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

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

  1. Asking the right question is key to AI discovery in a chain of hypotheses

    Nov 15, 2026Hu CangAutonomous Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

  2. Vibe synthesis: hierarchical agentic decision-making for intent-driven multistep molecule synthesis

    Nov 12, 2026Jie Chen, Guikun Chen, Feng Wan +15Scientific Workflow AutomationAutonomous Research Agents

  3. Adaptive catalyst discovery emerges from composable scientific intelligence

    Nov 10, 2026Wentao Li, Qilong Cai, Qi Lei +21Autonomous Scientific DiscoveryMolecular Property Prediction

  4. SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery

    Nov 9, 2026Weimin Wu, Han LiuMulti-Agent SystemsAutonomous Scientific Discovery

  5. SplatLab: Autonomous Scientific Discovery for 3DGS Research

    Oct 21, 2026Seemandhar Jain, Manmohan ChandrakerAutonomous Research AgentsAutomated Algorithm Discovery

  6. Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures

    Oct 20, 2026Yujian Liu, Li An, Zelin He +5Autonomous Scientific DiscoveryMulti-Agent Collaboration

  7. OptScientist: Automated Discovery of Optimization Laws

    Oct 20, 2026Ma ZhenYao, Yue Liang, Jian-Qiao ZhuAutonomous Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

  8. Agentic discovery of interpretable car-following laws from multi-source trajectory data

    Oct 20, 2026Jiamei Xu, Jie Sun, Keshuang Tang +1Traffic Flow TheoryIntelligent Transportation Systems

  9. EvoSim: Learning to Model, Modeling to Learn

    Oct 8, 2026Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang +3Autonomous Scientific DiscoveryPhysics-Based Simulation

  10. Open-ended Scientific Discovery with Possibilistic Reasoning

    Oct 8, 2026Anita Yang, Siu Lun Chau, Tomoya Wakayama +2Possibility TheoryScientific Discovery

  11. SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code

    Oct 6, 2026Seemandhar Jain, Keshav Gupta, Manmohan ChandrakerCode Generation3D Gaussian Splatting

  12. Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station

    Oct 6, 2026Wenyu Du, Stephen ChungAutonomous Scientific DiscoveryAI Agent Evaluation

  13. GitSwarm: Decentralized Compounding Inference

    Oct 4, 2026Vedant Shah, Ankur Samanta, Paras Dahal +11Inference-Time ScalingMulti-Agent Collaboration

  14. ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe

    Oct 2, 2026Weihan Li, Tianshi Zheng, Yangqiu Song +2Autonomous Scientific DiscoveryAbductive Reasoning

  15. The AI Theorist reveals excitonic structure in αα-RuCl3_3

    Oct 1, 2026Hongjian Zhou, Xianfan Nie, Sean Wu +5Autonomous Scientific DiscoveryAI Agents for Scientific Discovery

  16. Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings

    Oct 1, 2026Kevin Tirta Wijaya, Alston Lo, Michael Sun +2Pairwise RankingAutonomous Scientific Discovery

  17. EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights

    Sep 30, 2026Jiayi Geng, Zhengxuan Wu, Kevin S. Chen +12Scientific DiscoveryLong-Horizon Agent Evaluation

  18. AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks

    Sep 29, 2026Thibaud Gloaguen, Robin Staab, Martin VechevText WatermarkingLLM Watermarking

  19. DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery

    Sep 28, 2026Yulong Li, Rong Xia, Yuxuan Zhang +12Causal DiscoveryCausal Attribution

  20. Autonomous phase discovery

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