SODIUM: From Open Web Data to Queryable Databases

• URL: http://arxiv.org/abs/2603.18447v1
• Date: Thu, 19 Mar 2026 03:17:56 GMT
• Title: SODIUM: From Open Web Data to Queryable Databases
• Abstract summary: We formalize the SODIUM task, where we conceptualize open domains such as the web as latent databases.<n>Existing systems struggle with SODIUM tasks, with the strongest baseline achieving only 46.5% accuracy.<n>We develop SODIUM-Agent, a multi-agent system composed of a web explorer and a cache manager.<n>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.
• Score: 7.809458664810863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive Online Exploration for Deep Research Agents [70.77400371166922]
  Deep research web agents need to rigorously analyze and aggregate knowledge for insightful research.<n>We propose an Explore to Evolve paradigm to scalably construct verifiable training data for web agents.<n>Based on an open-source agent framework, SmolAgents, we collect supervised fine-tuning trajectories to develop a series of foundation models.
  arXiv  Detail & Related papers  (2025-10-16T08:37:42Z)
• LLM-based Multi-Agent Blackboard System for Information Discovery in Data Science [69.1690891731311]
  We propose a novel multi-agent communication paradigm inspired by the blackboard architecture for traditional AI models.<n>In this framework, a central agent posts requests to a shared blackboard, and autonomous subordinate agents respond based on their capabilities.<n>We evaluate our method on three benchmarks that require explicit data discovery.
  arXiv  Detail & Related papers  (2025-09-30T22:34:23Z)
• Scaling Generalist Data-Analytic Agents [95.05161133349242]
  DataMind is a scalable data synthesis and agent training recipe designed to build generalist data-analytic agents.<n>DataMind tackles three key challenges in building open-source data-analytic agents.
  arXiv  Detail & Related papers  (2025-09-29T17:23:08Z)
• DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery [26.388978716803464]
  Can AI agents transcend conventional search to systematically discover any dataset that meets specific user requirements?<n>Our benchmark and comprehensive analysis provide the foundation for the next generation of self-improving AI systems.
  arXiv  Detail & Related papers  (2025-08-09T12:15:08Z)
• WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization [68.46693401421923]
  WebShaper systematically formalizes IS tasks through set theory.<n>WebShaper achieves state-of-the-art performance among open-sourced IS agents on GAIA and WebWalkerQA benchmarks.
  arXiv  Detail & Related papers  (2025-07-20T17:53:37Z)
• From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents [96.65646344634524]
  Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research.<n>We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn.<n>We demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking.
  arXiv  Detail & Related papers  (2025-06-23T17:27:19Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.