Agentic Workflows

Follow this topic Ask about this topic

Agentic workflows study how language-model agents plan and carry out multi-step tasks by calling tools, coordinating specialized agents, and maintaining state or artifacts. Systems range from fixed graphs and typed protocols with deterministic checks to dynamically planned workflows that use reusable skills, human approval, and execution feedback. Work includes scientific and enterprise automation, workflow generation and evaluation, and serving methods such as model routing, caching, scheduling, and parallel execution. A central challenge is balancing flexible autonomy and efficiency with dependable, auditable behavior, since successful outputs can conceal unsafe shortcuts, semantic errors, privacy leaks, or failures that compound across steps.

Latest papers

218 papers20 papers in the last four weeks, up 18% on the four weeks before. 0.1% of all new papers.

El Agente Gráfico: A Semantic Execution Runtime for Scientific Agents
Feb 19, 2026Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick +12Computational Quantum Chemistry Runtime Enforcement for AI Agents
Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada · Department of Computer Science, University of Toronto, 40 St George St., Toronto, ON M5S 2E4, Canada +10
From Labor to Collaboration: A Methodological Experiment Using AI Agents to Augment Research Perspectives in Taiwan's Humanities and Social Sciences
Feb 19, 2026Yi-Chih HuangAgentic Workflows Human-AI Collaboration
National Applied Research Laboratories Science & Technology Policy Research and Information Center Contact Address: 1, 14-15F, No. 106, Heping E. Rd., Sec. 2, Taipei 10636, Taiwan (R.O.C.)
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.
ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI
Feb 16, 2026Gaoyang Zhang, Shanghong Zou, Yafang Wang +3Agentic Workflows
Accenture Information Technology, SGITG · Kexin Technology, CNPIEC
Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
Feb 16, 2026Bardia Mohammadi, Nearchos Potamitis, Lars Klein +2Tool Use Tool-Using Agents
Max Planck Institute for Software Systems · Aarhus University · EPFL
Nalar: Workflow-Aware Management of Agentic Applications
Jan 8, 2026Saurabh Agarwal, Marco Laju, Donghyun Son +4LLM Inference Efficiency LLM Agent Orchestration
UT-Austin · Cisco-Research
Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator
Sep 21, 2025Thorsten Hellert, Drew Bertwistle, Simon C. Leemann +2AI for Science Agentic Workflows
Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA
Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Sep 7, 2025Ahmed E. Hassan, Hao Li, Dayi Lin +4Software Engineering Agents Agentic Workflows
Queen’s University, Kingston, ON, Canada · Concordia University, Montreal, Canada · Nara Institute of Science and Technology, Ikoma, Japan +1

Feb 19, 2026J/K move · Enter open · S save

El Agente Gráfico: A Semantic Execution Runtime for Scientific Agents

Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick, Marcel Müller+11

Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada · Department of Computer Science, University of Toronto, 40 St George St., Toronto, ON M5S 2E4, Canada+10

Computational Quantum Chemistry Runtime Enforcement for AI Agents AI Agents for Scientific Discovery Agentic Workflows

Open paper AskPDF arXiv

Large language models (LLMs) can plan scientific workflows and generate code, but these capabilities do not specify how scientific state is validated, transferred and recorded across heterogeneous computational and experimental operations. Here we present El Agente Gráfico, a semantic execution runtime for scientific agents that uses typed execution graphs to enforce admissible scientific state transitions, record provenance and confine model judgement to explicit decision points. Using the same top-level LLM and task-specific rubrics on six university-level quantum chemistry exercises, El Agente Gráfico improved performance while reducing model cost by approximately 80% and wall-clock time by more than fourfold relative to our previous multi-agent architecture. Across ensemble spectroscopy and metal-organic framework (MOF) design, the runtime supported typed-state transfer, parallel execution and cross-session persistence. Open-ended studies of a disulfide redox mechanism and the vibrational hypothesis of olfaction required the agent to define the chemical scope and computational pathway of each investigation. A graph-construction skill distilled from these studies then enabled coding agents to author typed execution graphs for MOF literature mining. Together, these results show how typed execution graphs turn reusable procedural knowledge into scientific protocols that can be inspected, revised and transferred across computational and physical systems.