SODIUM: From Open Web Data to Queryable Databases
During research, domain experts often ask analytical questions whose answers require integrating data from a wide range of web sources. Thus, they must spend substantial effort searching, extracting, and organizing raw data before analysis can begin. We formalize this process as the SODIUM task, where we conceptualize open domains such as the web as latent databases that must be systematically instantiated to support downstream querying. Solving SODIUM requires (1) conducting in-depth and specialized exploration of the open web, which is further strengthened by (2) exploiting structural correlations for systematic information extraction and (3) integrating collected information into coherent, queryable database instances. To quantify the challenges in automating SODIUM, we construct SODIUM-Bench, a benchmark of 105 tasks derived from published academic papers across 6 domains, where systems are tasked with exploring the open web to collect and aggregate data from diverse sources into structured tables. Existing systems struggle with SODIUM tasks: we evaluate 6 advanced AI agents on SODIUM-Bench, with the strongest baseline achieving only 46.5% accuracy. To bridge this gap, we develop SODIUM-Agent, a multi-agent system composed of a web explorer and a cache manager. Powered by our proposed ATP-BFS algorithm and optimized through principled management of cached sources and navigation paths, SODIUM-Agent conducts deep and comprehensive web exploration and performs structurally coherent information extraction. SODIUM-Agent achieves 91.1% accuracy on SODIUM-Bench, outperforming the strongest baseline by approximately 2 times and the weakest by up to 73 times.
Code (0)
등록된 구현이 없습니다.
Tasks
Information ExtractionSimilar Papers 제목 키워드 기반
Outward Sodium Current, Fine-structure Constant and Ferroelectric Hysteresis Regimes in the Giant Squid Axon Propagating Action Potential: a Phase Space Approach
We derive a charge-conserving phase space cable equation for the propagating action potential, expressing ionic, membrane, and capacitive currents as functions of membrane potential. Analysis of the ionic current during …
Open-vocabulary Queryable Scene Representations for Real World Planning
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions. However, prior attempts to apply LLMs to real-world robotic tasks are limited by the lack of grounding in the surround…
Task PlanningRician Denoising Diffusion Probabilistic Models For Sodium Breast MRI Enhancement
Sodium MRI is an imaging technique used to visualize and quantify sodium concentrations in vivo, playing a role in many biological processes and potentially aiding in breast cancer characterization. Sodium MRI, however, …
DenoisingImage Quality AssessmentVision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps
Open-vocabulary 3D maps let robots answer language queries about what and where, but they assume a static world and cannot answer queries about how scene elements behave. We introduce Vision-Language-Motion Maps (VLMM), …
Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when generating semantic maps. This paper presents Open-Fusion, a groundbr…
3D Scene Reconstruction