mlsanityData to 7 Oct 2026

LLM4SR: A Survey on Large Language Models for Scientific Research

arXiv 2501.04306 ↗First posted 8 Jan 2025cs.CL cs.DLcited by 81

Not on the map. Why?

Abstract (arXiv)

In recent years, the rapid advancement of Large Language Models (LLMs) has transformed the landscape of scientific research, offering unprecedented support across various stages of the research cycle. This paper presents the first systematic survey dedicated to exploring how LLMs are revolutionizing the scientific research process. We analyze the unique roles LLMs play across four critical stages of research: hypothesis discovery, experiment planning and implementation, scientific writing, and peer reviewing. Our review comprehensively showcases the task-specific methodologies and evaluation benchmarks. By identifying current challenges and proposing future research directions, this survey not only highlights the transformative potential of LLMs, but also aims to inspire and guide researchers and practitioners in leveraging LLMs to advance scientific inquiry. Resources are available at the following repository: https://github.com/du-nlp-lab/LLM4SR

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jan 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 46; 2026: 35.

81 papers.

Sort:

By area:

  1. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  2. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  3. 2025ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decompositioncited by 57
  4. 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Researchcited by 57
  5. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  6. 2025Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Datacited by 35
  7. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 34
  8. 2025LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Researchcited by 29
  9. 2025PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifiercited by 28
  10. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 25
  11. 2025The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systemscited by 24
  12. 2025Sparks of Science: Hypothesis Generation Using Structured Paper Datacited by 22
38 more
  1. 2026PaperBanana: Automating Academic Illustration for AI Scientistscited by 22
  2. 2025All That Glitters is Not Novel: Plagiarism in AI Generated Researchcited by 17
  3. 2025RExBench: Can coding agents autonomously implement AI research extensions?cited by 17
  4. 2025How Far Are AI Scientists from Changing the World?cited by 15
  5. 2025SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agentscited by 14
  6. 2025CacheClip: Accelerating RAG with Effective KV Cache Reusecited by 14
  7. 2025Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agentscited by 13
  8. 2025MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Searchcited by 13
  9. 2025What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practicescited by 11
  10. 2025InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation Systemcited by 11
  11. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  12. 2025LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Modelscited by 9
  13. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  14. 2025A Survey of AI Scientistscited by 9
  15. 2026ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciencescited by 9
  16. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 9
  17. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  18. 2025PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensionscited by 8
  19. 2025GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Librariescited by 8
  20. 2025EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Modelscited by 7
  21. 2025AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Sciencecited by 6
  22. 2025PriM: Principle-Inspired Material Discovery through Multi-Agent Collaborationcited by 6
  23. 2025MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedbackcited by 6
  24. 2025AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveyscited by 6
  25. 2025ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoningcited by 5
  26. 2025Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoningcited by 4
  27. 2026DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttalcited by 4
  28. 2025ScienceMeter: Tracking Scientific Knowledge Updates in Language Modelscited by 3
  29. 2025Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extractioncited by 3
  30. 2026MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barriercited by 3
  31. 2026PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Qualitycited by 3
  32. 2025Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganographycited by 2
  33. 2025ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflowscited by 2
  34. 2026ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Reviewcited by 2
  35. 2026SciMDR: Advancing Scientific Multimodal Document Reasoningcited by 2
  36. 2026When AI reviews science: Can we trust the referee?cited by 2
  37. 2026Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contextscited by 2
  38. 2025Recent Advances and Future Directions in Literature-Based Discoverycited by 1

50 most cited of 81 All 81 (JSON)