# Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach

arXiv: https://arxiv.org/abs/2406.02616 · HTML: https://mlsanity.com/paper/2406.02616/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 65 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Applications of Deep Reinforcement Learning in Communications and Networking: A Survey](https://mlsanity.com/paper/1810.07862/) (2018)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [Wider and Deeper LLM Networks are Fairer LLM Evaluators](https://mlsanity.com/paper/2308.01862/) (2023)
- [Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities](https://mlsanity.com/paper/2309.16739/) (2023)
- [Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache](https://mlsanity.com/paper/2401.02669/) (2024)
- [Split Learning in 6G Edge Networks](https://mlsanity.com/paper/2306.12194/) (2023)
- [Mobile Edge Computing: A Survey on Architecture and Computation Offloading](https://mlsanity.com/paper/1702.05309/) (2017)
- [Scalable Multi-Agent Model-Based Reinforcement Learning](https://mlsanity.com/paper/2205.15023/) (2022)
- [The Landscape and Challenges of HPC Research and LLMs](https://mlsanity.com/paper/2402.02018/) (2024)
- [A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art](https://mlsanity.com/paper/1906.08452/) (2019)

## Built on by (most cited first, 12 of 12)

- [Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs](https://mlsanity.com/paper/2510.16062/) (2025)
- [The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks](https://mlsanity.com/paper/2505.09214/) (2025)
- [DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey](https://mlsanity.com/paper/2503.09956/) (2025)
- [Malware Detection at the Edge with Lightweight LLMs: A Performance Evaluation](https://mlsanity.com/paper/2503.04302/) (2025)
- [Dual-Mind World Models: A General Framework for Learning in Dynamic Wireless Networks](https://mlsanity.com/paper/2510.24546/) (2025)
- [Intelligent Orchestration of Distributed Large Foundation Model Inference at the Edge](https://mlsanity.com/paper/2504.03668/) (2025)
- [Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI](https://mlsanity.com/paper/2512.01039/) (2025)
- [Quantization-Aware Collaborative Inference for Large Embodied AI Models](https://mlsanity.com/paper/2602.13052/) (2026)
- [Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks](https://mlsanity.com/paper/2602.07215/) (2026)
- [Privacy-Aware Split Inference with Speculative Decoding for Large Language Models over Wide-Area Networks](https://mlsanity.com/paper/2602.16760/) (2026)
- [Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States](https://mlsanity.com/paper/2603.03146/) (2026)
- [Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing](https://mlsanity.com/paper/2606.22496/) (2026)

## Abstract (arXiv)

Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. On this basis, this study introduces a framework taking inspiration from model-based reinforcement learning (MBRL) to determine the optimal splitting point across the edge and user equipment (UE). By incorporating a reward surrogate model, our approach significantly reduces the computational cost of frequent performance evaluations. Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions, providing a robust solution for LLM deployment in decentralized settings.