Cognitive Stigmergy: Towards a Framework Based on Agents and Artifacts Alessandro Ricci, Andrea Omicini, Mirko Viroli, Luca Gardelli, and Enrico Oliva Alma Mater Studiorum—Universit`a di Bologna via Venezia 52, 47023 Cesena, Italy a.ricci@unibo.it, andrea.omicini@unibo.it, mirko.viroli@deis.unibo.it, luca.gardelli@unibo.it, enrico.oliva@unibo.it Abstract. Stigmergy has been adopted in MAS (multi-agent systems) and in other fields as a technique for realising forms of emergent co- ordination in societies composed by a large amount of ant-like, non- rational agents. In this paper we discuss 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.multi-agent We refer to this kind of stigmergy as cognitive stigmergy. Cognitive stigmergy is based on the use of artifacts as tools populating and structuring the agent working environment, and which agents perceive, share and rationally use for their individual goals. Artifacts are environment abstractions that me- diate agent interaction and enable emergent coordination: as such, they can be used to encapsulate and enact the stigmergic mechanisms and the shared knowledge upon which emergent coordination processes are based. In this paper, we start exploring this scenario introducing an agent- based framework for cognitive stigmergy based on artifacts. After dis- cussing the main conceptual issues—the notion of cognitive stigmergy and the role of artifacts—, we sketch an abstract architecture for cogni- tive stigmergy, and outline its implementation upon the TuCSoN agent coordination infrastructure. 1 Introduction In the last years, the study of stigmergy has influenced a number of different research fields, including MAS (multi-agent systems). In general, and in MAS research in particular, stigmergy is mostly used as the source of simple yet effec- tive coordination metaphors and mechanisms, to be exploited for building robust and reliable systems in unpredictable settings. The main source of inspiration is obviously represented by the studies on insects and ant societies [1], which have led to a basic meta-model based on (ant-like) simple and homogeneous agents possessing no relevant cognitive abilities. Such agents interact with each other through local modifications to the environment, eventually originating global structures and behaviours [2]. D. Weyns, H.V.D. Parunak, and F. Michel (Eds.): E4MAS 2006, LNAI 4389, pp. 124–140, 2007. c  Springer-Verlag Berlin Heidelberg 2007