The distributed nature of peer-to-peer networks offers a solid ground for the deployment of environments where multiple agents, managing several resources, can cooperate in pursuing common and individual goals while achieving good overall performance. In this article we present a survey of recent work on the integration of multi-agent systems and peer-to-peer computing for resource coordination (including discovery, composition and execution of resources) and we propose an approach for optimizing resource coordination through the use of efficient peer-to-peer search mechanisms relying upon a powerful semantic overlay network. We also present an approach for the dynamic development of the required semantic overlay network from a network of randomly-connected peers.

This paper describes Monitorix, a video-based

In this paper, we present an architecture for software agents that enables them to learn vocabulary through the observation of each other bodies and actions. Besides sensors, effectors, and action control, the architecture provides the equivalent of a body with visual appearance. The agent soft visual appearance is designed to be seen by other software agents, not by people. The paper describes the agent software body with visual appearance, the learning mechanism, the demonstration scenario and presents some results showing that the agent software body allows agents to learn vocabulary through observation and to ground the meaning of the symbols they learn. The paper emphasizes the important role of social interaction in learning processes.

Abstract. We present three mechanisms of attention shift for autonomous agents within the framework of the SALT model of memory [5]: activationbased attention shift, attention shift by event-driven emotion and attention shift by anticipation-driven emotion. The three mechanisms rely on automatically computed properties of memory (as opposed to deliberative processes).Activation-based attention shift is based on the activation of cognitive structures stored in long term memory. The other two are two-step emotionbased mechanisms of attention shift: first emotion interrupts the agent's current cognitive process (as in activation-based attention shift), then the processing of the emotion directs the agent's attention to the external environment. In attention shift by event-driven emotion, the ongoing cognitive process may be interrupted when an external event causes the agent to experience an emotion. In the attention shift by anticipation-driven emotion, the ongoing cognitive process may be interrupted when the agent anticipates affective states attributed to the external environment.

No abstract