mlsanityData to 14 Oct 2026

IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review

arXiv 2604.22861 ↗First posted 23 Apr 2026cs.IR cs.AI cs.LGcited by 2

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Scientific research relies on accurate information retrieval from literature to support analytical decisions. In this work, we introduce a new task, INformation reTRieval through literAture reVIEW (IntraView), which aims to automate fine-grained information retrieval faithfully grounded in the provided content in response to research-driven queries, and propose IntrAgent, an LLM-based agent that addresses this challenging task. In particular, IntrAgent is designed to mimic human behaviors when reading literature for information retrieval -- identifying relevant sections and then iteratively extracting key details to refine the retrieved information. It follows a two-stage pipeline: a Section Ranking stage that prioritizes relevant literature sections through structural-knowledge-enabled reasoning, and an Iterative Reading stage that continuously extracts details and synthesizes them into concise, contextually grounded answers. To support rigorous evaluation, we introduce IntraBench, a new benchmark consisting of 315 test instances built from expert-authored questions paired with literature spanning five STEM domains. Across seven backbone LLMs, IntrAgent achieves on average 13.2% higher cross-domain accuracy than state-of-the-art RAG and research-agent baselines.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 35 of its 87 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

35 of 87 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review30 Jul
  2. 2025Agent Laboratory: Using LLM Agents as Research Assistants8 Jan
  3. 2024Language agents achieve superhuman synthesis of scientific knowledge10 Sep
  4. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Research8 Dec

Other references · 31

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  3. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  4. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  5. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  8. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  9. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  10. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  11. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  12. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
19 more
  1. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  2. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  3. 2018CoQA: A Conversational Question Answering Challengecited by 683
  4. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  5. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 486
  6. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  7. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  8. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 108
  9. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  10. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
  11. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  12. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 71
  13. 2024LitLLM: A Toolkit for Scientific Literature Reviewcited by 63
  14. 2024HoneyComb: A Flexible LLM-Based Agent System for Materials Sciencecited by 57
  15. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  16. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  17. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphscited by 38
  18. 2024HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wildcited by 27
  19. 2024Efficient Encoder-Decoder Transformer Decoding for Decomposable Taskscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusioncited by 4
  2. 2026LinePilot Digitizer: Line-Plot Recovery with Manual and Automatic Calibrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning
  2. 2025Patience is all you need! An agentic system for performing scientific literature review
  3. 2026TechRAG: Evidence-Gated Multimodal Agentic RAG for Technical Literature Reasoning
  4. 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
  5. 2026iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics
  6. 2026ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments
  7. 2026Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
  8. 2025Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration