AgentAI: A comprehensive survey on autonomous agents in distributed AI for industry 4.0
AgentAI: Всеобъемлющее обзорное исследование автономных агентов в распределённом ИИ для Индустрии 4.0
2025-06-02
SCID: 54.1/xc5xyp3y
Discuss with AI
AgentAIIndustry 4.0autonomous agentsdistributed Artificial Intelligencemulti-domain taxonomy
Figures from the paper
Abstract (AI)
AgentAI represents a transformative approach within distributed Artificial Intelligence (AI) in which autonomous agents work either individually or collaboratively in decentralized environments to address challenging problems. AgentAI enhances scalability, robustness, and flexibility by utilizing advanced communication, learning, and decision-making capabilities, making it integral to diverse applications in Industry 4.0. The ability of AI systems to interpret sensory data in open-world environments has seen significant advancements in recent years. This progress emphasizes the need to move beyond reductionist approaches and embrace more embodied and cohesive systems, which integrate foundational models into agent-driven actions. Existing surveys often focus on isolated domains or specific autonomy levels, lacking a cohesive analysis that spans the full spectrum of AgentAI development in Industry 4.0. This survey explicitly fills this gap by introducing a multi-domain taxonomy and by systematically analyzing both non-autonomous and fully autonomous AgentAI systems, offering a comprehensive synthesis not previously available in the literature. Additionally, the paper extends the discussion to Industry 5.0 and 6.0, exploring the evolution of AgentAI from automation to collaboration and, ultimately, to fully autonomous systems. This comprehensive analysis highlights the potential of AgentAI in driving industries toward a more efficient, sustainable, and adaptable future.
Key Findings
1
Argues that recent advances in sensory interpretation and foundational models motivate a shift from reductionist to more embodied, cohesive agent-driven systems.
2
Extends discussion to Industry 5.0 and 6.0, outlining AgentAI's evolution from automation to collaboration and toward fully autonomous industrial systems.
3
Identifies state-of-the-art techniques and key challenges in AgentAI systems, including communication, learning, and decision-making in decentralized environments.
4
Introduces a comprehensive multi-domain taxonomy of AgentAI applications specific to Industry 4.0, filling a gap in existing literature.
5
Provides a systematic analysis covering both non-autonomous and fully autonomous AgentAI systems across the full spectrum of AgentAI development.
Research Object
Autonomous agents (AgentAI) deployed in distributed AI systems for Industry 4.0
Research Subject
Their applications, taxonomy, techniques, challenges, and the spectrum of autonomy (from non-autonomous to fully autonomous) including communication, learning, decision-making, and integration of foundational models within Industry 4.0 contexts
Publication Details
Publication Date
2025-06-02
Journal
Publisher
ISSN
Cited by
76
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Towards A Rigorous Science of Interpretable Machine Learning2017
Training language models to follow instructions with human feedback2022
A survey on large language model based autonomous agents2024
Continual lifelong learning with neural networks: A review2019
Knowledge Graphs2021
A Categorical Framework of Manufacturing for Industry 4.0 and Beyond2016
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning2017
Visibility into AI Agents2024
Cited by6
The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges2025
Evaluating and regulating agentic AI: A study of benchmarks, metrics, and regulation2026
Artificial Intelligence agents and autonomous decision-making in business: a review2026
Evaluating routing stability and coordination in swarm-based multi-agent task-oriented dialogue systems2026
Toward Sustainable Agentic AI Systems: A Survey of Architectures and Methodologies2026
A Systematic Literature Review of Agentic AI: Definitions, Architectures, and Challenges2026