ADeCoS 2026
First International Workshop on
Agentic and Decentralized Coordination for Softwarized Networks
Overview
Future softwarized networks are evolving toward highly decentralized and multi-domain operation. While Software-Defined Networking (SDN), Network Functions Virtualization (NFV), and cloud-native platforms enabled programmability, centralized orchestration is increasingly limited in terms of scalability, responsiveness, resilience, and trust.
ADeCoS 2026 aims to shape the next generation of AI-native and decentralized network control, where agentic AI systems autonomously coordinate decisions across domains, stakeholders, and layers of the network. These systems go beyond traditional automation by incorporating goal-driven behavior, adaptive communication, and context-aware decision-making.
The workshop focuses on fundamental and practical challenges in enabling such systems, including multi-agent coordination, intent-to-action translation, learning and planning under uncertainty, and policy-aware control with built-in safety and verification mechanisms.
Despite recent advances in AI-driven network management, scalable and trustworthy decentralized coordination across domains remains largely unresolved. ADeCoS 2026 aims to address this gap by bringing together researchers and practitioners from networking, distributed systems, and AI.
The workshop emphasizes realistic deployments, experimental validation, and reproducibility, fostering new directions toward trustworthy, scalable, and autonomous network infrastructures.
Agentic AI
Goal-driven systems with adaptive communication and context-aware decision-making
Decentralized Control
Multi-domain coordination without centralized orchestration bottlenecks
Autonomous Networks
Self-managing infrastructure with real-time adaptation capabilities
Trustworthy Systems
Policy-aware control with built-in safety and verification mechanisms
Topics of Interest
Non-exhaustive list
Call for Papers
We invite original and unpublished contributions on agentic AI and decentralized coordination for softwarized networks. Contributions may include theoretical advances, system designs, algorithms, prototypes, and experimental evaluations. We particularly encourage submissions demonstrating practical relevance and real-world applicability.
Each submission will receive at least 3 independent reviews.
Evaluation criteria include:
- Originality
- Technical quality
- Clarity
- Relevance to workshop topics
Important Dates
Paper Submission Deadline
April 8, 2026Notification of Acceptance
April 24, 2026Camera-Ready Deadline
May 4, 2026Workshop Date
June 29, 2026How to Submit
Prepare Your Manuscript
Format your paper using the IEEE two-column conference format (maximum 7 pages including references)
Submit via EDAS
Upload your manuscript through the EDAS submission system
Select the Workshop
Choose ADeCoS 2026 from the workshop list during submission
Program
Workshop Opening
9:00 - 9:05Keynote Session
9:05 - 9:40Agentic AI for Networks: Architectures, Challenges, and Research Frontiers
Professor Badii Jouaber (Télécom SudParis, Institut Polytechnique de Paris, France)
Technical Session 1
9:40 - 10:30Decentralized Control and Agentic Orchestration of Softwarized Infrastructures
- 1. Blockchain for SDN Control: Exploring the Trade-off Between Security and PerformanceAndrei Danila (Universite de Lorraine, France); Loic Desgeorges (Universite Claude Bernard Lyon 1, France); Guilain Leduc (University of Luxembourg, Luxembourg); Dongyu Zhang (ENS de Lyon, France); Jean-Philippe Georges (University of Lorraine, France)
- 2. Edgent: Towards an Agentic AI Framework for eBPF-based Service Deployment and Orchestration at the EdgeRaffaele Di Tommaso (University of Bologna, Italy); Gianluca Davoli (University of Bologna, Italy); Pietro Spadaccino (La Sapienza Universita di Roma, Italy); Walter Cerroni (University of Bologna, Italy)
Coffee Break
10:30 - 11:00Technical Session 2
11:00 - 12:15Intent-driven Agentic Coordination for Network Management
- 3. IntentNEF: LLM-Driven Natural Language Automation of 5G Network ExposureHaoyu You (University of Sussex, UK); Chathura Galkandage (University of Sussex, UK); Naercio Magaia (University of Sussex, UK); Maziar Nekovee (University of Sussex & Samsung, UK); Simon Davies (Honda, UK)
- 4. LLM-Assisted Design and Analytics of Next-Generation Optical Transport NetworksImran Chowdhury Dipto (Politecnico di Torino, Italy); Sanwal Zeb (Politecnico di Torino, Italy); Muhammad Umar Masood (Politecnico di Torino, Italy); Ihtesham Khan (Nokia Bell Labs, USA); Nelson Costa (Nokia, Germany); Joao Pedro (Nokia Portugal & Instituto de Telecomunicacoes, Portugal); Antonio Napoli (Nokia, Germany); Vittorio Curri (Politecnico di Torino, Italy)
- 5. A GenAI-Driven Multi-Agent Framework for Explainable Intent-Based Slice RecommendationRui Ferreira (University of Minho & Capgemini Engineering, Portugal); Raul F. D. Barbosa (Universidade de Aveiro, Portugal); Marco Araujo (Portucalense University, Portugal); Petia Georgieva (University of Aveiro, DETI/IEETA, Portugal); Susana Sargento (Universidade de Aveiro, Portugal); Anabela Pereira Tereso (University of Minho, Portugal); Paulo Novais (University of Minho, Portugal); Pedro Rito (University of Aveiro & Instituto de Telecomunicacoes, Portugal); Bruno Miguel Fonseca Mendes (University of Aveiro, Portugal)