Engineering the Next Generation of Multi-agent Systems : A Community Roadmap from EMAS 2025

Rodriguez, Sebastian and Bairy, Akhila and Baldoni, Matteo and Benjamin, Patrick and Blessing, Constantin and Brandstetter, Nicolas and Chopra, Amit K. and Clemen, Thomas and Dennis, Louise A. and Esmaeili, Ahmad and Feng, Lu and Ferrando, Angelo and Ghorrati, Zahra and Guillet, Victor and Gürcan, Önder and Hans, Soham and Herber, James and Mascardi, Viviana and Mauri, Marcel and Müller, Jörg P. and Thangarajah, John and Tyl, Rafał and Yang, Yi (2026) Engineering the Next Generation of Multi-agent Systems : A Community Roadmap from EMAS 2025. In: Engineering Multi-Agent Systems : EMAS 2025. Lecture Notes in Computer Science . Springer, Cham, pp. 238-258. ISBN 9783032180100

Text (EMAS-25-CR)
EMAS-25-CR.pdf - Accepted Version
Available under License None.
Download (384kB)

Abstract

This paper presents the outcomes of an open-floor session held at the 13th International Workshop on Engineering Multi-Agent Systems (EMAS 2025), aimed at co-developing a research roadmap for the EMAS community. Participants collaboratively identified and prioritised challenges in engineering large-scale, adaptive multiagent systems, particularly considering the need to engineer systems that can seamlessly integrate learning and reasoning. Through structured group discussions, four key challenges emerged: explainability in heterogeneous environments, environment modeling, handling dynamic contexts, and communication standardisation. For each of the challenges, participants proposed and ranked potential solutions based on impact and effort. The resulting roadmap highlights concrete research directions toward engineering intelligent, explainable, and interoperable multiagent systems that effectively integrate reasoning and learning in dynamic environments.