AutoResearcHAR: A Multi-Agent Framework for Dataset Adaptive IMU Based Human Activity Recognition
Lala Shakti Swarup Ray, Vitor Fortes Rey, Sizhen Bian, Paul Lukowicz, Bo Zhou
Summary
Treats IMU-HAR as a whole-pipeline optimisation problem run by LLM agents: a Data Agent (source selection, preprocessing, windowing, sampling), a Model Agent (architecture + training choices) and an Augmentation Agent (IMU augmentation and synthetic-data strategies), composed by an Orchestrator, with an LLM-based Judge that filters candidate edits before they are run. Search is iterative hill-climbing over bounded code/config edits, keeping candidates that raise Macro-F1. Evaluated on 10 IMU-HAR datasets (LOSO) and 3 held-out datasets (leave-one-dataset-out): +1.2 to +12.9 Macro-F1 over the best non-agent baselines in LOSO and +2.3 to +8.9 in LODO.
Key facts
- Form Factor
- other
- License
- Not stated
Updated: Oct 12, 2026
Related Research
- Lapras: Latent Reasoning for Time Series Language Models
Post-training framework for time-series language models (TSLMs): instead of verbalising the signal i
- REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without Labels
A gradient-free, label-free input calibration that sits in front of a frozen IMU activity classifier
- SLIP: Learning Transferable Sensor Models via Language-Informed Pretraining
An open-weights (MIT) sensor-language FM that is agnostic to channel count and sampling rate. That s