2nd Workshop on Inter-networking challenges for AI, collocated with CoNEXT'26
December 2026 (TBA)
Utrecht,
The Netherlands
Utrecht university campus
Utrecht university campus
Utrecht university campus
Utrecht university campus
Utrecht university campus
Utrecht university campus
Call For Papers
AI systems are increasingly distributed across datacenters, wide-area networks, edge platforms, and independently operated domains. Large-scale training pushes beyond the limits of single-site infrastructure; inference and fine-tuning require low-latency, resource-aware placement across heterogeneous compute environments; and agentic AI introduces new patterns of dynamic, multi-party, and often uncoordinated communication.
These developments raise fundamental networking questions. How should networks support AI workloads whose communication patterns differ from traditional cloud traffic? What abstractions, protocols, and measurement methods are needed for wide-area collective communication, distributed inference, edge-core execution, and decentralized AI services? How can such systems provide security, privacy, accountability, and operational trust across administrative boundaries?
The Second INET4AI Workshop at CoNEXT 2026 invites researchers and practitioners from networking, distributed systems, machine learning systems, and AI infrastructure to explore how AI changes the Internet — and how Internet architecture, protocols, and measurement can enable scalable, trustworthy, and efficient distributed AI.
.
Submitted papers must be at most six (6) pages long, excluding references and appendices, in two-column 10pt ACM format. Authors of accepted submissions are expected to present and discuss their work at the workshop. All submissions will be peer-reviewed, and the review process will be double-blind. Per the anonymity guidelines, please prepare your paper in a way that preserves the anonymity of the authors. No information will be shared with third parties.
Please submit your paper using the INET4AI Submission Portal: TBA.-
Workshop paper abstract registration deadline: July 7, 2026.
-
Workshop paper submissions deadline: July 14, 2026.
-
Workshop paper acceptance notification: August 31, 2026.
-
Camera ready due: September 30, 2026.
-
Program available online: October 16, 2026.
Contact
If you have any problems or questions about your paper's submission, please contact us via e-mail at: submit@inet4ai.org
Topics of interest include, but are not limited to:
- Traffic characterization and measurement of distributed AI training, inference, and agentic workloads;
- Wide-area and inter-domain collective communication for AI workloads;
- Transport protocols, congestion control, routing, and load balancing for distributed AI systems;
- In-network processing, aggregation, caching, and computation for large-scale or federated AI;
- Disaggregated and heterogeneous AI training and inference architectures;
- Edge-core distribution, placement, migration, and orchestration of AI workloads;
- Communication-efficient federated, collaborative, and decentralized learning systems;
- Distributed inference systems, including KV-cache distribution, model serving, and multi-node reasoning;
- Security, privacy, authentication, authorization, and accountability in distributed AI communication;
- Decentralized architectures for AI services across administrative domains;
- Agentic networking, including naming, identity, discovery, capability routing, and agent-to-agent communication;
- Measurement, benchmarking, reproducibility, and performance evaluation of distributed AI and agent systems;
- Real-world deployments, operational experience, case studies, governance, and regulation.