BaRA: Budget-constrained and Reliable Web Data Collection Agent
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
BARA: Efficient Incentive Mechanism with Online Reward Budget Allocation in Cross-Silo Federated Learning
Federated learning (FL) is a prospective distributed machine learning framework that can preserve data privacy. In particular, cross-silo FL can complete model training by making isolated data islands of different organi…
Bayesian OptimizationFederated LearningBuilding an ASR Solution for Training and Assessing Children's Reading
Automatic speech recognition for children's reading remains underdeveloped for most African languages, including Bambara, despite its potential value for reproducible literacy assessment. We present an open-source system…
Speech RecognitionA Deep Neural Network Based Approach to Building Budget-Constrained Models for Big Data Analysis
Deep learning approaches require collection of data on many different input features or variables for accurate model training and prediction. Since data collection on input features could be costly, it is crucial to redu…
An Open Data and Geo-based Information Systems
Barangay is the smallest type of government in the Philippines, and it is driven and represented by its barangay authorities. The barangay officials are accountable for keeping the records of citizens health and crime in…
Decision MakingA comparison of pipelines for the translation of a low resource language based on transformers
This work compares three pipelines for training transformer-based neural networks to produce machine translators for Bambara, a Mandè language spoken in Africa by about 14,188,850 people. The first pipeline trains a simp…