agent-integrated workflowagentic information systemsdynamic orchestrationmulti-agent artificial intelligencesocio-technical implications
Figures from the paper
Abstract (AI)
Abstract Multi-agent artificial intelligence (MAAI) represents a foundational shift in the automation of knowledge work, moving beyond static workflows toward adaptive systems of interacting AI-based agents. These agents perceive, reason, and coordinate in real time to address complex, context-rich tasks that traditionally require human expertise. Drawing on the conceptual roots of process automation, agentic information systems, and AI, this paper introduces a structured, five-component framework that conceptualizes MAAI as a layered architecture composed of foundation model, data-centric perception and action, dynamic orchestration, agent-integrated workflow, and interaction interface. This framework disentangles the technical, organizational, and human-facing dimensions of MAAI, offering researchers and practitioners a systematic lens to analyze and design agent-based AI automation. The framework further structures three research pathways focused on advancing technical capabilities, enabling organizational integration, and addressing socio-technical implications such as fairness, accountability, and labor transformation. Together, these contributions establish a foundation for interdisciplinary inquiry into how MAAI reshapes work, coordination, and digital value creation.
Key Findings
1
Multi-agent artificial intelligence is characterized as an adaptive alternative to static workflows, using interacting agents for real-time perception, reasoning, and coordination.
2
The framework positions multi-agent AI as a basis for interdisciplinary study of changing work practices, coordination, and digital value creation.
3
The framework separates technical, organizational, and human-facing dimensions to support systematic analysis and design of agent-based AI automation.
4
The paper introduces a five-component layered framework comprising foundation models, data-centric perception and action, dynamic orchestration, agent-integrated workflows, and interaction interfaces.
5
Three research pathways address technical advancement, organizational integration, and socio-technical issues including fairness, accountability, and labor transformation.
Research Object
multi-agent artificial intelligence (MAAI) systems for automating knowledge work
Research Subject
the layered architecture, capabilities, organizational integration, and socio-technical implications of interacting AI-agent systems in knowledge-work automation
Publication Details
Publication Date
2026-02-06
Journal
Publisher
ISSN
Cited by
25
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai14
A Design Science Research Methodology for Information Systems Research2007
Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy2023
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing2022
A survey on large language model based autonomous agents2024
Machine learning and deep learning2021
On the Opportunities and Risks of Foundation Models2021
ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope2023
Generative AI2023
Artificial intelligence in information systems research: A systematic literature review and research agenda2021
Generative artificial intelligence2023
A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges2024
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges2025
AI Agents and Agentic Systems: A Multi-Expert Analysis2025
Retrieval-Augmented Generation (RAG)2025