Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

BaRA: Budget-constrained and Reliable Web Data Collection Agent

About

Large language model (LLM)-based web agents automate web navigation and data collection. However, live web data collection demands capabilities beyond task completion: agents must discover site-internal pages and retrieve text, image, and video artifacts in an accessible form within a fixed interaction budget. We formulate this setting as budget-constrained, site-level multimodal web data collection and propose Budget-constrained and Reliable Agent (BaRA). BaRA performs breadth-first search (BFS)-based link discovery with liveness verification to filter hallucinated and dead links, then validates extracted multimodal artifacts using rule-based provenance and accessibility checks. A history-based self-reflection module recovers from execution failures and incomplete outputs. On controlled synthetic and real-world websites, BaRA consistently improves valid-link discovery and download-valid multimodal extraction over existing agents. Our code is available at https://github.com/MLAI-Yonsei/BaRA-Agent.

Soojeong Lee, Joseph Lee, Yongseong Cho, Sunjae Kim, Youngwoo Moon, Kyungwoo Song• 2026

Related benchmarks

TaskDatasetResultRank
Link discoveryloc.gov Internal Link Discovery (Step 1)
Precision100
4
Multimodal Text ExtractionSynthetic
Precision96.07
4
Multimodal Video ExtractionSynthetic
Precision100
4
Multimodal Video ExtractionLOC
Precision100
4
Video ExtractionSynthetic oracle-link setting
Precision100
4
Video ExtractionLOC oracle-link
Precision100
4
Image ExtractionSynthetic oracle-link setting
Precision0.9769
4
Image ExtractionLOC oracle-link setting
Precision88.34
4
Link discoverySynthetic Internal Link Discovery (Step 1)
Precision100
4
Multimodal Image ExtractionSynthetic
Precision97.69
4
Showing 10 of 28 rows

Other info

Follow for update