Both academia and industry have been putting a lot of effort into investigating various solutions to the problem of autonomic management of complex distributed computer systems. Existing approaches, based on the principles of autonomic computing, typically rely on monitoring a managed system, analysing the monitored values, and executing corresponding adaptation actions. By addressing existing limitations, we present a novel research area – stream reasoning – in the context of run-time monitoring and analysis in autonomic systems. This research area aims at enhancing existing stream processing techniques by adding dynamic reasoning support, thereby fitting scenarios when timely, yet precise analysis of dynamically flowing data is needed. In this paper, by discussing benefits and shortcomings, we speculate on the potential role of the approach in autonomic computer systems.