FOCAL: On-Device Multi-Agent System for Efficient Desktop Activity Summarization
FOCAL is a privacy-first, on-device multi-agent system designed to summarize desktop interaction streams into task-organized personal logs. By employing a filter-plan-log architecture, FOCAL reduces token consumption by 60.4% and Vision-Language Model (VLM) calls by 72.3% compared to baselines, while improving key information recall from 0.38 to 0.61. The system also maintains high accuracy and recall even during task interruptions, outperforming baseline approaches.
Why it matters: FOCAL demonstrates a significant advance in efficient, privacy-preserving summarization of continuous desktop activity, enabling practical on-device personal logging.
Full story at: arXiv Multiagent Systems ↗