mlsanityData to 14 Oct 2026

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

arXiv 2408.06292 ↗First posted 12 Aug 2024cs.AI cs.CL cs.LGcited by 1,071

Not on the map. Why?

Cited by 447 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aides to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific process. This paper presents the first comprehensive framework for fully automatic scientific discovery, enabling frontier large language models to perform research independently and communicate their findings. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its findings by writing a full scientific paper, and then runs a simulated review process for evaluation. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community. We demonstrate its versatility by applying it to three distinct subfields of machine learning: diffusion modeling, transformer-based language modeling, and learning dynamics. Each idea is implemented and developed into a full paper at a cost of less than 15 per paper. To evaluate the generated papers, we design and validate an automated reviewer, which we show achieves near-human performance in evaluating paper scores. The AI Scientist can produce papers that exceed the acceptance threshold at a top machine learning conference as judged by our automated reviewer. This approach signifies the beginning of a new era in scientific discovery in machine learning: bringing the transformative benefits of AI agents to the entire research process of AI itself, and taking us closer to a world where endless affordable creativity and innovation can be unleashed on the world's most challenging problems. Our code is open-sourced at https://github.com/SakanaAI/AI-Scientist

Key facts. Cited by 1,071 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Aug 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 71; 2025: 346; 2026: 654.

1,071 papers.

Sort:

By area:

  1. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  2. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
  3. 2024Automated Design of Agentic Systemscited by 407
  4. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
  5. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
  6. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
  7. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discoverycited by 235
  8. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Taskscited by 232
  9. 2025Video models are zero-shot learners and reasonerscited by 220
  10. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  11. 2024RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human expertscited by 175
  12. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 148
38 more
  1. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 132
  2. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
  3. 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 124
  4. 2024CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmarkcited by 123
  5. 2024Automatically Interpreting Millions of Features in Large Language Modelscited by 113
  6. 2025Agentic Large Language Models, a surveycited by 108
  7. 2026Self-Harness: Harnesses That Improve Themselvescited by 107
  8. 2025DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Processcited by 100
  9. 2025AI-Researcher: Autonomous Scientific Innovationcited by 100
  10. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 98
  11. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 97
  12. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoningcited by 94
  13. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  14. 2025Kosmos: An AI Scientist for Autonomous Discoverycited by 92
  15. 2025BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biologycited by 89
  16. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directionscited by 77
  17. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  18. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 72
  19. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 72
  20. 2025LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Modelscited by 71
  21. 2025Paper2Code: Automating Code Generation from Scientific Papers in Machine Learningcited by 70
  22. 2024Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent Systemcited by 68
  23. 2024MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agentscited by 67
  24. 2025Deep Research: A Survey of Autonomous Research Agentscited by 66
  25. 2024OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviewscited by 65
  26. 2025PaSa: An LLM Agent for Comprehensive Academic Paper Searchcited by 64
  27. 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Researchcited by 64
  28. 2026PostTrainBench: Can LLM Agents Automate LLM Post-Training?cited by 64
  29. 2025DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressivelycited by 63
  30. 2025Robin: A multi-agent system for automating scientific discoverycited by 62
  31. 2025LLM Agents for Education: Advances and Applicationscited by 59
  32. 2024Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideascited by 57
  33. 2025DataSciBench: An LLM Agent Benchmark for Data Sciencecited by 57
  34. 2025Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimizationcited by 56
  35. 2024Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Reviewcited by 53
  36. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflowscited by 52
  37. 2026CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discoverycited by 52
  38. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 51

50 most cited of 1,071 All 1,071 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Towards End-to-End Automation of AI Research
  2. 2026Contemporary AI lacks the imagination to diverge or negate in science
  3. 2025AI4Research: A Survey of Artificial Intelligence for Scientific Research
  4. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
  5. 2025Virtuous Machines: Towards Artificial General Science
  6. 2025SR-Scientist: Scientific Equation Discovery With Agentic AI
  7. 2025aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists
  8. 2026AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models