Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2508.13920

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

Yuyang Du·Qun Yang·Liujianfu Wang·Jingqi Lin·Hongwei Cui·Soung Chang Liew
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

eess.SYcs.SY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yuyang Du, Qun Yang, Liujianfu Wang, Jingqi Lin, Hongwei Cui, Soung Chang Liew. 2026-02-17. LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents. https://arxiv.org/abs/2508.13920

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Simultaneous state estimation and control for nonlinear systems subject to bounded disturbances

In this work, we address the output--feedback control problem for nonlinear systems under bounded disturbances using a moving horizon approach. The controller is posed as an optimisation-based problem that simultaneously estimates the state trajectory and computes future control inputs. It minimises a criterion that involves finite backward and forward horizons with respect to the unknown initial state, measurement noises and control input variables.The main novelty of this work relies on linking the lengths of the forward and backward windows with the closed-loop stability, assuming detectability and decoding sufficient conditions to assure system stabilizability. It leads to a formulation that does not require to be a Control Lyapunov Function for the terminal cost of the controller. Simulation examples are carried out to compare the performance of solving simultaneously and independently the estimation and control problems. Furthermore, the examples show how the controller influences the length of the estimation window through its gain.

eess.SY↗
arXiv2026

On finite-horizon approximation of an infinite-horizon feedback Nash equilibrium in discrete-time LQ games

Computing feedback Nash equilibria (FNEs) in infinite-horizon discrete-time linear-quadratic (LQ) dynamic games remains computationally challenging. Inspired by model predictive control (MPC) in single-agent optimal control, we address this challenge with a finite-horizon strategy for approximating one such FNE. The finite-horizon strategy is as follows. Each player $i$ has an individual prediction horizon $T^i$. At each stage, player $i$ envisions an auxiliary $T^i$-stage game, computes its unique FNE, and implements only the first-stage control. Our main results are as follows. First, we give parameter conditions that guarantee geometric convergence of the coupled Riccati iteration to a stabilizing solution. Second, under these conditions, the finite-horizon strategies stabilize the system, and each player's total cost converges to the limiting FNE cost as all prediction horizons tend to infinity. Third, we derive an explicit upper bound on this cost gap that decreases geometrically with the shortest prediction horizon. This bound tells us how long the prediction horizons need to be for a given accuracy. The strategy is tractable and implementable, as it avoids directly solving the coupled algebraic Riccati equations of the infinite-horizon game.

eess.SY↗
arXiv2026

Closed Loop Reference Optimization for Extrusion Additive Manufacturing

Various defects occur during material extrusion additive manufacturing processes that degrade the quality of the 3D printed parts and lead to significant material waste. This motivates feedback control of the extrusion process to mitigate defects and prevent print failure. We propose a linear quadratic regulator (LQR) for closed-loop control with force feedback to provide accurate width tracking of the extruded filament. Furthermore, we propose preemptive optimization of the reference force given to the LQR that accounts for the performance of the LQR and generates the optimal reference for the closed loop extrusion dynamics and machine constraints. Simulation results demonstrate the improved tracking performance and response time. Experiments on a Fused Filament Fabrication 3D printer showcase a root mean square error improvement of 39.57% compared to tracking the unmodified reference as well as an 83.7% shorter settling time.

eess.SY↗