Marie-Pierre Gleizes, Gal A. Kaminka, Ann Nowé, Sascha Ossowski, Karl Tuyls, Katja Verbeeck (eds.)
3rd European Workshop on Multi-Agent Systems (EUMAS 2005), pages 332–343
Koninklijke Vlaamse Academie van Belie voor Wetenschappen en Kunsten, Brussels, Belgium
7-8 December 2005
Stigmergy has been variously adopted in MASs (multi-agent systems) and in other fields as well—as a technique for realising forms of emergent coordination in societies composed by a large amount of typically simple, ant-like, non-rational agents.
In this article we introduce a conceptual and engineering framework for exploring the use of stigmergy in the context of societies composed by cognitive / rational agents, as a means for supporting high-level, knowledge-based social activities.
We refer to this kind of stigmergy as cognitive stigmergy.
Cognitive stigmergy is based on the use of suitable engineered <em>artifacts</em> as tools populating the agent working environment, and which agents share and rationally use for their individual goals.
In this seminal paper, we introduce an agent-based framework for cognitive stigmergy based on artifacts.
After discussing the main conceptual issues – the notion of cognitive stigmergy, the role of artifacts –, we sketch an abstract architecture for cognitive stigmergy, and we consider its implementation on the TuCSoN agent coordination infrastructure.