LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents

TL;DR

LLMind 2.0 introduces a distributed IoT automation framework using natural language for M2M communication, enabling scalable, reliable, and responsive device management with lightweight LLM agents and novel coordination protocols.

Contribution

This work presents a novel distributed framework that leverages natural language and lightweight LLMs for scalable IoT device automation, overcoming heterogeneity and centralization limitations.

Findings

Enhanced scalability in IoT systems.

Improved reliability and responsiveness.

Effective device-specific code generation.

Abstract

Recent advances in large language models (LLMs) have generated great interest in their applications for IoT automation and device management. However, centralized approaches struggle to scale across heterogeneous, large-scale systems. We present LLMind 2.0, a distributed framework that embeds lightweight LLM-empowered device agents and adopts natural language for machine-to-machine (M2M) communication. In LLMind 2.0, a central coordinator translates human instructions into natural-language subtask descriptions, which instruct distributed device agents to generate device-specific code locally based on their proprietary APIs. Using natural language as a unified medium overcomes device heterogeneity and enables seamless device collaboration. LLMind 2.0 integrates: 1) a timeout-based deadlock avoidance protocol that coordinates distributed subtask executions, 2) a retrieval-augmented generation (RAG) mechanism for precise subtask-to-API mapping, and 3) fine-tuned lightweight LLMs for reliable, device-specific code generation. Experiments in multi-robot warehouse operations and Wi Fi network deployments show LLMind 2.0 improved scalability, reliability, and responsiveness compared to centralized baselines.