HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Hongyang, Zhang, Yanxin, She, Yang, Xiao, Yue, Wu, Hao, Zhang, Yiyang, Hou, Jiapeng, Zhang, Rongshan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912994889302016
author Yang, Hongyang
Zhang, Yanxin
She, Yang
Xiao, Yue
Wu, Hao
Zhang, Yiyang
Hou, Jiapeng
Zhang, Rongshan
author_facet Yang, Hongyang
Zhang, Yanxin
She, Yang
Xiao, Yue
Wu, Hao
Zhang, Yiyang
Hou, Jiapeng
Zhang, Rongshan
contents Housing selection is a high-stakes and largely irreversible decision problem. We study housing consultation as a decision-support interface for housing selection. Existing housing platforms and many LLM-based assistants often reduce this process to ranking or recommendation, resulting in opaque reasoning, brittle multi-constraint handling, and limited guarantees on factuality. We present HabitatAgent, the first LLM-powered multi-agent architecture for end-to-end housing consultation. HabitatAgent comprises four specialized agent roles: Memory, Retrieval, Generation, and Validation. The Memory Agent maintains multi-layer user memory through internal stages for constraint extraction, memory fusion, and verification-gated updates; the Retrieval Agent performs hybrid vector--graph retrieval (GraphRAG); the Generation Agent produces evidence-referenced recommendations and explanations; and the Validation Agent applies multi-tier verification and targeted remediation. Together, these agents provide an auditable and reliable workflow for end-to-end housing consultation. We evaluate HabitatAgent on 100 real user consultation scenarios (300 multi-turn question--answer pairs) under an end-to-end correctness protocol. A strong single-stage baseline (Dense+Rerank) achieves 75% accuracy, while HabitatAgent reaches 95%.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00556
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation
Yang, Hongyang
Zhang, Yanxin
She, Yang
Xiao, Yue
Wu, Hao
Zhang, Yiyang
Hou, Jiapeng
Zhang, Rongshan
Machine Learning
Artificial Intelligence
Emerging Technologies
Computational Finance
Risk Management
Housing selection is a high-stakes and largely irreversible decision problem. We study housing consultation as a decision-support interface for housing selection. Existing housing platforms and many LLM-based assistants often reduce this process to ranking or recommendation, resulting in opaque reasoning, brittle multi-constraint handling, and limited guarantees on factuality. We present HabitatAgent, the first LLM-powered multi-agent architecture for end-to-end housing consultation. HabitatAgent comprises four specialized agent roles: Memory, Retrieval, Generation, and Validation. The Memory Agent maintains multi-layer user memory through internal stages for constraint extraction, memory fusion, and verification-gated updates; the Retrieval Agent performs hybrid vector--graph retrieval (GraphRAG); the Generation Agent produces evidence-referenced recommendations and explanations; and the Validation Agent applies multi-tier verification and targeted remediation. Together, these agents provide an auditable and reliable workflow for end-to-end housing consultation. We evaluate HabitatAgent on 100 real user consultation scenarios (300 multi-turn question--answer pairs) under an end-to-end correctness protocol. A strong single-stage baseline (Dense+Rerank) achieves 75% accuracy, while HabitatAgent reaches 95%.
title HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation
topic Machine Learning
Artificial Intelligence
Emerging Technologies
Computational Finance
Risk Management
url https://arxiv.org/abs/2604.00556