INFOCOM 2026 Workshop on Embodied Intelligence Networks (EIN)
Submissions on network architectures, protocols, algorithms, and systems for embodied and agentic intelligence in virtual and physical environments.
Motivation and Scope
As autonomous and intelligent agents rapidly emerge as a mainstream phenomenon in both virtual environments and the physical world, they interact and collaborate with humans routinely in a multimodal fashion, encompassing physical entities such as collaborative robots, smart glasses, and industrial IoT sensors. These autonomous agents are capable of real-time perception of their surroundings and can take actions — but both their perception and their decisions critically depend on an efficient, low-latency, highly dependable, and adaptive network infrastructure.
In both virtual and physical environments, with the ubiquity of tool use (e.g., via the Model Context Protocol), the ways in which autonomous agents interact and network with one another will inevitably evolve beyond traditional data transport and connectivity, and become an embodied intelligence network with agentic workflows. Such a network resembles an intelligent mesh consisting of actors that communicate with each other by message passing, running agents who are capable of perceiving and adapting to the environment, understanding human intent, coordinating multi-agent activities, and providing semantic communication with real-time control loops.
This workshop aims to provide an interdisciplinary forum for researchers and professionals from academia and industry to exchange ideas concerning the network architectures, protocols, algorithms, and system designs for embodied intelligence networks in the near future. We encourage submissions of forward-looking research, novel system designs, and practical deployment experiences that deeply integrate networking with embodied perception, reasoning, and action. Papers with open-source artifacts — including source code and datasets — are especially welcome and strongly encouraged. The freshness of visionary and forward-looking ideas is more important than the completeness of theoretical proofs, and simplicity may not be inferior to complexity.
Topics of Interest
Submissions are solicited for short technical papers, posters, and demos. Topics of interest include, but are not limited to:
- Semantics-driven network design: Semantic communication, network-aware perception, and intent-aware reasoning for embodied intelligence tasks (e.g., navigation, grasping, collaboration).
- Embodied network architectures and protocols: Next-generation network architectures (e.g., 6G) supporting multimodal data, real-time control loops, and ultra-low-latency requirements.
- Edge computing for distributed embodied intelligence: Joint perception, model training, and inference offloading at the network edge.
- In-network computing and acceleration: Accelerating embodied intelligence models (such as transformer and diffusion models) for inference and training.
- Communication and sensing in embodied networks: Utilizing network signals for environmental sensing and localization.
- Trust and security in embodied intelligence networks: Defences against malicious attacks targeting both embodied agents and network infrastructure.
- Data and privacy preservation: Federated learning, differential privacy, and privacy-preserving analytics in embodied intelligence networks.
- Digital twins and embodied intelligence networks: Using digital twin systems for network simulation and system verification.
- Testbeds for embodied intelligence networks: Design and implementation of testbeds for large-scale multi-agent collaboration and real-world deployment.
- Embodied network simulators and toolchains: Platforms supporting the joint simulation of networking, the physical world, and AI models.
- Real-world deployment experiences: Case studies of real-world deployments, such as smart city traffic, intelligent manufacturing, and disaster relief.
Submission Guidelines
Papers must be formatted in the standard IEEE two-column format used by the INFOCOM 2026 main conference and must not exceed six pages in length, including references.
All submitted papers will undergo single-blind peer review. Accepted papers that are presented by one of the authors at the workshop will be published in the IEEE INFOCOM 2026 proceedings and IEEE Xplore, and will be submitted for inclusion in major abstracting and indexing databases.
Submit your paper at the submission site (via EDAS).
Important Dates
- Submission deadline
- December 29, 2025
- Notification of acceptance
- February 2, 2026
- Camera-ready manuscript due
- February 16, 2026
- Workshop date
- May 18, 2026
Dates are tentative and may follow the final IEEE INFOCOM 2026 schedule; please refer to the workshop website and INFOCOM 2026 announcements for updates.