---
id: 20260929-T0-09
title: "HybridInfer：面向端-边-云LLM推理的热感知强化学习分层路由"
title_en: "HybridInfer: Thermal-Aware RL Tier Routing for On-Device, Edge, and Cloud LLM Inference"
url: https://ai.daily.yangsir.net/daily/20260929-T0-09
issue_date: 2026-09-29
publish_date: 2026-09-28T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2609.30270
---

# HybridInfer：面向端-边-云LLM推理的热感知强化学习分层路由

arXiv上一篇新论文提出HybridInfer方法，针对端侧、边缘和云端协同的大语言模型推理场景，解决设备端推理受热约束影响的问题。端侧小模型推理能保护数据隐私、支持离线运行且无单次查询成本，但热限制比预期更严格。该方法利用热感知强化学习动态决定推理任务在端、边、云各层间的路由分配，以在满足热约束的同时优化性能。这对提升移动端和边缘设备上LLM部署的实用性和能效具有实际意义。

## English Version

**HybridInfer: Thermal-Aware RL Tier Routing for On-Device, Edge, and Cloud LLM Inference**

A new arXiv paper introduces HybridInfer, addressing thermal constraints in on-device LLM inference across on-device, edge, and cloud tiers. On-device small-model inference preserves privacy, works offline, and has no per-query cost, but thermal limits are tighter than expected. HybridInfer uses thermal-aware reinforcement learning to dynamically route inference tasks across device, edge, and cloud to optimize performance under thermal constraints. This work has practical implications for improving the viability and energy efficiency of LLM deployment on mobile and edge devices.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2609.30270)

**详情页**：https://ai.daily.yangsir.net/daily/20260929-T0-09

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*