Engineering Multi-agent Systems and Generative AI: Report from the Agent Toolkits 2025 Community Session
 |
 |
 |
abstract = {Intelligent agents have been a cornerstone of Artificial Intelligence (AI) since its early days—and received significant attention in the 1990s when the notion of autonomous agent was established, giving rise to research on Engineering Multi-Agent Systems (EMAS). Traditionally, this area has focused on theories, architectures, methodologies, paradigms, and languages for designing, implementing, and governing systems of autonomous agents. More recently, advances in Generative AI—and specifically large language models—have led to a new generation of agents and multi-agent systems, often referred to as Agentic AI. However, the conceptual bridges, overlaps, and complementarities between Agentic AI and traditional EMAS research are often unclear. The Agent Toolkits 2025 community session invited positions statements from senior members of the EMAS community to discuss these recent developments. This paper summarizes and integrates their contributions and outlines key directions for research on EMAS with Generative AI.},
apice = {AgenttoolkitEumas2025},
author = {Andrei Ciortea and Katharine Beaumont and Gianluca Aguzzi and Matteo Baldoni and Cristina Baroglio and Amit K. Chopra and Ciatto, Giovanni and Rem W. Collier and Mehdi Dastani and Angelo Ferrando and Andrea Gatti and Gürcan, Önder and Timotheus Kampik and Jérémy Lemée and Somsakun Maneerat and Elisa Marengo and Viviana Mascardi and Simon Mayer and Roberto Micalizio and Guillaume Muller and Vivek Nallur and Richard Niamke and Andrei Olaru and Heloise Pajot and Chloé Petridis and I. S. W. B. Prasetya and Ricci, Alessandro and Alexandru Sorici and Stefano Tedeschi and Michael Winikoff},
booktitle = {Multi-Agent Systems: 22nd European Conference, EUMAS 2025, Bucharest, Romania, September 3–5, 2025, Proceedings, Part I},
dblp = {conf/eumas/CiorteaBABBCCCDFGGKLMMM25.bib},
doi = {10.1007/978-3-032-22817-8_22},
editor = {Matteo Baldoni and Franziska Klügl and Andrei Olaru and Alexandru Sorici and Adina Magda Florea},
keywords = {Engineering Multi-Agent Systems, Generative AI, Agent Toolkits},
pages = {379--401},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
subseries = {Lecture Notes in Artificial Intelligence},
title = {Engineering Multi-agent Systems and Generative {AI:} Report from the Agent Toolkits 2025 Community Session},
url = {https://link.springer.com/10.1007/978-3-032-22817-8_22},
urlpdf = {https://link.springer.com/content/pdf/10.1007/978-3-032-22817-8_22.pdf},
volume = 16258,
year = 2025
}