CodeR3: A GenAI-Powered Workflow Repair and Revival Ecosystem

2025-11-23

AI Summary

Scientific workflows (e.g., Taverna) frequently suffer from decay due to service deprecation, outdated dependencies, and system obsolescence, severely impeding knowledge reuse. To address this, we propose a generative AI–driven workflow revival framework. First, it semantically parses decaying workflows; then, it jointly leverages service-matching algorithms and large language models to automate service replacement and cross-platform migration (e.g., to Snakemake or VisFlow). A human-in-the-loop verification mechanism and progressive visual analytics ensure reconstruction reliability. Finally, an open-source, crowdsourced platform facilitates community collaboration for repair and functional validation. Evaluated on multiple real-world Taverna workflows, our approach significantly reduces manual parsing effort while preserving expert oversight at critical decision points. To the best of our knowledge, this is the first framework to establish a closed-loop revival pipeline—from automated diagnosis and intelligent reconstruction to verifiable, reusable workflows.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Scientific workflows encode valuable domain expertise and computational methodologies. Yet studies consistently show that a significant proportion of published workflows suffer from decay over time. This problem is particularly acute for legacy workflow systems like Taverna, where discontinued services, obsolete dependencies, and system retirement render previously functional workflows unusable. We present a novel legacy workflow migration system, called CodeR$^3$ (stands for Code Repair, Revival and Reuse), that leverages generative AI to analyze the characteristics of decayed workflows, reproduce them into modern workflow technologies like Snakemake and VisFlow. Our system additionally integrates stepwise workflow analysis visualization, automated service substitution, and human-in-the-loop validation. Through several case studies of Taverna workflow revival, we demonstrate the feasibility of this approach while identifying key challenges that require human oversight. Our findings reveal that automation significantly reduces manual effort in workflow parsing and service identification. However, critical tasks such as service substitution and data validation still require domain expertise. Our result will be a crowdsourcing platform that enables the community to collaboratively revive decayed workflows and validate the functionality and correctness of revived workflows. This work contributes a framework for workflow revival that balances automation efficiency with necessary human judgment.

Problem

• Addresses legacy workflow decay from discontinued services and dependencies
• Migrates obsolete workflows to modern systems using generative AI
• Automates workflow repair while maintaining human oversight for validation

Innovation

• Generative AI analyzes decayed workflow characteristics
• Automated migration to modern workflow technologies
• Human-in-the-loop validation with service substitution