Evaluation of a Conversation Management Toolkit for Multi Agent Programming
The Agent Conversation Reasoning Engine (ACRE) is intended to aid agent developers to improve the management and reliability of agent communication. To evaluate its effectiveness, a problem scenario was created that could be used to compare code written with and without the use of ACRE by groups of test subjects.
This paper describes the requirements that the evaluation scenario was intended to meet and how these motivated the design of the problem. Two experiments were conducted with two separate sets of students and their solutions were analysed using a combination of simple objective metrics and subjective analysis. The analysis suggested that ACRE by default prevents some common problems arising that would limit the reliability and extensibility of conversation-handling code.
As ACRE has to date been integrated only with the Agent Factory multi agent framework, it was necessary to verify that the problems identified are not unique to that platform. Thus a comparison was made with best practice communication code written for the Jason platform, in order to demonstrate the wider applicability of a system such as ACRE.
Unable to display preview. Download preview PDF.
- 2.Muldoon, C., O’Hare, G.M.P., Collier, R.W., O’Grady, M.J.: Towards Pervasive Intelligence: Reflections on the Evolution of the Agent Factory Framework. In: El Fallah Seghrouchni, A., Dix, J., Dastani, M., Bordini, R.H. (eds.) Multi-Agent Programming: Languages, Platforms and Applications and Applications, pp. 187–212. Springer US, Boston (2009)Google Scholar
- 4.Bordini, R.H., Hübner, J.F., Wooldridge, M.: Programming multi-agent systems in AgentSpeak using Jason. Wiley-Interscience (2007)Google Scholar
- 5.Bellifemine, F., Caire, G., Trucco, T., Rimassa, G.: JADE Programmer’s Guide (JADE 4.0) (2010)Google Scholar
- 6.Barbuceanu, M., Fox, M.S.: COOL: A language for describing coordination in multi agent systems. In: Proceedings of the First International Conference on Multi-Agent Systems, ICMAS 1995, pp. 17–24 (1995)Google Scholar
- 7.Cost, R.S., Finin, T., Labrou, Y., Luan, X., Peng, Y., Soboroff, I., Mayfield, J., Boughannam, A.: Jackal: a Java-based Tool for Agent Development. Working Papers of the AAAI 1998 Workshop on Software Tools for Developing Agents. AAAI Press (1998)Google Scholar
- 8.Bradshaw, J.M., Dutfield, S., Benoit, P., Woolley, J.D.: KAoS: Toward an industrial-strength open agent architecture. Software Agents, 375–418 (1997)Google Scholar
- 9.Huget, M.P., Koning, J.L.: Interaction Protocol Engineering. Communications, 291–309 (2003)Google Scholar
- 10.Ancona, D., Drossopoulou, S., Mascardi, V.: Automatic Generation of Self-Monitoring MASs from Multiparty Global Session Types in Jason. In: Baldoni, M., Dennis, L., Mascardi, V., Vasconcelos, W. (eds.) DALT 2012. LNCS (LNAI), vol. 7784, pp. 76–95. Springer, Heidelberg (2013)Google Scholar
- 12.Luff, M.: Empirically Investigating Parallel Programming Paradigms: A Null Result. In: Workshop on Evaluation and Usability of Programming Languages and Tools, PLATEAU, pp. 43–49 (2009)Google Scholar
- 14.VanderWiel, S.P., Nathanson, D., Lilja, D.J.: Complexity and performance in parallel programming languages. In: Second International Workshop on High-Level Programming Models and Supportive Environments, pp. 3–12 (1997)Google Scholar