 30%, as existing agents generate keyword-oriented sub-queries.
• Score: 60.53966065867568
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions or reasoning. This raises a critical question: can LLM-based retrievers effectively contribute to deep research agent workflows? To investigate this, we introduce SAGE, a benchmark for scientific literature retrieval comprising 1,200 queries across four scientific domains, with a 200,000 paper retrieval corpus. We evaluate six deep research agents and find that all systems struggle with reasoning-intensive retrieval. Using DR Tulu as backbone, we further compare BM25 and LLM-based retrievers (i.e., ReasonIR and gte-Qwen2-7B-instruct) as alternative search tools. Surprisingly, BM25 significantly outperforms LLM-based retrievers by approximately 30%, as existing agents generate keyword-oriented sub-queries. To improve performance, we propose a corpus-level test-time scaling framework that uses LLMs to augment documents with metadata and keywords, making retrieval easier for off-the-shelf retrievers. This yields 8% and 2% gains on short-form and open-ended questions, respectively.

Related papers

• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent [74.10138164281618]
  BrowseComp-Plus is a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus.<n>This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods.
  arXiv  Detail & Related papers  (2025-08-08T17:55:11Z)
• Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion [0.0]
  Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion.<n>We introduce a novel fusion ranking framework, Exp4Fuse, which enhances the performance of sparse retrievers.
  arXiv  Detail & Related papers  (2025-06-05T08:44:34Z)
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning [50.419872452397684]
  Search-R1 is an extension of reinforcement learning for reasoning frameworks.<n>It generates search queries during step-by-step reasoning with real-time retrieval.<n>It improves performance by 41% (Qwen2.5-7B) and 20% (Qwen2.5-3B) over various RAG baselines.
  arXiv  Detail & Related papers  (2025-03-12T16:26:39Z)
• ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance [21.777817032607405]
  Large language models (LLMs) have demonstrated significant potential in enhancing dense retrieval through query augmentation.<n>In this work, we propose ExpandR, a unified LLM-augmented dense retrieval framework.<n> Experimental results on multiple benchmarks show that ExpandR consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-02-24T11:15:41Z)
• R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation [11.890598082534577]
  Retrieval augmented generation (RAG) has been applied in many scenarios to augment large language models (LLMs) with external documents provided by retrievers. This paper proposes R$2$AG, a novel enhanced RAG framework that incorporates Retrieval information into Retrieval Augmented Generation.
  arXiv  Detail & Related papers  (2024-06-19T06:19:48Z)
• SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation [50.26966969163348]
  Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG) Existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries. We propose Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm.
  arXiv  Detail & Related papers  (2024-06-17T06:48:31Z)
• Large Language Models are Strong Zero-Shot Retriever [89.16756291653371]
  We propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an LLM.
  arXiv  Detail & Related papers  (2023-04-27T14:45:55Z)
• Query2doc: Query Expansion with Large Language Models [69.9707552694766]
  The proposed method first generates pseudo- documents by few-shot prompting large language models (LLMs) query2doc boosts the performance of BM25 by 3% to 15% on ad-hoc IR datasets. Our method also benefits state-of-the-art dense retrievers in terms of both in-domain and out-of-domain results.
  arXiv  Detail & Related papers  (2023-03-14T07:27:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.