Can LLMs Be Effective Sensor Processing Copilots?

Pengrui Quan

doi:10.1109/JIOT.2026.3664751

Can LLMs Be Effective Sensor Processing Copilots?

2026-02-13

0

PRE

AI

Jeya Vikranth Jeyakumar

DOI：10.1109/JIOT.2026.3664751

Original

Original request for help

Save

Abstract

En 中文

Effective sensor data processing is critical for cyber-physical and Internet of Things (IoT) systems, but often requires specialized expertise. While large language models (LLMs) show promise as autonomous <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">copilots</i> for sensor processing, their capabilities remain underexplored. We introduce SensorBench, the first comprehensive benchmark for evaluating LLMs across diverse real-world sensor datasets and tasks. SensorBench evaluates three paradigms for leveraging LLMs in sensing tasks: tool-augmented coding (TAC), standalone coding (SAC), and direct answer (DA). We evaluate 8 leading LLM variants, including 2 large reasoning models (LRMs) and 2 domain-specific LLMs, providing a structured reference for absolute performance, latency, and resource requirements. Our analysis reveals that: 1) TAC significantly outperforms SAC and DA; 2) LLMs excel at simple tasks but consistently underperform domain experts on compositional tasks requiring parameter tuning and multistep reasoning; and 3) the reasoning mechanism introduced in LRMs does not yield substantial performance gains. To improve the performance, we explore four prompting strategies and fine-tuning approaches (using our newly released sensor-processing corpus). The results show that self-verification prompting proves most effective, outperforming other methods simultaneously in 48% of tasks, while fine-tuning yields marginal gains. Our analysis suggests that more sophisticated interaction frameworks, such as signal-level self-verification, may bridge the gap to human expert-level performance. This benchmark provides a foundation for evaluating and improving LLMs in sensing applications <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/nesl/LLM_sensor_processing</uri>

Keywords:

Large language model (LLM)

sensor signal processing

Can LLMs Be Effective Sensor Processing Copilots?

Abstract

Journal

Organization