name “CrossTalk” underlines the fact that different animated agents have cross-screen conversations amongst themselves. From the point of view of information presentation CrossTalk explores a meta-theater metaphor that let agents live beyond the actual presentation, as professional actors, enriching the interactive experience of the user with unexpected intermezzi and rehearsal periods. CrossTalk is designed [...] In this paper, we describe CrossTalk, an interactive installation in which the virtual fair hostess Cyberella presents and explains the idea of simulated dialogues among animated agents to present product information. In particular, Cyberella introduces two further virtual agents, Tina and Ritchie who engage in a car-sales dialogue. Cyberella on the one hand, and Tina and Ritchie on the other hand

This paper introduces CrossTalk, an interactive installation with animated presentation agents. CrossTalk is an attempt to spatially extend the interaction experience beyond the usual single front screen. It offers two separated agent spaces (screens), where the agents "live", which form a triangle with the user's control panel. In this setting, we explore the meta-theatre metaphor for a new variant [...] off-duty dialogs, including rehearsals. The name CrossTalk expresses the variety of human-agent and agent-agent interactions that emerge and work together to attract and bind the user's attention. Technically, we rely on a fine-grained interweaving of automatically generated sales dialogs and manually scripted scenes of off-duty conversations. CrossTalk has be exposed during a one-week demo at the CeBIT

proposed for the user to reach her goal. We introduce a logic-based approach where plan generation and plan recognition is done on a common logical basis and both components work in some kind of cross-talk. Mathias Bauer; Susanne Biundo; Dietmar Dengler; Matthias Hecking; Jana Koehler; G. Merziger, 1991

improves the performance of intelligent help systems by supplying them with plan generation and plan recognition components. Both components work in close mutual cooperation. We demonstrate two modes of cross-talk between them, one where plan recognition is done on the basis of abstract plans provided by the planner and the other where optimal plans are generated based on recognition results. The examples