LLM-based Question-Answer Framework for Sensor-driven HVAC System Interaction

TL;DR

This paper introduces JARVIS, a two-stage LLM-based question-answering framework designed for real-time, sensor-driven HVAC system interaction, effectively integrating sensor data, domain knowledge, and multi-stage reasoning.

Contribution

The paper presents JARVIS, a novel two-stage LLM-based QA framework with adaptive context injection, reliable SQL data access, and multi-stage response planning for HVAC systems.

Findings

JARVIS outperforms baseline methods in accuracy and response quality.

Effective integration of sensor data and domain knowledge improves response interpretability.

Demonstrated high performance on real-world HVAC data and expert-curated QA datasets.

Abstract

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 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 a commercial HVAC system 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 consistently outperforms baseline and ablation variants in both automated and user-centered assessments, achieving high response quality and accuracy.