Collaborative Device-Cloud LLM Inference through Reinforcement Learning

• URL: http://arxiv.org/abs/2509.24050v1
• Date: Sun, 28 Sep 2025 19:48:56 GMT
• Title: Collaborative Device-Cloud LLM Inference through Reinforcement Learning
• Authors: Wenzhi Fang, Dong-Jun Han, Liangqi Yuan, Christopher Brinton,
• Abstract summary: Device-cloud collaboration has emerged as a promising paradigm for deploying large language models (LLMs)<n>We propose a framework where the on-device LLM makes routing decisions at the end of its solving process, with this capability instilled through post-training.<n>In particular, we formulate a reward problem with carefully designed rewards that encourage effective problem solving and judicious offloading to the cloud.
• Score: 17.71514700623717
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Device-cloud collaboration has emerged as a promising paradigm for deploying large language models (LLMs), combining the efficiency of lightweight on-device inference with the superior performance of powerful cloud LLMs. An essential problem in this scenario lies in deciding whether a given query is best handled locally or delegated to the cloud. Existing approaches typically rely on external routers, implemented as binary classifiers, which often struggle to determine task difficulty from the prompt's surface pattern. To address these limitations, we propose a framework where the on-device LLM makes routing decisions at the end of its solving process, with this capability instilled through post-training. In particular, we formulate a reward maximization problem with carefully designed rewards that encourage effective problem solving and judicious offloading to the cloud. To solve this problem, we develop a group-adaptive policy gradient algorithm, featuring a group-level policy gradient, designed to yield an unbiased gradient estimator of the reward, and adaptive prompt filtering, developed to enforce the constraint on cloud LLM usage. Extensive experiments across models and benchmarks show that the proposed methodology consistently outperforms existing baselines and significantly narrows the gap to full cloud LLM performance.

Related papers

• AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Models [4.4866154758274375]
  In-context learning (ICL) has emerged as a promising paradigm that enables LLMs to adapt to new tasks using examples provided within the input.<n>Previous FL approaches that incorporate ICL have struggled with severe straggler problems and challenges associated with heterogeneous non-identically data.<n>We propose an asynchronous distributed bilevel tuning (AsynDBT) algorithm that optimize both in-context learning samples and prompt fragments based on the feedback from the LLM.
  arXiv  Detail & Related papers  (2026-02-06T13:07:49Z)
• Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference [49.141930185079325]
  We propose an integer linear program (ILP) that determines the optimal placement of experts, minimizing the expected number of transmissions.<n>We demonstrate that ILP-based placement strategy yields lower network traffic than competitors for small-scale (DeepSeekMoE16B) and large-scale (DeepSeek-R1671B) models.
  arXiv  Detail & Related papers  (2025-08-12T07:08:48Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration [1.6021932740447968]
  Large Language Models (LLMs) exhibit remarkable human-like predictive capabilities.<n>It is challenging to deploy LLMs to provide efficient and adaptive inference services at the edge.<n>This paper proposes a novel Cloud-Edge Collaboration framework for LLMs (CE-CoLLM) to tackle these challenges.
  arXiv  Detail & Related papers  (2024-11-05T06:00:27Z)
• AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning [36.37717583840935]
  We propose a novel LLM utilization paradigm that facilitates the collaborative operation of large cloud-based LLMs and smaller local-deployed LLMs. Our framework comprises two primary modules: the local agent instantiated with a relatively smaller LLM, and the cloud agent equipped with a larger LLM. This collaborative processing is enabled through an adaptive mechanism where the local agent introspectively identifies errors and proactively seeks assistance from the cloud agent.
  arXiv  Detail & Related papers  (2024-10-17T03:07:37Z)
• EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty.<n>We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.<n>Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification [76.14641982122696]
  We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. We show that our approach leads to an LLM that produces fewer inappropriate responses while achieving competitive performance on benchmarks and a toxicity detection task.
  arXiv  Detail & Related papers  (2024-10-07T23:38:58Z)
• Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance [0.0]
  Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks. Smaller language models (SLMs), which can be deployed on lower-cost edge devices, struggle to match the performance of their larger counterparts. This paper presents a novel hybrid inference approach that leverages the strengths of both model types.
  arXiv  Detail & Related papers  (2024-09-15T15:12:45Z)
• Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach [18.153641696306707]
  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.
  arXiv  Detail & Related papers  (2024-06-03T09:41:42Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.