mlsanityData to 7 Oct 2026

Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges

arXiv 2609.04778 ↗First posted 4 Sep 2026cs.AIcited by 0

On the map: Diffusion models → Discrete and text diffusion

also in 2 more
Abstract (arXiv)

Diffusion language models (DLMs) offer a non-autoregressive alternative for mobile edge agentic artificial intelligence (AI) by refining tokens through iterative denoising rather than left-to-right decoding. Compared with autoregressive Transformer-based large language models (LLMs), DLMs can update multiple uncertain tokens in parallel and exploit bidirectional context throughout the generation process, enabling more flexible quality-latency trade-offs beyond fixed sequential decoding. These properties are particularly attractive for edge agents, where partial refinement, early exit, and constraint-guided correction can reduce response delay and communication overhead while improving robustness under noisy, incomplete, or dynamic contexts. This survey reviews DLM foundations and analyzes their suitability for edge settings under latency, memory, energy, bandwidth, privacy, and reliability constraints. We cover resource-efficient architectures, training and inference acceleration, compression, edge/cloud deployment, communication-aware serving, Internet of Things (IoT)/wireless applications, and evaluation of DLM-based agents. We further discuss open issues in long-context state management, split inference, trustworthy execution, multimodal grounding, and reproducible benchmarking. The goal is to connect DLM modeling properties, including bidirectionality, parallel refinement, controllability, and quality-latency elasticity, with system-level requirements of future mobile edge intelligence.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 53 of its 162 references that are in the map. First posted on arXiv 4 Sep 2026.

Builds on

53 of 162 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens12 Jun
  2. 2026Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models15 Apr
  3. 2026Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching26 Feb
  4. 2025From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models26 Nov
  5. 2025CDLM: Consistency Diffusion Language Models For Faster Sampling24 Nov
  6. 2025How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices21 Oct
  7. 2025Dream 7B: Diffusion Large Language Models21 Aug
  8. 2025A Survey on Diffusion Language Models14 Aug
  9. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing8 Aug
  10. 2025Discrete Diffusion in Large Language and Multimodal Models: A Survey16 Jun
  11. 2025Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding22 May
  12. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models17 Oct

Other references · 41

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2023Mistral 7Bcited by 3,065
  7. 2024Mixtral of Expertscited by 1,785
  8. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  9. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  10. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  11. 2024A Survey on Large Language Model Acceleration based on KV Cache Managementcited by 125
  12. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
29 more
  1. 2024Scaling Diffusion Transformers to 16 Billion Parameterscited by 65
  2. 2022Progressive Distillation for Fast Sampling of Diffusion Modelscited by 61
  3. 2025LLaDA-VLA: Vision Language Diffusion Action Modelscited by 30
  4. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  5. 2025Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decodingcited by 26
  6. 2025Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Drivingcited by 24
  7. 2025On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devicescited by 14
  8. 2024Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Modelscited by 11
  9. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  10. 2025MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generationcited by 8
  11. 2025Diffusion Model Quantization: A Reviewcited by 6
  12. 2025Diffusion Models for Future Networks and Communications: A Comprehensive Surveycited by 6
  13. 2026R2-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reductioncited by 6
  14. 2025Diffusion Models on the Edge: Challenges, Optimizations, and Applicationscited by 5
  15. 2024CollaFuse: Collaborative Diffusion Modelscited by 4
  16. 2025Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edgecited by 4
  17. 2025Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computingcited by 3
  18. 2026SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devicescited by 3
  19. 2026HillInfer: Efficient Long-Context LLM Inference on the Edge with Hierarchical KV Eviction using SmartSSDcited by 3
  20. 2026ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Drivingcited by 3
  21. 2026Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Designcited by 2
  22. 2026Markov-Enforced Discrete Diffusion Model for Digital Semantic Symbol Error Correctioncited by 2
  23. 2025Edge-Assisted Collaborative Fine-Tuning for Multi-User Personalized Artificial Intelligence Generated Content (AIGC)cited by 1
  24. 2025DiffusionX: Efficient Edge-Cloud Collaborative Image Generation with Multi-Round Prompt Evolutioncited by 1
  25. 2025Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computingcited by 1
  26. 2026Latent Diffusion for Internet of Things Attack Data Generation in Intrusion Detectioncited by 1
  27. 2026FastUSP: A Multi-Level Collaborative Acceleration Framework for Distributed Diffusion Model Inferencecited by 1
  28. 2026SimpleTool: Parallel Decoding for Real-Time LLM Function Callingcited by 1
  29. 2026Evo: Autoregressive-Diffusion Large Language Models with Evolving Balancecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks
  2. 2023Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities
  3. 2026End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services
  4. 2025Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment
  5. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications
  6. 2026DLLM Agent: See Farther, Run Faster
  7. 2026Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants
  8. 2026A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation