
Workshop on The Intelligent Mesh – Edge AI Technology Roadmap for Orchestrating Autonomous Systems with Agentic and Generative AI
HiPEAC 2026 Conference, 27 January 2026
The Intelligent Mesh – Edge AI Technology Roadmap for Orchestrating Autonomous Systems with Agentic and Generative AI workshop explores the future of this transformation, offering a critical forum to discuss the European roadmap for next-generation edge AI systems. The presentations explore the foundational pillars of this evolution, from novel heterogeneous hardware platforms, edge AI accelerators, and bio-inspired neuromorphic architectures to the edge AI frameworks and advanced algorithms needed to power them. Key discussions will focus on the rise of Small Language Models (SLMs) optimised for embedded hardware, the deployment of Vision-Language Models (VLMs) for advanced machine perception, and the transformative potential of edge generative AI.
A central theme of the workshop is the emergence of agentic AI at the edge. We will investigate how agentic reasoning can empower individual devices and how mesh agentic AI will enable complex swarms of autonomous systems to collaborate, negotiate, and orchestrate their actions seamlessly. This leap forward is crucial for creating autonomous systems that can navigate and interact with the complexities of the real world, from innovative industry to intelligent infrastructure.
The workshop is co-organised by large-scale Chips JU EdgeAI and Horizon Europe dAIEDGE projects to exchange ideas to foster collaboration among academia, researchers, and industry leaders to identify and roadmap next-generation edge AI technologies and applications for secure, intelligent, and autonomous systems of the future.
Session 1 - Foundations of the Next-Gen Edge. "Intelligent Mesh" vision for edge AI.
Session 2 - Edge AI Technology Developments. Challenges, and trends.
Session 3 - Rise of SLMs, VLMs and Agentic AI.
Session 4 - Edge AI Future Technology and Applications. Trends and Strategic Research Agenda. Presentations and Panel Discussions.


Charting the Future of Edge AI
Functional and Non-Functional Requirements in the Age of Generative AI
January 21 / 2025
The workshop provides a comprehensive platform for stakeholders to exchange ideas, share experiences, and collaborate on advancing edge AI technologies. By addressing functional and non-functional requirements defined based on system engineering principles, participants will gain valuable insights into deploying effective and responsible edge AI solutions using cross-disciplinary approaches for enhancing edge AI capabilities in the generative AI era.
The workshop combines presentations and panel discussions to allow the participants to share their insights, research findings, and best practices, facilitating a collaborative environment that promotes innovation in edge AI.
Session 1: Edge AI Functional and Non-functional Requirements in the Generative AI Era.
Session 2: Technology Developments
Session 3: Applications Developments
Session 4: Edge AI Future Trends and Strategic Research Agenda Panel


Driving Next-Gen Edge AI Technologies
January 17 / 2024
The workshop aims to address the latest developments in the implementation of edge AI technologies and present and discuss the advances in intelligent embedded devices across the edge AI computing continuum from micro- to deep- and meta-edge. The aim is to advance the field of smart embedded devices by systematically evaluating and comparing technologies for edge AI.
The workshop is organised as a combination of presentations and panel discussions to allow the participants to share their insights, research findings, and best practices, fostering a collaborative environment that drives innovation in edge AI. The workshop is co-organised by large-scale Chips JU EdgeAI, ANDANTE, REBECCA, CLEVER, NEUROKIT2E, and Horizon Europe dAIEDGE projects to exchange ideas for providing a set of reference comprehensive benchmarking solutions by bringing together a diverse community of experts, researchers, and industry leaders to collectively tackle the intricacies of benchmarking in edge AI.