The theme of EDGE 2026 is:

Agentic AI as a Service for Edge Computing

Agentic AI systems can interpret objectives, construct plans, invoke tools, collaborate with other agents, and execute multi-step tasks. Deploying such systems at the edge enables them to respond to local events, use real-time contextual information, and operate closer to users and physical environments.

For the EDGE community, the central question is:

How can edge platforms host, coordinate, secure, and manage agentic AI as dependable services across the device–edge–cloud continuum?

Edge environments introduce constraints that differ from centralized clouds. Computing resources may be limited and heterogeneous. Network connectivity may vary. Devices and users may move. Decisions may need to be made within strict latency, energy, privacy, or safety limits.

Agentic AI is transforming edge computing:

·       From centralized intelligence to distributed edge intelligence

·       From stateless requests to persistent, context-aware agents

·       From best-effort processing to real-time task completion

·       From transferring raw data to privacy-preserving local processing

·       From isolated edge nodes to collaborative agent and edge federations

·       From fixed deployment to adaptive placement, offloading, and migration

·       From cloud-only execution to coordinated device–edge–cloud operation

EDGE 2026 invites researchers and practitioners to develop the distributed computing foundations required for responsive, efficient, secure, and trustworthy agentic services at the edge.

EDGE focuses on computing architectures, platforms, runtimes, resource management, networking, storage, security, and applications located near data sources and users.

Research whose primary contribution concerns centralized cloud infrastructure, IoT devices and sensing networks, AI model development, general service engineering, Web protocols, or big-data analytics should be submitted to the corresponding SCF conference unless it makes a clear systems contribution to edge computing.

Topics include, but are not limited to:

1. Agentic AI at the Edge

·       Edge-native agents and agentic edge services

·       Edge runtimes for context-aware and tool-using agents

·       Distributed and collaborative edge agents

·       Local memory, perception, planning, and execution

·       Split and collaborative AI across devices, edge, and cloud

·       Evaluation and management of agentic edge workloads

2. Edge Architectures and Platforms

·       Edge, fog, and multi-access edge computing architectures

·       Device–edge–cloud computing continua

·       Federated and hierarchical edge platforms

·       Containers, serverless computing, and lightweight virtualization at the edge

·       Edge service placement, migration, and orchestration

·       Programmable and software-defined edge systems

3. Edge Resource Management

·       Resource discovery, allocation, scheduling, and provisioning

·       Computation offloading and workload placement

·       CPU-, GPU-, and NPU-aware edge scheduling

·       Latency-, energy-, cost-, and context-aware optimization

·       Multitenancy, performance isolation, and admission control

·       Adaptive management of heterogeneous edge resources

4. Edge Networking, Storage, and Data Processing

·       Edge networking and low-latency communication

·       5G/6G and mobile edge computing

·       Edge storage, caching, and content delivery

·       Mobility-aware and intermittently connected edge systems

·       Real-time data processing and streaming at the edge

·       Network–compute coordination and optimization

5. Edge Reliability, Security, and Privacy

·       Fault tolerance, resilience, and self-healing edge systems

·       Edge monitoring, observability, and diagnostics

·       Identity, trust, authentication, and access control

·       Secure execution, isolation, and remote attestation

·       Privacy-preserving and federated edge processing

·       Security and safety of agentic edge systems

6. Edge Applications and Experimental Practice

·       Industrial and manufacturing edge systems

·       Connected vehicles, mobility, and transportation

·       Robotics, embodied systems, and real-time control

·       Healthcare, smart spaces, and urban applications

·       Extended reality, media, and interactive edge services

Edge testbeds, benchmarks, deployments, and industry experience

The EDGE 2026 technical program includes four submission tracks.

Research Track

The Research Track welcomes original and technically rigorous contributions that advance edge-computing architectures, systems, algorithms, runtimes, networking, or resource management.

Research papers should:

·       Clearly define the edge-computing problem

·       Explain the novelty relative to relevant literature

·       Present technically sound methods or system designs

·       Use appropriate workloads, baselines, and performance metrics

·       Provide rigorous and reproducible evaluation

·       Discuss limitations and threats to validity

·       Demonstrate a generalizable edge-computing contribution

Application and Industry Track

The Application and Industry Track focuses on deployed edge systems, operational solutions, industrial platforms, testbeds, and evidence-based implementation experience.

Papers should:

·       Describe a significant real-world edge-computing problem

·       Explain the architecture and implementation

·       Present deployment evidence or measurable outcomes

·       Discuss latency, resource, connectivity, reliability, security, and energy constraints

·       Identify lessons that can be transferred to other environments

·       Clarify the practical or system-level innovation

Papers in this track do not need to introduce a new algorithm. However, they should contribute through edge-system architecture, deployment evidence, performance improvement, operational innovation, or generalizable engineering knowledge.

Short Paper Track

The Short Paper Track welcomes focused contributions, including:

·       Promising early-stage edge research

·       Novel architectures or system concepts

·       Emerging challenges and research visions

·       Testbeds, benchmarks, tools, and reusable artifacts

·       Focused empirical findings or negative results

·       Concise deployment and operational reports

Short papers must clearly state their contribution, evidence, relationship to prior work, and limitations.

Special Paper Track

The Special Paper Track addresses designated emerging topics and community priorities announced by EDGE 2026. Submissions should follow the requirements of the corresponding special-track call.

All submissions must report original and unpublished work and must not be under review elsewhere at the time of submission.

Each manuscript will be reviewed by at least three program committee members. Papers will be evaluated according to:

·       Relevance to EDGE

·       Originality and significance

·       Technical or practical quality

·       Strength of evaluation

·       Clarity and organization

·       Reproducibility

·       Research or operational impact

Papers should position their contributions accurately within the relevant international literature. Authors are encouraged to cite EDGE and other conferences or journals when genuinely relevant. Citation of any particular venue is not required.

Research Track and Application and Industry Track manuscripts are limited to 15 pages in the Springer LNCS format. Short Paper Track manuscripts are limited to 8 pages. Authors may purchase up to two additional pages, subject to the applicable publication fee. Special Paper Track submissions should follow the limits specified in the corresponding call.

Authors must use the official Springer LNCS templates:

·       Microsoft Word template

·       LaTeX template

Electronic submission in PDF or Word format is required. Manuscripts that do not follow the required format or exceed the permitted page limit may be returned without review.

A Research Track submission that primarily presents a deployed application or operational solution may be recommended for consideration by the Application and Industry Track.

At least one author of each accepted paper must register for EDGE 2026 and present the paper at the conference.

EDGE 2026 will recognize outstanding contributions through:

·       Best Paper Award

·       Best Student Paper Award

For the Best Student Paper Award, the first author must be a full-time student.

EDGE has developed alongside the movement of computation from centralized data centers toward networks, gateways, local servers, access points, vehicles, and user devices. Its scope has expanded from localized resource sharing to distributed intelligence across the device–edge–cloud continuum.

Recent EDGE conferences were held in Seattle in 2018, San Diego in 2019, virtually in 2020 and 2021, Hawaii in 2022, Shenzhen in 2023, Bangkok in 2024, and Hong Kong in 2025.

EDGE 2026 continues this development by examining how agentic intelligence can operate close to data, users, and physical environments.

EDGE is a member of the Smart Computing Frontier, a federation of ten co-located international conferences.

Within SCF, EDGE focuses on distributed computing systems located near data sources and users, including edge architectures, runtimes, resource management, networking, security, and edge applications.

Its scope is complementary to the other SCF conferences:

·       ICWS focuses on Web interfaces, APIs, protocols, and Web-based services.

·       SCC focuses on service engineering, lifecycle management, and value creation.

·       CLOUD focuses on centralized and federated cloud infrastructure and platforms.

·       BigData focuses on large-scale data systems and analytics.

·       AIMS focuses on AI models, multimodal intelligence, and AI-enabled services.

·       ICIOT focuses on connected devices, sensing, communication, and IoT systems.

·       ICCC focuses on cognitive computing.

·       ICBC focuses on blockchain technologies and trusted ecosystems.

·       METAVERSE focuses on immersive and persistent digital environments.

This structure enables cross-conference collaboration while preserving EDGE’s distinctive identity as the conference devoted to edge-computing systems and distributed intelligence.