An interesting application of self-organization techniques is in the context of coordination languages and models, which aims at developing tools (languages, models, infrastructures) to flexibly manage the interaction of components in distributed systems. In a coordinated system, the environment is filled with coordination media - e.g. tuple spaces or interaction channels - enacting coordination laws that are typically reactive, deterministic, and global. Based on the pillars of self-organizing systems and few emerging works in coordination, we propose and discuss the alternative view of self-organizing coordination, where coordination laws are probabilistic, based on local criteria, and time-reactive, thus resulting in coordination services where global properties of interest appear by emergence. To make the discussion more concrete we show an application inspired by corpse clustering and larvae sorting in ant colonies, where a distributed tuple-space-based scenario is enhanced with adaptive tuple clustering and sorting.