Call for Papers

SNAI 2026 · 3rd Symposium on Networking and Artificial Intelligence · 7–9 December 2026, Barcelona, Spain

SNAI 2026 invites original research contributions on the two-way intersection of computer networking and artificial intelligence. Papers are reviewed double-blind by at least three independent reviewers, with author rebuttal and a dedicated artifact evaluation track.

Submit a paper

The SNAI 2026 submission system is provided by LiteConf. All submissions, reviews, and rebuttals are managed through the platform.

Open submission system →

Important dates

Workshop & tutorial proposals
26 June 2026
Paper submission deadline
21 August 2026 (23:59 AoE)
Reviews released to authors
2 October 2026
Author rebuttal
2–9 October 2026
Acceptance notification
16 October 2026
Camera-ready due
6 November 2026
Conference
7–9 December 2026

Submission categories

  • Full papers (8 pages + references): original research contributions with comprehensive evaluation.
  • Short papers (4 pages + references): preliminary results, system experiences, position papers, or negative results.
  • Artifact submissions (optional, 2 pages): code, datasets, and measurement traces supporting a submitted paper.

Track 1 — AI-Native 6G and Next-Generation Networks

Learning-driven radio access, intelligent resource allocation, network slicing, AI-native architecture for 6G and beyond, semantic and goal-oriented communication, and AI for end-to-end network orchestration.

Track 2 — LLM Agents for Network Operations

Large language model agents for configuration synthesis, troubleshooting, incident response, intent translation, root-cause analysis, and operator-facing AI tooling. Reasoning, planning, tool use, and human-in-the-loop evaluation.

Track 3 — Edge and In-Network Intelligence

Model placement and partitioning across the edge and the data plane, in-switch and SmartNIC inference, line-rate feature extraction, latency-aware serving, and hardware-software co-design for in-network ML.

Track 4 — Distributed and Federated Learning over Networks

Communication-efficient and privacy-preserving training, gradient compression and quantization, federated learning under heterogeneous and bandwidth-constrained links, straggler mitigation, and decentralized training over peer-to-peer topologies.

Track 5 — Machine Learning for Network Security

Intrusion and anomaly detection, encrypted-traffic classification, attack attribution, evasion and adversarial robustness, and large-scale measurements of malicious traffic.

Track 6 — Networking Systems for Large-Scale AI Training

Collective communication, RDMA and lossless fabrics, congestion control for AI workloads, topology design and topology-aware scheduling, training-cluster reliability, and the systems that sustain trillion-parameter training.

Track 7 — Datasets, Benchmarks and Reproducibility

Open datasets and measurement traces, evaluation methodology, reproducibility studies, artifact evaluation, and benchmarking infrastructure for the networking/AI community.

Review process

All papers are reviewed double-blind. Authors must anonymize their submission, including references phrased in the third person. Each paper receives at least three independent reviews. Authors may respond to reviewers during the rebuttal period. The program chairs will resolve disagreements and may consult additional reviewers for borderline cases.

Publication and indexing

Accepted papers will be published in the open-access SNAI 2026 proceedings, archived in the LiteConf repository, and assigned DOIs. Authors retain copyright. The proceedings will be submitted to major indexing services. Authors of the strongest submissions will be invited to submit extended versions to a special issue of an associated journal.

Double-blind policies

  • Remove author names, affiliations, and acknowledgments from the submitted PDF.
  • Phrase self-citations in the third person ("Prior work [12] showed...") rather than "Our prior work [12]...".
  • Do not include hyperlinks that reveal identity (e.g. personal webpages, GitHub organisations named after the author).
  • Pre-prints already on arXiv are permitted but should be cited as a third-party work, not linked from the submission text.

Conflicts of interest

Authors are asked to declare conflicts of interest for the program committee during submission. A conflict exists when an author is at the same institution as a potential reviewer, has co-authored with them in the past two years, or has a personal relationship. The submission system will surface the declared conflicts to the program chairs.

Contact

For questions about the call, contact the program chairs at [email protected].