mlsanityData to 7 Oct 2026

AI-Researcher: Autonomous Scientific Innovation

arXiv 2505.18705 ↗First posted 24 May 2025cs.AIcited by 88

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

The powerful reasoning capabilities of Large Language Models (LLMs) in mathematics and coding, combined with their ability to automate complex tasks through agentic frameworks, present unprecedented opportunities for accelerating scientific innovation. In this paper, we introduce AI-Researcher, a fully autonomous research system that transforms how AI-driven scientific discovery is conducted and evaluated. Our framework seamlessly orchestrates the complete research pipeline--from literature review and hypothesis generation to algorithm implementation and publication-ready manuscript preparation--with minimal human intervention. To rigorously assess autonomous research capabilities, we develop Scientist-Bench, a comprehensive benchmark comprising state-of-the-art papers across diverse AI research domains, featuring both guided innovation and open-ended exploration tasks. Through extensive experiments, we demonstrate that AI-Researcher achieves remarkable implementation success rates and produces research papers that approach human-level quality. This work establishes new foundations for autonomous scientific innovation that can complement human researchers by systematically exploring solution spaces beyond cognitive limitations.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 18 of its 27 references that are in the map. First posted on arXiv 24 May 2025.

Builds on

18 of 27 references.

References · 18

  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  3. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  4. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  5. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  6. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 375
  7. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  8. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  9. 2023SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Modelscited by 246
  10. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 200
  11. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 150
  12. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 142
6 more
  1. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
  2. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 94
  3. 2024AgentReview: Exploring Peer Review Dynamics with LLM Agentscited by 92
  4. 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solvingcited by 82
  5. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 49
  6. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challengescited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 74.

88 papers.

Sort:

By area:

  1. 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 48
  2. 2026PostTrainBench: Can LLM Agents Automate LLM Post-Training?cited by 45
  3. 2025Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agentscited by 42
  4. 2025ReportBench: Evaluating Deep Research Agents via Academic Survey Taskscited by 34
  5. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  6. 2026Towards Execution-Grounded Automated AI Researchcited by 19
  7. 2026ResearchGym: Evaluating Language Model Agents on Real-World AI Researchcited by 15
  8. 2026Toward Autonomous Long-Horizon Engineering for ML Researchcited by 15
  9. 2026ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidencecited by 15
  10. 2025DeepCode: Open Agentic Codingcited by 14
  11. 2026Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memorycited by 13
  12. 2025Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Papercited by 10
38 more
  1. 2026AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discoverycited by 10
  2. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  3. 2025A Survey of AI Scientistscited by 9
  4. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 9
  5. 2025Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automationcited by 8
  6. 2026QUEST: Training Frontier Deep Research Agents with Fully Synthetic Taskscited by 8
  7. 2026AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systemscited by 8
  8. 2026Can AI agents conduct open-ended AI research? Early evidence from two case studiescited by 7
  9. 2026Principle-Evolvable Scientific Discovery via Uncertainty Minimizationcited by 6
  10. 2026InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problemcited by 6
  11. 2026TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Explorationcited by 6
  12. 2026FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamicscited by 6
  13. 2025K-Dense Analyst: Towards Fully Automated Scientific Analysiscited by 5
  14. 2026Towards a Medical AI Scientistcited by 5
  15. 2026Benchmark Everything Everywhere All at Oncecited by 5
  16. 2026DeepInnovator: Triggering the Innovative Capabilities of LLMscited by 4
  17. 2026Sanity Checks for Agentic Data Sciencecited by 4
  18. 2026NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automationcited by 4
  19. 2026GEAR: Genetic AutoResearch for Agentic Code Evolutioncited by 4
  20. 2026AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecyclecited by 4
  21. 2026Training AI Scientists to Replicate Researchcited by 4
  22. 2026AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agentscited by 3
  23. 2026S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agentscited by 3
  24. 2025FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Datacited by 2
  25. 2025AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agentcited by 2
  26. 2025MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Modelscited by 2
  27. 2026FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Explorationcited by 2
  28. 2026Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Taskscited by 2
  29. 2026ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgmentcited by 2
  30. 2026Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Noveltycited by 2
  31. 2025From AutoRecSys to AutoRecLab: A Call to Build, Evaluate, and Govern Autonomous Recommender-Systems Research Labscited by 1
  32. 2026Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Predictioncited by 1
  33. 2025HybridQuestion: Human-AI Collaboration for Identifying High-Impact Research Questionscited by 1
  34. 2026SciDER: Scientific Data-centric End-to-end Researchercited by 1
  35. 2026IntentGrasp: A Comprehensive Benchmark for Intent Understandingcited by 1
  36. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1
  37. 2026How Post-Training Shapes Biological Reasoning Modelscited by 1
  38. 2026Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agentscited by 1

50 most cited of 88 All 88 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
  2. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
  3. 2026Towards End-to-End Automation of AI Research
  4. 2026Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
  5. 2025AI4Research: A Survey of Artificial Intelligence for Scientific Research
  6. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
  7. 2025Virtuous Machines: Towards Artificial General Science
  8. 2026Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery