LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917278134566912 |
|---|---|
| author | Du, Yuyang Yang, Qun Wang, Liujianfu Lin, Jingqi Cui, Hongwei Liew, Soung Chang |
| author_facet | Du, Yuyang Yang, Qun Wang, Liujianfu Lin, Jingqi Cui, Hongwei Liew, Soung Chang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13920 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents Du, Yuyang Yang, Qun Wang, Liujianfu Lin, Jingqi Cui, Hongwei Liew, Soung Chang Systems and Control 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. |
| title | LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2508.13920 |