mlsanityData to 14 Oct 2026

PaperQA: Retrieval-Augmented Generative Agent for Scientific Research

arXiv 2312.07559 ↗First posted 8 Dec 2023cs.CL cs.AI cs.LGcited by 149

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) generalize well across language tasks, but suffer from hallucinations and uninterpretability, making it difficult to assess their accuracy without ground-truth. Retrieval-Augmented Generation (RAG) models have been proposed to reduce hallucinations and provide provenance for how an answer was generated. Applying such models to the scientific literature may enable large-scale, systematic processing of scientific knowledge. We present PaperQA, a RAG agent for answering questions over the scientific literature. PaperQA is an agent that performs information retrieval across full-text scientific articles, assesses the relevance of sources and passages, and uses RAG to provide answers. Viewing this agent as a question answering model, we find it exceeds performance of existing LLMs and LLM agents on current science QA benchmarks. To push the field closer to how humans perform research on scientific literature, we also introduce LitQA, a more complex benchmark that requires retrieval and synthesis of information from full-text scientific papers across the literature. Finally, we demonstrate PaperQA's matches expert human researchers on LitQA.

Key facts. Cited by 149 papers in the map (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 55 of its 78 references that are in the map. First posted on arXiv 8 Dec 2023.

Builds on

55 of 78 references.

References · 55

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  12. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
38 more
  1. 2017Billion-scale similarity search with GPUscited by 2,497
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  4. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  5. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  6. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  7. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  8. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  9. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  11. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  13. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  14. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  15. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  16. 2023Large Language Models as Optimizerscited by 864
  17. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  18. 2022Galactica: A Large Language Model for Sciencecited by 744
  19. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  20. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  21. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 538
  22. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 517
  23. 2023Active Retrieval Augmented Generationcited by 516
  24. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
  25. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  26. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  27. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  28. 2022Teaching language models to support answers with verified quotescited by 292
  29. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 156
  30. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  31. 2022SciRepEval: A Multi-Format Benchmark for Scientific Document Representationscited by 129
  32. 2023Almanac: Retrieval-Augmented Language Models for Clinical Medicinecited by 123
  33. 2023The Semantic Scholar Open Data Platformcited by 118
  34. 2021Can Language Models be Biomedical Knowledge Bases?cited by 83
  35. 2020BioMegatron: Larger Biomedical Domain Language Modelcited by 76
  36. 2023Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare deliverycited by 30
  37. 2018Over-Optimization of Academic Publishing Metrics: Observing Goodhart's Law in Actioncited by 22
  38. 2023Improving Retrieval-Augmented Large Language Models via Data Importance Learningcited by 17

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 30; 2025: 58; 2026: 59.

149 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 509
  3. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
  4. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  5. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  6. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 169
  7. 2024Language agents achieve superhuman synthesis of scientific knowledgecited by 137
  8. 2024Empowering Biomedical Discovery with AI Agentscited by 118
  9. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 99
  10. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  11. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLcited by 87
  12. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 72
38 more
  1. 2025LLM Agents for Education: Advances and Applicationscited by 59
  2. 2024BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experimentscited by 53
  3. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflowscited by 52
  4. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  5. 2024CiteME: Can Language Models Accurately Cite Scientific Claims?cited by 48
  6. 2026Code as Agent Harnesscited by 47
  7. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 46
  8. 2024DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaborationcited by 44
  9. 2024BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrieverscited by 38
  10. 2025EXP-Bench: Can AI Conduct AI Research Experiments?cited by 37
  11. 2024Are large language models superhuman chemists?cited by 34
  12. 2025Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoningcited by 33
  13. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generationcited by 31
  14. 2025Single-agent or Multi-agent Systems? Why Not Both?cited by 29
  15. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  16. 2026Towards Execution-Grounded Automated AI Researchcited by 28
  17. 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 27
  18. 2024Aviary: training language agents on challenging scientific taskscited by 26
  19. 2025RAG-Enhanced Collaborative LLM Agents for Drug Discoverycited by 18
  20. 2024Quantum Many-Body Physics Calculations with Large Language Modelscited by 17
  21. 2026BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agentscited by 16
  22. 2023Agent-based Learning of Materials Datasets from Scientific Literaturecited by 15
  23. 2024Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorizationcited by 15
  24. 2025How Far Are AI Scientists from Changing the World?cited by 15
  25. 2025PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literaturecited by 15
  26. 2025MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Sciencecited by 15
  27. 2025Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Modelscited by 14
  28. 2025Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Surveycited by 13
  29. 2024SurveyAgent: A Conversational System for Personalized and Efficient Research Surveycited by 11
  30. 2025Spark: A System for Scientifically Creative Idea Generationcited by 11
  31. 2025A Survey of AI Scientistscited by 11
  32. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  33. 2024VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilitiescited by 10
  34. 2025Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool usecited by 10
  35. 2026NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?cited by 10
  36. 2025ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrievalcited by 9
  37. 2025Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Modelscited by 9
  38. 2025Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterizationcited by 9

50 most cited of 149 All 149 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation
  2. 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
  3. 2026MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
  4. 2026SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
  5. 2026Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning
  6. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
  7. 2026Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
  8. 2026Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)