# OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

arXiv: https://arxiv.org/abs/2411.14199 · HTML: https://mlsanity.com/paper/2411.14199/

## 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.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Built on by (most cited first, 30 of 72)

- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation](https://mlsanity.com/paper/2502.14846/) (2025)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics](https://mlsanity.com/paper/2509.00496/) (2025)
- [MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.00332/) (2024)
- [ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry](https://mlsanity.com/paper/2507.16280/) (2025)
- [Characterizing Deep Research: A Benchmark and Formal Definition](https://mlsanity.com/paper/2508.04183/) (2025)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark](https://mlsanity.com/paper/2509.26574/) (2025)
- [SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks](https://mlsanity.com/paper/2507.01001/) (2025)
- [Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving](https://mlsanity.com/paper/2603.18897/) (2026)
- [IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery](https://mlsanity.com/paper/2504.16728/) (2025)
- [All That Glitters is Not Novel: Plagiarism in AI Generated Research](https://mlsanity.com/paper/2502.16487/) (2025)
- [SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation](https://mlsanity.com/paper/2506.12689/) (2025)
- [RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards](https://mlsanity.com/paper/2605.10899/) (2026)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [State Space Models are Strong Text Rerankers](https://mlsanity.com/paper/2412.14354/) (2024)
- [ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations](https://mlsanity.com/paper/2504.00824/) (2025)
- [Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges](https://mlsanity.com/paper/2508.00217/) (2025)
- [TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval](https://mlsanity.com/paper/2502.20969/) (2025)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems](https://mlsanity.com/paper/2503.01424/) (2025)
- [InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem](https://mlsanity.com/paper/2602.14367/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review](https://mlsanity.com/paper/2604.09590/) (2026)
- [Distillation versus Contrastive Learning: How to Train Your Rerankers](https://mlsanity.com/paper/2507.08336/) (2025)
- [Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights](https://mlsanity.com/paper/2511.06738/) (2025)
- [PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR](https://mlsanity.com/paper/2601.18207/) (2026)

## 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.