Search papers, labs, and topics across Lattice.
SensingAgents, a novel multi-agent system, is introduced to enhance IMU-based Human Activity Recognition (HAR) by leveraging LLMs in specialized roles for sensor analysis, conflict resolution, and decision-making. The system employs Analyst Agents for position-specific sensor data interpretation, Advocate Agents for resolving conflicts through debates, and a Decision Agent for ensuring reliability. Evaluated on the Shoaib dataset, SensingAgents achieves a 79.5% accuracy in a zero-shot setting, outperforming existing agent models by 29% and deep learning baselines by 9.4%, demonstrating improved robustness and interpretability in HAR.
LLM-powered multi-agent collaboration can boost zero-shot IMU activity recognition accuracy by 29% compared to existing agent models, even surpassing deep learning baselines.
Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is a cornerstone of mobile health, smart environments, and human-computer interaction. However, current deep learning-based HAR models often struggle with heavy reliance on labeled data, position-specific ambiguity, and a lack of transparent reasoning. Inspired by the advanced agents framework, which emulates a collaborative agent using Large Language Models (LLMs), we propose SensingAgents, a novel multi-agent system for robust IMU activity recognition. SensingAgents organizes LLM-powered agents into specialized roles: a group of Analyst Agents for position-specific sensor analysis (arm, wrist, belt, pocket), a pair of Advocate Agents that resolves sensor conflicts through dynamic and static dialectical debates, and a Decision Agent that ensures reliability under sensor drift or failure. Evaluation on the Shoaib dataset demonstrates that SensingAgents significantly outperforms state-of-the-art single-agent and multi-agent LLM models, achieving an accuracy of 79.5% in a zero setting--29% higher than existing agent models and 9.4% higher than deep learning baselines--particularly in complex scenarios where multi-sensor data is conflicting or noisy. Our work highlights the potential of multi-agent collaborative reasoning for advancing the robustness and interpretability of ubiquitous sensing systems.
