About SAGE for IoT 2026 

The convergence of AI, the Internet of Things, and Big Data is enabling a new generation of intelligent, autonomous, and context-aware systems. As billions of devices generate high-velocity, heterogeneous data across edge, fog, and cloud environments, the demand for scalable, real-time, adaptive data engineering has never been greater.

SAGE for IoT 2026 is a forum for foundational and applied research at the intersection of agentic AI, generative models, and IoT infrastructure. The workshop addresses the full stack: from hardware-constrained edge inference and federated learning to the deployment of Large Language Models (LLMs) and Small Language Models (SLMs) as intelligent coordinators in distributed systems. Particular emphasis is placed on agentic architectures — where AI agents autonomously sense, reason, plan, and act — and on the trustworthy operationalization of generative AI in high-stakes physical environments.

A defining theme for 2026 is the emergence of AI as a scientific collaborator. IoT-enabled, self-driving laboratories are beginning to close the loop between data collection, hypothesis generation, and experimental execution with minimal human oversight, accelerating discovery across the physical, biological, and engineering sciences. SAGE provides a dedicated venue to explore both the technical foundations and the ethical implications of this shift.

Previous editions: 2018 · 2019 · 2020 · 2021 · 2022 · 2025

Research topics of interest

SAGE for IoT 2026 welcomes original, unpublished contributions across the following areas. Topics include, but are not limited to:

1. Agentic AI and autonomous systems for IoT

   • Multi-agent architectures for distributed IoT orchestration, including negotiation, coordination, and self-healing behavior

   • Tool-using and reasoning LLM agents deployed at the network edge for real-time control and decision support

   • Autonomous sensor networks and AI-guided instrumentation for adaptive, field-deployed data collection

   • AI-powered digital twins for remote lab management, predictive maintenance, and simulation-driven optimization

2. Generative AI and foundation models at the edge

   • Small Language Models for on-device reasoning: deployment strategies, evaluation benchmarks, and performance profiling

   • Foundation model adaptation for IoT — quantization, pruning, LoRA, and distillation on embedded and mobile-class hardware

   • Prompt engineering, retrieval-augmented generation, and chain-of-thought reasoning in resource-constrained settings

   • Multimodal pipelines integrating vision, audio, time-series, and sensor fusion on heterogeneous edge nodes

3. Federated, continual, and privacy-preserving learning

   • Federated learning under non-IID distributions, communication constraints, and adversarial participants

   • Continual and lifelong learning for AIoT devices that must adapt without catastrophic forgetting

   • Differential privacy, secure aggregation, and homomorphic encryption for IoT workloads

   • Trust-aware model aggregation and participant verification in decentralized learning ecosystems

4. Edge data engineering and real-time analytics

   • Stream processing and adaptive dataflow pipelines for high-velocity IoT data across edge/fog/cloud hierarchies

   • Data quality, provenance, and governance in distributed sensing environments

   • Benchmarking and FAIR-compliant dataset development for AIoT research

   • Real-time anomaly detection, event-driven processing, and context-aware analytics for cyber-physical systems

5. Security, trust, and explainability in AIoT

   • Adversarial robustness and threat modeling for edge-deployed AI models

   • Zero-trust architectures and secure inference pipelines for IoT environments

   • Explainable AI adapted for real-time, resource-limited deployment contexts

   • Human-in-the-loop systems, adaptive oversight, and trust calibration for autonomous IoT agents

6. Autonomous scientific experimentation 

   • Self-driving laboratories: closed-loop systems for hypothesis generation, experimental execution, and iterative adaptation

   • AI-curated experiment loops integrating robotic systems, IoT sensors, and intelligent data pipelines

   • Scalable scientific workflows for distributed, multi-site experimentation in biology, materials science, and engineering

   • Ethical, legal, and social implications of autonomous AI in scientific research — accountability, equity, and transparency

Workshop Schedule

• • TBD

Important Dates

• • July 1, 2026 — Workshop call for papers released

  • October 16, 2026 — Paper submission deadline

  • November 1, 2026 — Notification of acceptance to authors

  • November 14, 2026 — Camera-ready papers due (firm)

  • December 14–17, 2026 — TBD

Workshop Team

Co-Chairs:

• • Eyhab Al-Masri (University of Washington, USA)

  • Olivera Kotevska Oak Ridge National Laboratory (ORNL)

Program Committee Members:

• • Vikas Agarwal (IBM Research, India)

  • Amr Amrallah (KDDI Research, Inc., Japan)

  • Abdelmadjid Benarfa (University of Laghouat, Algeria)

  • Christian Beecks (University of Muenster, Germany)

  • Chi-Hua Chen (Chunghwa Telecom, Taiwan)

  • Mingzhe Chen (Princeton University, USA)

  • Subarna Chatterjee (Harvard University, USA)

  • Xuan-Hong Dang (IBM Thomas J. Watson Research Center, USA)

  • Mawaba Dao (Florida Institute of Technology, USA)

  • Carlos Garcia-Rubio (Universidad Carlos III de Madrid, Spain)

  • Abdelfatteh Haidine (Chouaib Doukkali University, Morocco)

  • Mohamed Hamdi (University of Toronto)

  • Ruksana Kabealo (Florida Institute of Technology, USA)

  • Sergey Kanzhelev (Google, USA)

  • Ahmed Kawther (Mustansiriyah University, Iraq)

  • Mena Olyan (University of Waterloo, Canada)

  • Afzel Noore (Texas A&M University-Kingsville, USA)

  • Andrea Monteriù (Università Politecnica delle Marche, Italy)

  • Lauritz Thamsen (Technische Universitat Berlin, Germany)

  • Angelo Trotta (University of Bologna, Italy)

  • Keping Yu (Hosei University, Japan)

Submission Instructions

We welcome contributions describing original ideas, experiments and applications relevant to the workshop theme which have not been published earlier or are not currently pending submission at any other venue. All submitted papers must include the names and affiliations of all authors. Submitted papers will be peer-reviewed by members of the Workshop Program Committee. All accepted papers will be included in the main conference proceedings (see Proceedings section below).  

Submission Categories:

• • Long Papers: 8-10 pages (research at a mature stage, including references & appendices)

  • Short/Work-in-Progress Papers: 4-6 pages (early or intermediate stage, including references & appendices))

Paper Submission Link: 

Please submit your paper via this link.

Templates:

• • https://www.ieee.org/conferences/publishing/templates.html 

Camera Ready Instructions:

• •  https://conferences.cis.um.edu.mo/ieeebigdata2026/

Proceedings:

• • All papers accepted will be included in the IEEE Big Data Conference Proceedings published by the IEEE Computer Society Press.  At least one author of each accepted paper must register for the conference and present the paper at the workshop for the paper to be included in the conference proceedings. Details on the registration will be posted on the main conference's page. 

• Registration: 

  • Full registration for IEEE BigData 2026 is required for at least one of the authors to participate in the workshop and have the paper published in the proceedings.

Seventh International Workshop on ternational Workshop on Scalable Agentic and Generative Edge Intelligence (SAGE 2026)