Design of Context-Aware Embodied AI Agents

Establish how embodied AI agents in immersive analytics systems should be designed, including the behaviours they should exhibit, their visual appearance, and the ways they should respond to users and their environments.

Background

The paper proposes a preliminary framework for designing embodied AI agents in immersive analytics around three dimensions of context: spatial, social, and semantic. Spatial context concerns how agents inhabit and move through physical or virtual space; social context concerns adherence to interactional norms; and semantic context concerns meaningful responses to tasks and conversations. The authors identify agent behaviour, appearance, and responses to users and environments as unresolved design considerations requiring further investigation.

References

How we design embodied AI agents in immersive analytics systems remains an open question. The behaviours these agents should exhibit, how they look, and how they respond to the user and the environment must all be considered.

— Context Matters! Social, Spatial, and Semantic Coordination with an Embodied Agent in Immersive Analytics  (2610.21484 - Cunningham et al., 15 Oct 2026) in Section 2, “Context in Embodied Agent Interaction”