Among the central challenges of Ambient Assisted Living systems are the autonomous and reliable recognition of the assisted person's current situation and the proactive offering and rendering of adequate assistance services. In the context of emergency support, such situations may be acute emergency situations or long-term deviations from typical behavior that will result in emergency situations in the future. To optimize the treatment of the former and the prevention of the latter, reliable recognition of characteristic activities of daily living is necessary. In this paper, we present our multi-agent-based activity recognition framework as well as experiences made with it. Besides a detailed discussion of our hybrid recognition approach, we also elaborate on the tailoring of the underlying reasoning models to the individual environments and users in an initial learning phase. Finally, we present experiences made with the recognition framework in our Ambient Assisted Living Laboratory.