Research map / Multi-agent systems and games / LLM agents
AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environments
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes AgentSense, which uses LLM-driven embodied virtual agents acting in simulated smart homes to generate virtual sensor data for human activity recognition.
Problem
Human activity recognition for smart homes lacks large, diverse labeled sensor datasets, and layout, sensor configuration, and behavioral variation worsen generalization.
Approach
Embodied LLM agents with internal world models perceive and act in simulated home environments to produce virtual sensor data, providing diversity across layouts, sensors, and behaviors.
Closest papers by meaning
- HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation (NeurIPS 2026 · similarity 0.86)
- AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents (ICLR 2026 · similarity 0.86)
- SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents (ICLR 2026 · similarity 0.86)
- Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence (NeurIPS 2025 · similarity 0.85)
- PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks (ICLR 2025 · similarity 0.85)
- AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.