cs.DCNov 14, 2025

Flash-Fusion: Fast, Expressive Queries over Sensor Streams with LLMs

Authors: Kausar Patherya, Ashutosh Dhekne, Francisco Romero

Organizations: Georgia Institute of Technology, Atlanta, Georgia, USA

Abstract

Pervasive sensor deployments have generated significant interest in IoT data analysis across fields such as healthcare, transportation and urban planning. At the same time, the rise of Large Language Models (LLMs) offer a new tool for exploring IoT data through their expressive, natural language interface. Unfortunately, natural language querying of IoT sensor streams is impractical today: raw telemetry exhausts LLM context windows in fractions of a second at scale, incurs prohibitive per-token costs, and produces hallucinated responses. Existing systems work around these limits with lossy text summarization or unconstrained code synthesis, producing expensive, unverified computations. Multi-step queries compound this problem: logical errors in intermediate operations can derail the final answer. We present Flash-Fusion, an agentic framework for natural-language querying of tabular IoT data. Flash-Fusion identifies which available data fields and supported derivations can answer the user's query, constructs a plan using typed, domain-specific operators, and validates its structure and schema compatibility before executing. Because constructing plans still requires costly LLM reasoning, Flash-Fusion caches validated operator sequences for reuse across compatible queries. A smaller LLM adapts a cached plan's parameters to each query, cutting latency and cost. We evaluate Flash-Fusion across human activity recognition, ECG monitoring, and vehicular telematics, covering direct lookups, multi-step reasoning, predictive tasks, and out-of-scope requests. Flash-Fusion achieves 92.2% query accuracy versus 76.1% for ReAct, the strongest baseline, while completing queries 7x faster and consuming 5x fewer tokens. Flash-Fusion enables users across disciplines to explore IoT data without manually constructing queries.

Figures & tables

Explore similar work

CardsList
  1. Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing

    Jun 21, 2026Aygün Varol, Katarzyna Kołodziej, Łukasz Sobczak +5On-Device Language Model InferenceLLM Prompting

  2. IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling

    Apr 9, 2026Zhaomeng Zhou, Lan Zhang, Junyang Wang +3Wireless Sensor NetworksLLM Reasoning with Graphs