Answers are grounded in this paper and cite their sources.
Demonstrates JARVIS enhances HVAC system interaction for non-expert users, suggesting improved usability and accuracy.
Question-answering (QA) interfaces powered by large language models (LLMs) present a promising direction for improving interactivity with HVAC system insights, particularly for non-expert users. However, enabling accurate, real-time, and context-aware interactions with HVAC systems introduces unique challenges, including the integration of frequently updated long-term sensor data, domain-specific knowledge grounding, and coherent multi-stage reasoning. In this paper, we present JARVIS , a two-stage LLM-based QA framework tailored for sensor data-driven HVAC system interaction. JARVIS employs an Expert-LLM to translate high-level user queries into structured execution instructions, and an Agent that performs SQL-based data retrieval, statistical processing, and final response generation. To address HVAC-specific challenges, JARVIS integrates (1) an adaptive context injection strategy for efficient HVAC and deployment-specific information integration, (2) a parameterized SQL builder and executor to improve data access reliability, and (3) a bottom-up planning scheme to ensure consistency across multi-stage response generation. We evaluate JARVIS using real-world data collected from two commercial HVAC systems and a ground truth QA dataset curated by HVAC experts to demonstrate its effectiveness in delivering accurate and interpretable responses across diverse queries. Results show that JARVIS outperforms baseline implemented with modern off-the-shelf LLMs and ablation variants in both automated and user-centered assessments, achieving high response quality and accuracy.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: