Year: 2026
Type: preprint
Abstract: Modern scientific facilities and instruments generate datasets at scales that are difficult for individual researchers to discover, access, and explore. Although many datasets are publicly available, using them often requires familiarity with repository organization, data formats, multiresolution structures, and visualization parameters. We present WebVisus, a constrained and resource-aware multi-agent system for discovering and autonomously exploring remote, multiresolution scientific datasets. Given a natural-language research question, WebVisus identifies the user's intent and launches an autonomous exploration agent that examines slices, volumes, and timesteps while adapting data resolution and retrieval quality to available client memory and computational resources. This design supports progressive exploration without complete dataset downloads or manual configuration of low-level visualization parameters using natural languages. We report the system architecture, constrained agent protocol, resource-aware access mechanism, and case studies evaluating autonomous visual exploration and resource-aware agentic access across scientific datasets.
Source: arXiv (Cornell University)
Language: English
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: CI CoE: CI Compass: An NSF Cyberinfrastructure (CI) Center of Excellence for Navigating the Major Facilities Data Lifecycle, G1088636562, G1356433355, Global Centers Track 1: U.S.-Canada Center on Climate-Resilient Western Interconnected Grid, G2717806384, G3669113783, OAC: Piloting the National Science Data Fabric: A Platform Agnostic Testbed for Democratizing Data Delivery, G4744444288, G5630301777, G895790057, G991281326
OpenAlex ID: W7204197056