ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering
Provides a new benchmark and baseline for tool-augmented multi-step reasoning in the real-estate domain, addressing the lack of such resources for hybrid workflows.
ReCoQA introduces a large-scale benchmark of 29,270 real-estate QA instances with machine-verifiable intermediate supervision, and proposes HIRE-Agent, a hierarchical framework that achieves strong performance on complex multi-step reasoning tasks involving database queries and API calls.
Developing agents capable of navigating fragmented, multi-source information remains challenging, primarily due to the scarcity of benchmarks reflecting hybrid workflows combining database querying with external APIs. To bridge this gap, we introduce ReCoQA, a large-scale benchmark of 29,270 real-estate instances featuring machine-verifiable supervision for intermediate steps, including structured intent labels, SQL queries, and API calls. Complementarily, we propose HIRE-Agent, a hierarchical framework instantiating an understand-plan-execute architecture as a strong baseline. By orchestrating a Front-end parser, a planning Supervisor, and execution Specialists, HIRE-Agent effectively integrates heterogeneous evidence. Extensive experiments demonstrate that HIRE-Agent constitutes a strong baseline and substantiates the necessity of hierarchical collaboration for complex, real-world reasoning tasks.