# RAG-HAR+: Towards Cost-Efficient LLM-Based Human Activity Recognition for Edge Deployment

arXiv: https://arxiv.org/abs/2607.26631 · HTML: https://mlsanity.com/paper/2607.26631/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 12 of 12)

- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?](https://mlsanity.com/paper/2403.02727/) (2024)
- [SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition](https://mlsanity.com/paper/2410.10624/) (2024)
- [Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data](https://mlsanity.com/paper/2403.01133/) (2024)
- [Unsupervised Human Activity Recognition through Two-stage Prompting with ChatGPT](https://mlsanity.com/paper/2306.02140/) (2023)
- [Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition](https://mlsanity.com/paper/2110.12163/) (2021)
- [RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition](https://mlsanity.com/paper/2512.08984/) (2025)
- [Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition](https://mlsanity.com/paper/2211.06173/) (2022)
- [Towards LLM-Powered Ambient Sensor Based Multi-Person Human Activity Recognition](https://mlsanity.com/paper/2407.09529/) (2024)
- [A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning](https://mlsanity.com/paper/2507.01976/) (2025)

## Built on by (most cited first, 2 of 2)

- [More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev](https://mlsanity.com/paper/2609.36154/) (2026)
- [CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition](https://mlsanity.com/paper/2610.15298/) (2026)

## Abstract (arXiv)

Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments. Yet, existing deep learning approaches require dataset-specific training, large labeled corpora, and repeated adaptation to new sensor settings or activity taxonomies. Retrieval-Augmented Generation for Human Activity Recognition (RAG-HAR) addresses this by framing HAR as a training-free, retrieval-augmented task, in which statistical descriptions of sensor windows are used to retrieve similar labeled examples that guide LLM-based classification. We introduce RAG-HAR+, a retrieval-first and cost-optimized extension that strengthens retrieval while reducing dependence on LLM-based inference. RAG-HAR+ uses an offline Retrieval Designer Agent to design dataset-specific feature groups from a diverse pool of motion descriptors, enabling sensor windows to be compared using features better aligned with dataset-specific activity patterns. During inference, RAG-HAR+ uses majority voting over retrieved neighbors for samples with strong retrieval evidence and defers only uncertain cases to an LLM-based Ambiguity Resolver Agent. Across six HAR benchmarks, RAG-HAR+ maintains competitive or improved performance while reducing LLM usage, token consumption, and inference time. We further extend the RAG-HAR mobile prototype to demonstrate the practical feasibility of retrieval-first, LLM-assisted HAR in mobile sensing scenarios.