Embodied conversational agents - let's specify and evaluate them!

16 July, 2002

Bologna, Italy

in conjunction with

The First International Joint Conference on

Autonomous Agents & Multi-Agent Systems


The workshop themes are on the representation and evaluation of multimodal capabilities of embodied conversational characters. In particular, this workshop is concerned with the language and representation format which, metaphorically speaking, bridges between an agent's mind and body.

Agreeing on standard formats is important for sharing work, but another crucial component is evaluation, that is we need to understand how well the goals of a system are being achieved, both in terms of the architecture and in terms of the application.

The workshop will address issues such as the description, semantics and extensibility of representation formats and languages in a system, as well as the requirements for representation formats and a specification / mark-up language.

It will also address the criteria and methodologies to evaluate different aspects (engagement, entertainment, efficiency in learning and usage) of embodied agents as well as the definition of 'benchmarks' to compare and evaluate them.