MLN 2026 is the 9th International Conference on Machine Learning for Networking. The conference brings together researchers, practitioners, engineers, and industry experts working at the intersection of artificial intelligence, machine learning, communication networks, and distributed systems. MLN 2026 aims to foster multidisciplinary exchanges on the design, operation, optimization, security, and evolution of intelligent networks, as well as on the networking infrastructures required to support emerging AI systems. The conference welcomes original research contributions, experimental studies, system and prototype descriptions, industry experiences, datasets, benchmarks, and survey papers. MLN 2026 will be held in Paris, France, from December 1st to December 3rd, 2026.

Artificial intelligence and machine learning are transforming the way communication networks are designed, deployed, operated, secured, and optimized. At the same time, the rapid development of foundation models, generative AI, agentic systems, and large-scale distributed learning is creating new networking requirements in terms of performance, scalability, reliability, energy efficiency, privacy, and security. MLN 2026 provides an international forum for presenting and discussing advances at the intersection of machine learning and networking. The scope of the conference encompasses two complementary perspectives:

AI and machine learning for networks: the use of intelligent methods to analyze, automate, optimize, secure, and manage communication and distributed systems.
Networks and distributed systems for AI: the design of communication infrastructures, protocols, architectures, and resource- management mechanisms that support AI training, inference, agent collaboration, and intelligent services.
MLN 2026 encourages contributions that combine methodological advances with networking applications, as well as interdisciplinary work spanning artificial intelligence, telecommunications, distributed computing, cybersecurity, operations research, control, and data science.

Authors are invited to submit complete unpublished papers, which are not under review in any other conference or journal, to https://easychair.org/conferences/?conf=mln2026.

The accepted papers will be published as a post-proceedings in Springer's LNCS. Lecture Notes in Computer Science (LNCS) series is indexed by the ISI Conference Proceedings Citation Index - Science (CPCI-S), included in ISI Web of Science, EI Engineering Index (Compendex and Inspec databases), ACM Digital Library, dblp, Google Scholar, Scopus, etc.

Topics of interest include and are not limited to:

Machine Learning and Artificial Intelligence for Networks
Deep, reinforcement, graph, federated, and distributed learning
Traffic prediction, anomaly detection, routing, and resource allocation
Machine learning for 5G, 6G, IoT, satellite, and wireless networks
Intelligent SDN, NFV, cloud, edge, and service orchestration
Energy-efficient and sustainable communications

Agentic AI and Autonomous Network Management
Agentic AI for network operations and optimization
Autonomous, zero-touch, and intent-based networks
Multi-agent coordination and collaboration
AI agents for control, fault detection, and remediation
Human-in-the-loop automation, safety, and governance

Generative AI, Foundation Models, and Network Digital Twins
Large language models and foundation models for networking
Generative AI for network design and management
RAG, knowledge graphs, and natural-language interfaces
Network digital twins and synthetic data generation
Multimodal and resource-efficient models for cloud and edge

Networking and Distributed Systems for AI
Networks for distributed AI training and inference
Data-center, cloud, edge, and high-performance AI networking
Efficient federated learning and collaborative inference
Joint optimization of communication, computing, and energy
Architectures and protocols for AI-agent ecosystems

Security, Trustworthiness, Experimentation, and Applications
Machine learning for network security and resilience
Adversarial AI and security of autonomous agents
Explainable, trustworthy, and privacy-preserving AI
Datasets, benchmarks, testbeds, and real-world deployments
Intelligent applications for smart and critical systems

Position papers are also welcome and should be clearly marked as such.