cs.DCNov 9, 2026

PegasusAI Studio: Legible Cyberinfrastructure and Accountable AI Agents for Scientific Workflows

Authors: Komal Thareja, Mats Rynge, Berent Aldikacti, Angelina Ju, Ian Lumsden, Anirban Mandal, Rajiv Mayani, Kin Wai Ng, 

Organizations: University of North Carolina at Chapel Hill, Chapel Hill, NC, USA · University of Southern California, Los Angeles, CA, USA · University of Massachusetts Amherst, Amherst, MA, USA · University of Tennessee, Knoxville, Knoxville, TN, USA

Abstract

AI coding agents can now construct scientific workflows, but operating them on shared cyberinfrastructure (CI) raises problems that code generation does not solve. Agents need current knowledge of the workflow system and its execution sites and access to the runtime state of distributed executions, while facilities need to attribute every agent action to a user and bound it by that user's privileges. We present PegasusAI Studio, an AI-assisted science gateway built on the Pegasus and HTCondor stack. Studio makes CI legible to agents by projecting one facility-curated knowledge base into the native configuration of several coding agents, by introspecting workflow interfaces and execution sites, and by grounding diagnosis in workflow and scheduler telemetry. Agent actions operate within a trust envelope that combines federated authentication, per-user execution environments and scheduler credentials, provider-neutral model access, observability, and approval controls for state-changing actions. The same application runs as a JupyterHub-based gateway on a research cloud and as an Open OnDemand application on HPC systems. We evaluate Studio through case studies of legacy CASA weather workflow modernization, a gravitational-wave reanalysis, an EEG analysis built with an open-weight model, and an Event Horizon Telescope (EHT) M87 image reconstruction that recovered from two failed runs to a zero-failure execution. The evaluation establishes that these mechanisms operate as designed.

Figures & tables

Explore similar work

CardsList
  1. ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution

    Sep 13, 2026Baixi Sun, Mingze Xia, Huihuo ZhengScientific Workflow AutomationAI for Science

  2. SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery

    Jul 17, 2026SciForge Team, Zhangyang Gao, Minghao Fang +10AI Agents for Scientific DiscoveryAI Agent Governance

  3. OpenAI4S: Code as Action, Science as Sessions

    Sep 14, 2026Gongbo Zhang, Hao Li, Yu Wang +15Data ProvenanceRuntime Enforcement for AI Agents