Overview

AI for Science studies how computational methods can help researchers analyze data, build and test models, design experiments, and discover new explanations or materials. Approaches include scientific foundation models, retrieval and multi-agent systems, causal and symbolic methods, Bayesian optimization, and tools that connect AI to simulators, code, instruments, and high-performance computing. Benchmarks increasingly test scientific coding, image interpretation, simulator use, experimental design, and multi-step research workflows. AI often helps with well-specified tasks, but reliable open-ended discovery remains difficult: systems can make plausible errors, struggle with mechanistic reasoning, and need stronger verification, provenance, and evaluation against expert work.

Latest papers

CardsList

167 papers10 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

  1. SciWorkBench: A Benchmark for Real Scientific Workflows

    Nov 17, 2026Yuchen Zhang, Taolin Han, Jinghang Wang +19Scientific Agent BenchmarksAI for Science

  2. Embodied AI for Scientific Discovery: From Physical Action to Scientific Evidence

    Nov 3, 2026Wenhao Xu, Changwei Wang, Shunpeng Chen +6AI for ScienceAutonomous Experimentation

  3. Can AI Do Formal Demography? Why Vaccinating the Oldest Saves Both the Most Lives and the Most Years of Life

    Nov 2, 2026Joshua R. Goldstein, Kenneth W. WachterAI for Science

  4. From FAIR to AI-FAIR Metadata-First Infrastructure for AI-Enabled Science

    Nov 2, 2026Elizabeth G. Campolongo, Eric R. Sokol, Marty Downs +9AI for Science

  5. Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI

    Oct 31, 2026Yusuke Hashimoto, Takaaki TomaiData Analysis AgentsAI for Science

  6. FARMS: A Verifiable Foundation for Automated Computational Science

    Oct 29, 2026Di Wu, Ling Liang, Haizhao YangAI for ScienceFormal Verification

  7. AI in the EGI e-infrastructure -- Past experiences and future strategies

    Oct 29, 2026Gergely Sipos, Sergio Andreozzi, Marco Rorro +2AI for ScienceAI-Assisted Scientific Research

  8. AI for Science in Space: Orbital Laboratories, Planetary Fieldwork, and Embodied Autonomy

    Oct 29, 2026Zizhe Wang, Jia Deng, Xin Lu +4AI for ScienceAutonomous Experimentation

  9. Agentic Systems for Calibrating Cosmological Simulations

    Oct 26, 2026Chaipat Tirapongprasert, Matthew HoModel CalibrationAI for Science

  10. SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks

    Oct 23, 2026Tianyun Zhong, Wei Wang, Jialin Li +17Scientific Agent BenchmarksLLM Agent Evaluation

  11. ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization

    Oct 22, 2026Zhaoran Feng, Yuchen Ni, Jianan Liu +3AI for ScienceSelf-Evolving Agents

  12. Framework for an AI-Ready ARPES Community Database

    Oct 11, 2026Zhi-Xun Shen, Jin Gene Wong, Karen Lei +41AI for Science

  13. VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation

    Oct 9, 2026Katherine J. Koebel, Renata Ivanek, Parminder Basran +33AI for Science

  14. OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences

    Oct 8, 2026Zhiyi Li, Sihan Hu, Tianning Xiao +4AI for ScienceScientific Reasoning in Language Models

  15. SciExam for ENSO: Can AI Agents Build Climate Models?

    Oct 7, 2026Yinling Zhang, Langchen Liu, Dongbin Xiu +4AI for ScienceAI Agent Benchmarks

  16. ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences

    Oct 6, 2026Mingda Zhang, Wenjin Liu, Tiesunlong Shen +6Scientific Agent BenchmarksSelf-Evolving Agents

  17. OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software

    Sep 30, 2026Dingyuan Dai, Heli Qi, Lei Liu +28Computer-Use Agent BenchmarksAI for Science

  18. Searching for BSM Experimental Signatures with Large Lagrangian Models

    Sep 29, 2026Ibrahim Elsharkawy, Victoria Knapp-Perez, Wahid Bhimji +1AI for ScienceHigh-Energy Physics

  19. ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations

    Sep 26, 2026J. Paul Liu, Uthpala Herath, Andrew PetersenAI for ScienceHigh-Performance Computing

  20. PhyMo: A Physical-Field Modality for Multimodal AI4Physics

    Sep 23, 2026Henan Sun, Haitao Hu, Jin Liu +4AI for ScienceCross-Modal Representation Learning

  21. PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research

    Sep 15, 2026Xinle Yu, Fan Bai, Kaiser Sun +5AI for ScienceAutonomous Research Agents

  22. The AI-Enabled Scientific Frontier

    Sep 14, 2026Gabriel Manso, Emma Fu, Neil ThompsonAI for ScienceAI-Assisted Scientific Research

  23. ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution

    Sep 13, 2026Baixi Sun, Mingze Xia, Huihuo ZhengScientific Workflow AutomationAI for Science

  24. AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era

    Sep 7, 2026Yunxiang Mo, Tianshi Zheng, Yisen Gao +7AI for ScienceAI Agent Evaluation