Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2025.074384
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

LEAF: A Lightweight Edge Agent Framework with Expert SLMs for the Industrial Internet of Things

Qingwen Yang1, Zhi Li2, Jiawei Tang1, Yanyi Liu1, Tiezheng Guo1, Yingyou Wen1,*
1 School of Computer Science and Engineering, Northeastern University, Shenyang, 110169, China
2 School of Information Science and Engineering, Shenyang Ligong University, Shenyang, 110159, China
* Corresponding Author: Yingyou Wen. Email: email
(This article belongs to the Special Issue: Intelligent Computation and Large Machine Learning Models for Edge Intelligence in industrial Internet of Things)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.074384

Received 10 October 2025; Accepted 23 December 2025; Published online 05 January 2026

Abstract

Deploying Large Language Model (LLM)-based agents in the Industrial Internet of Things (IIoT) presents significant challenges, including high latency from cloud-based APIs, data privacy concerns, and the infeasibility of deploying monolithic models on resource-constrained edge devices. While smaller models (SLMs) are suitable for edge deployment, they often lack the reasoning power for complex, multi-step tasks. To address these issues, this paper introduces LEAF, a Lightweight Edge Agent Framework designed for efficiently executing complex tasks at the edge. LEAF employs a novel architecture where multiple expert SLMs—specialized for planning, execution, and interaction—work in concert, decomposing complex problems into manageable sub-tasks. To mitigate the resource overhead of this multi-model approach, LEAF implements an efficient parameter-sharing scheme based on Scalable Low-Rank Adaptation (S-LoRA). We introduce a two-stage training strategy combining Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) to significantly enhance each expert’s capabilities. Furthermore, a Finite State Machine (FSM)-based decision engine orchestrates the workflow, uniquely balancing deterministic control with intelligent flexibility, making it ideal for industrial environments that demand both reliability and adaptability. Experiments across diverse IIoT scenarios demonstrate that LEAF significantly outperforms baseline methods in both task success rate and user satisfaction. Notably, our fine-tuned 4-billion-parameter model achieves a task success rate over 90% in complex IIoT scenarios, demonstrating LEAF’s ability to deliver powerful and efficient autonomy at the industrial edge.

Keywords

Industrial internet of things; edge computing; LLM-based agents; small language models

  • 125

    View

  • 46

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link