用多智能体系统让买房咨询更可靠，推理透明且事实准确。
HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation
- 四类智能体协同：记忆、检索、生成、验证，全程可追溯。
- 在300轮问答中准确率达95%，远超基线的75%。
- 适合需要透明决策过程的购房人群和房产平台使用。
住房选择是高风险且不可逆的决策问题。现有住房平台和许多基于大模型的助手常将此过程简化为排序或推荐，导致推理不透明、多约束处理脆弱，且事实性难以保证。我们提出HabitatAgent，首个端到端的基于大模型的多智能体住房咨询系统。该系统包含四类专用智能体：记忆代理通过多层内部阶段实现约束提取、记忆融合与验证触发更新；检索代理采用混合向量-图检索（GraphRAG）；生成代理产出有证据支持的推荐与解释；验证代理执行多层级验证与定向修正。四者共同构建可审计、可靠的全流程咨询机制。我们在100个真实用户咨询场景（共300轮多轮问答）下，以端到端正确性协议评估。强基线模型（Dense+Rerank）准确率为75%，HabitatAgent达95%。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。