The reviewed record of science sign in
Pith

arxiv: 2311.00772 · v2 · pith:3MH3TSAF · submitted 2023-11-01 · cs.AI · cs.HC· cs.RO

SAGE: Smart home Agent with Grounded Execution

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:3MH3TSAFrecord.jsonopen to challenge →

classification cs.AI cs.HCcs.RO
keywords homesmartsageuserdeviceactionactionsagent
0
0 comments X
read the original abstract

The common sense reasoning abilities and vast general knowledge of Large Language Models (LLMs) make them a natural fit for interpreting user requests in a Smart Home assistant context. LLMs, however, lack specific knowledge about the user and their home limit their potential impact. SAGE (Smart Home Agent with Grounded Execution), overcomes these and other limitations by using a scheme in which a user request triggers an LLM-controlled sequence of discrete actions. These actions can be used to retrieve information, interact with the user, or manipulate device states. SAGE controls this process through a dynamically constructed tree of LLM prompts, which help it decide which action to take next, whether an action was successful, and when to terminate the process. The SAGE action set augments an LLM's capabilities to support some of the most critical requirements for a Smart Home assistant. These include: flexible and scalable user preference management ("is my team playing tonight?"), access to any smart device's full functionality without device-specific code via API reading "turn down the screen brightness on my dryer", persistent device state monitoring ("remind me to throw out the milk when I open the fridge"), natural device references using only a photo of the room ("turn on the light on the dresser"), and more. We introduce a benchmark of 50 new and challenging smart home tasks where SAGE achieves a 75% success rate, significantly outperforming existing LLM-enabled baselines (30% success rate).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes

    cs.AI 2026-06 unverdicted novelty 6.0

    SMH-Bench supplies 1,100 stratified tasks in a verifiable smart-home simulator to measure LLM performance on explicit control, scheduling, ambiguity, and personalization as environment complexity grows.

  2. SCENIC: Semantic-Conditioned Edge-Aware Neural Framework for Structured IoT Command Generation

    cs.LG 2026-06 unverdicted novelty 4.0

    SCENIC framework reports up to 99% exact match on structured IoT command generation using sub-0.2B models, with pruned INT8 versions retaining 91% EM@1 after 25% size reduction.

  3. MiCU: End-to-End Smart Home Command Understanding with Large Language Model

    cs.CL 2026-05 unverdicted novelty 4.0

    MiCU is a domain-adapted LLM for smart-home command understanding that reports 20% average accuracy gains over baselines and is deployed in the Xiaomi Home app.