Research Directions in Agent Communication

A. K. Chopra, A. Artikis, J. Bentahar, M. Colombetti, F. Dignum, N. Fornara, A. J. I. Jones, M. P. Singh, and P. Yolum, ACM Transactions on Intelligent Systems, 2011, []

Increasingly, software applications involve open systems consisting of autonomous and heterogeneous participants or agents who carry out loosely coupled interactions. Accordingly, understanding and specifying communications among agents is a key concern for such systems. A focus on ways to formalize meaning distinguishes agent communication from traditional distributed computing: meaning provides a basis for flexible interactions and compliance checking. Over the years, a number of approaches have emerged with some essential and some irrelevant distinctions drawn among them. As agent abstractions gain increasing traction in the software engineering of open systems, it is important to resolve such irrelevant distinctions and highlight the essential distinctions, so that future research can be focused in the most productive directions. This paper is an outcome of a year-long exercise by agent communication researchers to take stock of the field and to develop, critique, and refine their positions on specific approaches and future challenges. This paper serves some important purposes, including identifying (1) points of broad consensus; (2) points where substantive differences remain; and (3) interesting directions of future work.