Graphs provide a universal language for representing relationships, dependencies, and structural patterns across diverse domains. Their flexibility enables them to bridge data, models, and knowledge, establishing a connection between symbolic reasoning, statistical learning, and neural computation. While Graph Neural Networks (GNNs) have popularized graph-based learning, the role of graphs in Artificial Intelligence (AI) extends far beyond this paradigm. Graphs underpin computational structures in neural architectures, capture relational dependencies in attention mechanisms, organize knowledge through Knowledge Graphs (KGs), and model interactions among agents in social, multimodal, and dynamic environments.

This workshop aims to explore the expanding role of graph-based reasoning and representation across AI, moving beyond GNNs toward structure-aware learning both for and with foundation models. It seeks to foster discussion among researchers investigating how graphs can unify reasoning, learning, and computation across scales and modalities.

Topics of interest include (but are not limited to):
- Graphs in neural and attention-based architectures
- Graph-based explainability and reasoning
- Graph-based retrieval and trustworthy search
- Graphs for foundation model analysis and adaptation

Submission formats
Graphs Across AI invites research, industry, and application contributions submissions. We welcome both original works and discussion papers.
- Regular papers (up to 12 pages + references): original, unpublished work.
- Discussion papers (up to 8 pages + references): extended abstracts of recent publications, works under review, position papers, application/system descriptions, or preliminary results.

Submissions must be in English, PDF format, and follow the CEUR-ART 1-column style (Overleaf template available).

Submission portal: https://cmt3.research.microsoft.com/GRAAI2026

All accepted papers will be published in the CEUR-WS proceedings.

Important Dates
- Submission deadline: February 27, 2026 (AoE)
- Notification: March 27, 2026 (AoE)
- Camera-ready deadline: April 15, 2026 (AoE)