mlsanityData to 14 Oct 2026

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

arXiv 2411.14199 ↗First posted 21 Nov 2024cs.CL cs.AI cs.DLcited by 72

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

Abstract (arXiv)

Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscience, and biomedicine. On ScholarQABench, OpenScholar-8B outperforms GPT-4o by 5% and PaperQA2 by 7% in correctness, despite being a smaller, open model. While GPT4o hallucinates citations 78 to 90% of the time, OpenScholar achieves citation accuracy on par with human experts. OpenScholar's datastore, retriever, and self-feedback inference loop also improves off-the-shelf LMs: for instance, OpenScholar-GPT4o improves GPT-4o's correctness by 12%. In human evaluations, experts preferred OpenScholar-8B and OpenScholar-GPT4o responses over expert-written ones 51% and 70% of the time, respectively, compared to GPT4o's 32%. We open-source all of our code, models, datastore, data and a public demo.

Key facts. Cited by 72 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 0 of its 6 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

0 of 6 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 35; 2026: 35.

72 papers.

Sort:

By area:

  1. 2025DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Processcited by 100
  2. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 77
  3. 2025Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generationcited by 58
  4. 2025Flipping the Dialogue: Training and Evaluating User Language Modelscited by 58
  5. 2025SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writingcited by 49
  6. 2025ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubricscited by 49
  7. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generationcited by 44
  8. 2025ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquirycited by 32
  9. 2025Characterizing Deep Research: A Benchmark and Formal Definitioncited by 30
  10. 2026Towards Execution-Grounded Automated AI Researchcited by 28
  11. 2025Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmarkcited by 21
  12. 2025SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Taskscited by 20
38 more
  1. 2026Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Servingcited by 20
  2. 2025IRIS: Interactive Research Ideation System for Accelerating Scientific Discoverycited by 19
  3. 2025All That Glitters is Not Novel: Plagiarism in AI Generated Researchcited by 18
  4. 2025SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generationcited by 12
  5. 2026RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewardscited by 12
  6. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  7. 2024State Space Models are Strong Text Rerankerscited by 10
  8. 2025ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citationscited by 10
  9. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challengescited by 10
  10. 2025TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrievalcited by 9
  11. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 9
  12. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  13. 2026InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problemcited by 8
  14. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  15. 2026DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Reviewcited by 7
  16. 2025Distillation versus Contrastive Learning: How to Train Your Rerankerscited by 6
  17. 2025Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insightscited by 6
  18. 2026PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVRcited by 6
  19. 2025Retrieval-augmented systems can be dangerous medical communicatorscited by 5
  20. 2025ScienceMeter: Tracking Scientific Knowledge Updates in Language Modelscited by 4
  21. 2025TusoAI: Agentic Optimization for Scientific Methodscited by 4
  22. 2025SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literaturecited by 4
  23. 2025Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMscited by 3
  24. 2025Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpuscited by 3
  25. 2025HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Servingcited by 3
  26. 2025Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answerscited by 3
  27. 2025In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysiscited by 2
  28. 2025From Queries to Criteria: Understanding How Astronomers Evaluate LLMscited by 2
  29. 2026Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attributioncited by 2
  30. 2026Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Userscited by 2
  31. 2026AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Modelcited by 2
  32. 2026Improving Attributed Long-form Question Answering with Intent Awarenesscited by 2
  33. 2026Self-Optimizing Multi-Agent Systems for Deep Researchcited by 2
  34. 2026FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verificationcited by 2
  35. 2026Towards Recursive Self-Evolving Agentic Literature Retrievalcited by 2
  36. 2026Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completenesscited by 2
  37. 2026Training Documents Reranker with Search Rubrics for Deep Research Agentcited by 2
  38. 2025Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarizationcited by 1

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
  2. 2025Patience is all you need! An agentic system for performing scientific literature review
  3. 2025SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search
  4. 2026LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering
  5. 2025SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs
  6. 2023Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning
  7. 2025SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning
  8. 2024OpenResearcher: Unleashing AI for Accelerated Scientific Research