BaRA: BFS-and-Reflection Web Data Collection Agent
Summary
BaRA is a framework for site-level web data collection combining bounded BFS traversal with history-based self-reflection, outperforming existing methods on link discovery and downloadable extraction.
View Cached Full Text
Cached at: 07/02/26, 05:41 AM
# BaRA: BFS-and-Reflection Web Data Collection Agent Source: [https://arxiv.org/abs/2607.00007](https://arxiv.org/abs/2607.00007) [View PDF](https://arxiv.org/pdf/2607.00007) > Abstract: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[this https URL](https://github.com/MLAI-Yonsei/BaRA-Agent)\. ## Submission history From: Soojeong Lee \[[view email](https://arxiv.org/show-email/8dae5879/2607.00007)\] **\[v1\]**Sat, 2 May 2026 08:09:10 UTC \(1,151 KB\)
Similar Articles
@DeRonin_: Do you understand what Browserbase just open-sourced??? an agent that learns any website once, then does the job 10x ch…
Browserbase open-sourced Autobrowse, an agentic web browsing tool that learns website structures through iterative exploration and saves discovered patterns as reusable markdown skills, dramatically reducing time and cost for repeated web automation tasks.
I made a small tool to inspect retrieval results before feeding them into RAG
A developer created a small local tool for inspecting retrieval results from search providers like Brave, Serper, Tavily, and Exa before feeding them into a RAG pipeline, checking signals such as source diversity, duplicates, freshness, and SEO/GEO pollution risk.
Building web agents made me realize how much context gets wasted on bad URLs. How do you filter your scrapes?
The author discusses the problem of context window waste in web agents when scraping bad URLs and asks about methods to filter scrapes using metadata to improve efficiency.
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
ARBOR introduces a reusable rubric buffer to provide online process rewards for LLM-based search agents, improving training efficiency when outcome-only rewards are insufficient. It outperforms GRPO and DAPO on multi-hop QA benchmarks, converting up to 42% of zero-gradient training groups into informative ones.
Region4Web: Rethinking Observation Space Granularity for Web Agents
This paper introduces Region4Web, a framework that improves web agent performance by organizing observation spaces into functional regions rather than individual elements. It demonstrates that this approach reduces observation length and increases task success rates on the WebArena benchmark.