Challenges and Directions for Engineering Multi-agent Systems

In this talk I review where we stand regarding the engineering of multi-agent systems. There is both good news and bad news. The good news is that over the past decade we’ve made considerable progress on techniques for engineering multi-agent systems: we have good, usable methodologies, and mature tools. Furthermore, we’ve seen a wide range of demonstrated applications, and have even begun to quantify the advantages of agent technology. However, industry involvement in AAMAS appears to be declining (as measured by industry sponsorship of the conference), and industry affiliated attendants at AAMAS 2012 were few (1-2%). Furthermore, looking at the applications of agents being reported at recent AAMAS, usage of Agent Oriented Software Engineering (AOSE) and of Agent Oriented Programming Languages (AOPLs) is quite limited. This observation is corroborated by the results of a 2008 survey by Frank and Virginia Dignum. Based on these observations, I make five recommendations: 1. Re-engage with industry 2. Stop designing AOPLs and AOSE methodologies . . . and instead . . . 3. Move to the “macro” level: develop techniques for designing and implementing interaction, integrate micro (single cognitive agent) and macro (MAS) design and implementation 4. Develop techniques for the Assurance of MAS 5. Re-engage with the US ∗Dagstuhl Seminar 12342 (August 2012), “Engineering Multi-Agent Systems”, organizers: Jürgen Dix, Koen V. Hindriks, Brian Logan, Wayne Wobcke. 1 ar X iv :1 20 9. 14 28 v1 [ cs .M A ] 7 S ep 2 01 2