Paper Details

Abstract

This paper presents CORA (COntextual Retrieval and Allocation), a unified framework that combines Retrieval-Augmented Generation (RAG) with multi-agent task allocation and planning systems to support aging-in-place in smart homes. The system utilizes a curated elderly care knowledge base to enable context-aware retrieval and grounded response generation. Simultaneously, distributed language agents manage task decomposition, allocation, and execution within an embodied environment. Evaluation in the AI2-THOR (AI2 - The House Of inteRactions) simulator demonstrates that our hybrid retrieval approach outperforms standalone methods (TF-IDF, BM25, semantic retrieval), achieving 0.613 Precision@3, while GPT-4o-based multi-agent coordination achieves up to 95% task completion rate, significantly outperforming other Large Language Models (LLMs) backbones. The results highlight the potential of integrating language-driven reasoning with embodied intelligence for scalable and adaptive eldercare systems.

Keywords
Elderly care Smart homes Retrieval-Augmented Generation Large Lan- guage Models Multi-agent systems
Contact Information
Le Duy Tan (Corresponding Author)
Vietnam National University, Ho Chi Minh City, Vietnam, Vietnam
0389081824

All Authors (5)

Son Thanh Le

Affiliation: Vietnam National University, Ho Chi Minh City, Vietnam

Country: Vietnam

Email: ltson@hcmiu.edu.vn

Phone: 0389081824

Truong Le Minh Toan

Affiliation: Swinburne University of Technology (via Swinburne Vietnam Alliance Program), Ho Chi Minh City, Vietnam

Country: Australia

Email: 104995838@student.swin.edu.au

Phone: 0389081824

Sy Huu Le

Affiliation: Industrial University of Ho Chi Minh City

Country: Vietnam

Email: lhsy.workspace@gmail.com

Phone: 0389081824

Le Duy Tan C

Affiliation: Vietnam National University, Ho Chi Minh City, Vietnam

Country: Vietnam

Email: ldtan@hcmiu.edu.vn

Phone: 0389081824

Tuyen Nguyen

Affiliation: University of Southampton

Country: United Kingdom

Email: tuyen.nguyen@soton.ac.uk

Phone: 0389081824