Adapting granular rough theory to multi-agent context

The present paper focuses on adapting the Granular Rough Theory to a Multi-Agent system. By transforming the original triple form atomic granule into a quadruple, we encapsulate agent-specific viewpoint into information granules to mean "an agent knows/believes that a given entity has the attribute type with the specific value". Then a quasi-Cartesian qualitative coordinate system named Granule Space is defined to visualize information granules due to their agent views, entity identities and attribute types. We extend Granular Rough Theory into new versions applicable to the 3-D information cube based M-Information System. Then challenges in MAS context to rough approaches are analyzed, in forms of an obvious puzzle. Though leaving systematic solutions as open issues, we suggest auxiliary measurements to alleviate, at least as tools to evaluate, the invalidity of rough approach in MAS.