In recent months, IEEE Computer Graphics and Applications (CG&A) has featured a growing number of discussions on the convergence of AI and interactive graphics. Agentic AI has leapfrogged the field of Generative AI forward by enabling LLMs to interact outside the realm of their training and augmented data to provide automated reasoning capabilities. Agentic AI refers to systems that autonomously make decisions, reason, and act to achieve goals. These advances promise to transform how humans interact with intelligent systems and how complex information is visualized, communicated, manipulated, and interpreted.
We invite submissions for a special issue on Agentic AI in Computer Graphics and Human-AI Collaboration. We welcome original research contributions addressing various aspects of Agentic AI interfacing with novel computer graphics, animation, and interactive visualization applications, and innovative forms of human-AI interactions. Submissions are encouraged to deepen our understanding of Agentic AI in these areas through theoretical frameworks, innovative systems, and empirical research.
A non-exhaustive list of topics includes:
In addition to research papers, IEEE CG&A invites Perspective and Overview Paper (POP) submissions related to this theme. POP papers may include surveys, tutorials, state-of-the-art reports, or forward-looking perspectives that synthesize knowledge or explore emerging aspects of the CFP theme. For details, visit https://www.computer.org/csdl/
Submission Guidelines:
For author information and guidelines on submission criteria, visit the Author’s Information Page. Please submit papers through the IEEE Author Portal and be sure to select the special issue or special section name. Manuscripts should not be published or currently submitted for publication elsewhere. Please submit only full papers intended for review, not abstracts.
This special issue on 3D Web Technologies will also publish interactive 3D models on the IEEE DataPort as an archival collection showcasing the described work in the papers. Wherever appropriate, and especially for applications, each submission is expected to provide live URLs to validated, open-source, publishable X3D models that demonstrate the capabilities described. Similar inclusion of original non-X3D models (used for conversion into corresponding publishable X3D models) is also welcome.