Scientific Workflow Automation

Follow this topic Ask about this topic

The field connects research goals to executable sequences of data processing, analysis, simulation, and laboratory operations. Approaches include workflow engines and directed acyclic graphs, LLM-based planning and multi-agent systems, typed tools and domain-specific languages, and deterministic checks for execution, safety, and provenance. These methods increasingly automate bounded tasks across fields such as biology, materials science, climate research, and imaging, often with human review at key decisions. Reliable end-to-end work remains difficult: agents can produce plausible plans or code yet miss silent scientific errors, while designers must balance flexible reasoning with reproducibility and human oversight.

Latest papers

161 papers12 papers in the last four weeks, down 14% on the four weeks before. 0.1% of all new papers.

Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows
Mar 6, 2026Joel Strickland, Arjun Vijeta, Chris Moores +7LLM Agent Orchestration Scientific Workflow Automation
Intellegens, The Studio, Chesterton Mill, Cambridge, CB4 3NP, UK · Independent Researcher · Cavendish Laboratory, J.J. Thomson Avenue, Cambridge, UK
TritonDFT: Automating DFT with a Multi-Agent Framework
Mar 2, 2026Zhengding Hu, Kuntal Talit, Zhen Wang +8Scientific Workflow Automation Density Functional Theory
University of California, San Diego · University of California, Merced · Los Alamos National Laboratory
What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction
Mar 2, 2026Lehui Li, Ruining Wang, Haochen Song +8Scientific Code Generation Scientific Reproducibility
School of Software, Shandong University China · Beijing Institute of Technology China · Zhejiang University China +4
SciDER: Scientific Data-centric End-to-end Researcher
Mar 2, 2026Ke Lin, Owais Aijaz, Yilin Lu +3AI Agents for Scientific Discovery Scientific Workflow Automation
Data Science, College of William & Mary, Williamsburg, USA · Natural Language Processing, MBZUAI, Abu Dhabi, UAE · Computer Science, University of Minnesota, Minneapolis, USA +1
Airavat: An Agentic Framework for Internet Measurement
Feb 24, 2026Alagappan Ramanathan, Eunju Kang, Dongsu Han +1Agentic Workflows Scientific Workflow Automation
University of California, Irvine · KAIST
InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing
Feb 22, 2026Kun Ding, Jian Xu, Ying Wang +2Scientific Workflow Automation Scientific Code Generation
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography
Feb 18, 2026Zhongcan Xiao, Leyi Zhang, Guannan Zhang +1Scientific Workflow Automation AI Agent Governance
Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA · Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA · Department of Linguistics, University of Illinois Urbana-Champaign, Urbana, Illinois, USA +3
DataJoint 2.0: A Computational Substrate for Agentic Scientific Workflows
Feb 18, 2026Dimitri Yatsenko, Thinh T. NguyenScientific Workflow Automation Agentic Workflows
DataJoint Inc., Houston, USA · DataJoint Inc.
AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research
Dec 18, 2025Ignacio Heredia, Álvaro López García, Fernando Aguilar Gómez +28AI-Assisted Scientific Research Scientific Workflow Automation
Instituto de Física de Cantabria (IFCA), CSIC-UC, Avda. los Castros s/n, Santander, 39006, Cantabria, Spain · Instituto de Instrumentación para Imagen Molecular (I3M), Centro Mixto CSIC - Universitat Politècnica de València (UPV), Camino de Vera s/n, Valencia, 46022, Valencia, Spain · Karlsruher Institut für Technologie, Kaiserstraße 12, Karlsruhe, 76131, Germany +7
ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms
Dec 3, 2025Juan Diego Toscano, Daniel T. Chen, George Em KarniadakisScientific Code Generation Scientific ML
Division of Applied Mathematics, Brown University, Providence, 02912, RI, USA
CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows
Nov 25, 2025Chenyue Li, Hyeonjae Kim, Wen Deng +4AI for Science Multi-Agent Orchestration
1The Hong Kong University of Science and Technology

Mar 6, 2026J/K move · Enter open · S save

Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows

Joel Strickland, Arjun Vijeta, Chris Moores, Oliwia Bodek+6

Intellegens, The Studio, Chesterton Mill, Cambridge, CB4 3NP, UK · Independent Researcher · Cavendish Laboratory, J.J. Thomson Avenue, Cambridge, UK

LLM Agent Orchestration Scientific Workflow Automation LLM Agent Evaluation

Open paper AskPDF arXiv

Large language models (LLMs) can now translate a researcher's plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are difficult to guarantee when an LLM decides what runs. Semi-structured interviews with 18 experts across 10 industrial R&D stakeholders surface 2 competing requirements--deterministic, constrained execution and conversational flexibility without workflow rigidity--together with boundary properties (human-in-the-loop control and transparency) that any resolution must satisfy. We propose schema-gated orchestration as the resolving principle: the schema becomes a mandatory execution boundary at the composed-workflow level, so that nothing runs unless the complete action--including cross-step dependencies--validates against a machine-checkable specification. We operationalize the 2 requirements as execution determinism (ED) and conversational flexibility (CF), and use these axes to review 20 systems spanning 5 architectural groups along a validation-scope spectrum. Scores are assigned via a multi-model protocol--15 independent sessions across 3 LLM families--yielding substantial-to-near-perfect inter-model agreement (Krippendorff a=0.80 for ED and a=0.98 for CF), demonstrating that multi-model LLM scoring can serve as a reusable alternative to human expert panels for architectural assessment. The resulting landscape reveals an empirical Pareto front--no reviewed system achieves both high flexibility and high determinism--but a convergence zone emerges between the generative and workflow-centric extremes. We argue that a schema-gated architecture, separating conversational from execution authority, is positioned to decouple this trade-off, and distill 3 operational principles--clarification-before-execution, constrained plan-act orchestration, and tool-to-workflow-level gating--to guide adoption.