Papers
arxiv:2508.04038

ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

Published on Aug 6
· Submitted by Breezelled on Aug 20
Authors:
,

Abstract

ZARA is an agent-based framework for zero-shot, explainable human activity recognition from raw motion time-series, achieving state-of-the-art performance without fine-tuning.

AI-generated summary

Motion sensor time-series are central to human activity recognition (HAR), with applications in health, sports, and smart devices. However, existing methods are trained for fixed activity sets and require costly retraining when new behaviours or sensor setups appear. Recent attempts to use large language models (LLMs) for HAR, typically by converting signals into text or images, suffer from limited accuracy and lack verifiable interpretability. We propose ZARA, the first agent-based framework for zero-shot, explainable HAR directly from raw motion time-series. ZARA integrates an automatically derived pair-wise feature knowledge base that captures discriminative statistics for every activity pair, a multi-sensor retrieval module that surfaces relevant evidence, and a hierarchical agent pipeline that guides the LLM to iteratively select features, draw on this evidence, and produce both activity predictions and natural-language explanations. ZARA enables flexible and interpretable HAR without any fine-tuning or task-specific classifiers. Extensive experiments on 8 HAR benchmarks show that ZARA achieves SOTA zero-shot performance, delivering clear reasoning while exceeding the strongest baselines by 2.53x in macro F1. Ablation studies further confirm the necessity of each module, marking ZARA as a promising step toward trustworthy, plug-and-play motion time-series analysis. Our codes are available at https://github.com/zechenli03/ZARA.

Community

Paper author Paper submitter
This comment has been hidden

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.04038 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.04038 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.04038 in a Space README.md to link it from this page.

Collections including this paper 1