Evaluation of a Conversation Management Toolkit for Multi Agent Programming

TL;DR

This paper evaluates the Agent Conversation Reasoning Engine (ACRE), demonstrating its effectiveness in improving communication reliability in multi-agent programming through experiments and cross-platform comparison.

Contribution

It introduces an evaluation framework for ACRE, showing its benefits in preventing communication issues and validating its applicability beyond a single platform.

Findings

ACRE reduces common communication problems in agent code.

Experimental results show improved reliability and extensibility with ACRE.

ACRE's benefits are applicable across different multi-agent frameworks.

Abstract

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.