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.
@article{arxiv.2508.13920,
title = {LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents},
author = {Yuyang Du and Qun Yang and Liujianfu Wang and Jingqi Lin and Hongwei Cui and Soung Chang Liew},
journal= {arXiv preprint arXiv:2508.13920},
year = {2026}
}