Autonomous Scientific Discovery

Overview

The field studies how AI can move beyond answering questions to uncovering patterns, mechanisms, equations, and useful experiments across mathematics, physics, biology, and materials science. Approaches include symbolic regression and sparse equation identification, active learning and Bayesian experiment selection, and LLM-based agents that coordinate coding, simulation, literature review, or laboratory work. Evaluation increasingly uses executable benchmarks, held-out data, formal proofs, and experimental validation to check both results and the evidence behind them. Systems can handle well-specified workflows, but open-ended insight, reliable mechanism claims, identifiability, and reproducibility remain difficult, motivating stronger verification and human oversight.

Latest papers

CardsList

137 papers12 papers in the last four weeks, down 40% on the four weeks before. 0.1% of all new papers.

  1. Autonomous phase discovery

    Sep 27, 2026Shiyu Zhou, Yuxuan Zhang, Sebastian Wetzel +2Differentiable ProgrammingAutonomous Scientific Discovery

  2. ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds

    Sep 24, 2026Ming Zhang, Zhenghao Xiang, Peizhong Gao +17AI Agent EvaluationAI Agent Benchmarks

  3. Divergent strategies and convergent outcomes in autonomous materials discovery

    Sep 21, 2026Jihan KimAutonomous Scientific DiscoveryAutonomous Research Agents

  4. ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

    Sep 17, 2026Jaehyun Nam, Jinsung Yoon, Yanzhou Pan +4Scientific Hypothesis GenerationMulti-Agent Systems

  5. Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents

    Sep 16, 2026Izumi Takahara, Kazunori Nishio, Akira Aiba +4LLM Agent Skill LearningAutonomous Scientific Discovery

  6. LabAgent: Customize Any Research Hubs for Scientific Discoveries Using AI Agents

    Sep 11, 2026Lei Liu, Yikun Zhang, Jialin Chen +7LLM Agent HarnessesScientific Reproducibility

  7. Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval

    Sep 11, 2026Junghyun Min, Huseyin Uzunalioglu, Mohamed TrabelsiHuman-in-the-Loop AIAutonomous Scientific Discovery

  8. Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation

    Sep 10, 2026Dong Li, Sixuan Mi, Zihao Ye +10Agentic ReasoningAutonomous Scientific Discovery

  9. SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

    Sep 8, 2026Yuqiao Tan, Shizhu He, Jun Zhao +1AI Agent EvaluationSparse Autoencoders

  10. AutoKD: Autonomous Knowledge Discovery

    Sep 6, 2026Qinwen Ge, Bo Ni, Haowei Fu +3AI Agents for Scientific DiscoveryAutonomous Scientific Discovery

  11. A computable representation of the physical laboratory enables verifiable workflows

    Sep 3, 2026Xiaobo Li, Luyao Ge, Xiaohui Li +8Robotic Laboratory AutomationAgentic Workflows

  12. Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

    Aug 31, 2026Xuehai Wang, Haowei Qin, Tongxin Liu +6Automatic Rubric GenerationAI Agent Evaluation

  13. Accelerating Scientific Research with Gemini in the Real-World

    Aug 27, 2026Samuel Schmidgall, Xiaokai Zhu, Marian Shaw +32AI for ScienceAutonomous Scientific Discovery

  14. HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning

    Aug 26, 2026Ziqing Qian, Jiaying Lei, Yifang Wang +1Scientific Hypothesis GenerationAutonomous Scientific Discovery

  15. Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

    Aug 24, 2026Stephen Chung, Wenyu Du, William J. WesleyMulti-Agent CollaborationMulti-Agent Systems

  16. AutoSR: Automatic Symbolic Regression by Searching Research States

    Aug 17, 2026Kejia Zhang, Youran Sun, Xinyu Ren +2Symbolic RegressionAutonomous Scientific Discovery

  17. The Past and Future of AI Scientists

    Aug 14, 2026Ross D. KingAutonomous Scientific DiscoveryAutonomous Experimentation

  18. OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

    Aug 13, 2026Bobo Li, Hao Fei, Tianjie Ju +2AI Agents for Scientific DiscoveryScientific Discovery

  19. POMDPs for Autonomous Science Exploration

    Aug 4, 2026Daniel Guirguis, Nathan Wallace, Hanna Kurniawati +1Belief-Space PlanningAI for Science

  20. Towards a new paradigm of scientific discovery with socialized artificial intelligence

    Aug 3, 2026Xinjie Yao, Xingxin Xu, Xiyuan Gao +21AI for ScienceHuman-in-the-Loop AI

  21. Verifier-Guided Model Discovery for Physical Dynamical Systems with Pretrained Symbolic Transformers

    Aug 1, 2026Farbod Faraji, Francesco BelardinelliNonlinear System IdentificationAutonomous Scientific Discovery