Advanced Techniques for Multi-Agent Systems

Dear Colleagues,

Multi-agent systems (MASs) represent a vibrant area of research in artificial intelligence that focuses on the coordinated interactions between autonomous agents, each with their own capabilities and goals. The applications of MAS are both diverse and impactful. In robotics, MAS techniques enhance the coordination of multiple robots, allowing them to execute complex tasks with unprecedented efficiency. In the gaming industry, MAS is employed to develop dynamic and responsive AI characters, increasing player engagement and game realism. Additionally, MAS is applied in traffic management to optimize flow and reduce congestion, and in automated trading systems to predict market movements and execute trades at superhuman speeds. Each application underscores MAS's potential to revolutionize various aspects of our lives by introducing advanced levels of automation and intelligence.

Recent advances in computational hardware and AI algorithms have enhanced MAS, improving the efficiency of agent interactions. This issue will include papers detailing innovations in real-time decision making, adaptive learning, cooperative strategies, and MAS robustness in uncertain conditions. We encourage papers that investigate novel neural network models, reinforcement learning, and evolutionary algorithms for optimizing agent behavior and decision making, pushing forward the frontiers of MAS development. In addition, we welcome papers to explore advanced techniques in MAS and their applications across diverse domains.

We invite researchers to contribute original research articles as well as review articles that explore new developments, propose innovative theories, and present applied research in the field of multi-agent systems (MASs). We welcome comprehensive studies and articles that focus on, but are not limited to, the following areas:

• Adaptive Learning and Decision Making: Exploring how agents can evolve and improve their decision-making skills over time through advanced learning algorithms, especially in dynamic and unpredictable environments.
• Agent Cooperation and Competition: Investigating interaction protocols and strategies for agent cooperation in complex scenarios involving multiple stakeholders, with an emphasis on optimizing collective outcomes.
• Robustness in Multi-Agent Systems: Research aimed at enhancing the reliability and performance stability of MAS, particularly when faced with operational uncertainties and environmental fluctuations.
• Applications in Robotics: Utilizing MAS to improve coordination and operational efficiency in groups of robots, applicable in various contexts such as industrial automation, exploratory missions, and healthcare services.
• Multi-Agent Systems in Gaming: Developing more complex and adaptive non-player characters (NPCs) using sophisticated MAS techniques to enhance realism and engagement in video games.
• Traffic Management and Smart Cities: Applying MAS to optimize urban infrastructure management and alleviate congestion through smarter, coordinated traffic systems.
• Multi-agent Reinforcement Learning: Studies on how multiple agents engage in learning behaviors that adapt based on their interactions with the environment and other agents.
• Multi-agent Path Finding: Research into algorithms and strategies for efficient path finding and navigation solutions involving multiple agents, critical in logistics and operations research.
• Multi-Agent Systems for IoT: Examining the integration of MAS with the Internet of Things (IoT) to enhance connectivity and functionality across various devices and platforms.
• Foundation Model based Multi-Agents: Applying the foundation model to improve the planning and reasoning abilities of multi-agent systems.
• Other applications of multi-agent systems.

Dr. Rongye Shi
Dr. Qunbo Wang
Prof. Dr. Si Liu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• multi-agent systems
• autonomous agents
• multi robot systems
• smart city
• path finding
• IoT integration
• decision dynamics
• agent-based modelling
• security and privacy in modeling MAS
• large language model-based MAS
• MAS-based pattern recognition