Search papers, labs, and topics across Lattice.
HabitatAgent, a novel LLM-powered multi-agent architecture, is introduced for end-to-end housing consultation, addressing limitations of existing systems in reasoning, constraint handling, and factuality. It employs four specialized agents (Memory, Retrieval, Generation, Validation) to provide an auditable and reliable workflow. Evaluated on 100 real user consultation scenarios, HabitatAgent achieves 95% accuracy, significantly outperforming a strong single-stage baseline (75%).
A multi-agent system can dramatically improve the accuracy of LLM-based housing consultations, jumping from 75% to 95% correctness in real-world scenarios.
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%.
