BaRA: BFS-and-Reflection Web Data Collection Agent
摘要
Large language model (LLM)-based web agents reduce manual scripting for web data collection, yet on live websites, they often miss relevant pages, return incomplete multimodal outputs, or return media URLs that are not directly downloadable. We present BFS-and-Reflection Agent (BaRA), a framework for site-level collection under a fixed interaction budget. The framework combines bounded breadth-first search (BFS) traversal with history-based self-reflection. We evaluate BaRA on 50 synthetic websites with ground-truth reference sets. We additionally test on three public websites with cluttered or dynamic layouts. BaRA outperforms Pure LLM, SeeAct-Vision, and Browser-use on link discovery and downloadable multimodal extraction, with the largest gains in download-valid image and video recovery. Our code is available at https://github.com/MLAI-Yonsei/BaRA-Agent.
引用
@article{arxiv.2607.00007,
title = {BaRA: BFS-and-Reflection Web Data Collection Agent},
author = {Soojeong Lee and Joseph Lee and Yongseong Cho and Sunjae Kim and Youngwoo Moon and Kyungwoo Song},
journal= {arXiv preprint arXiv:2607.00007},
year = {2026}
}