Logo image
BioWeaver: Adaptive Workflow Orchestration for Biomedical Data Integration with Progressive Deep Web Exploration
Conference paper   Open access

BioWeaver: Adaptive Workflow Orchestration for Biomedical Data Integration with Progressive Deep Web Exploration

Syed Nazmus Sakib, Sajratul Yakin Rubaiat and Hasan Jamil
Proceedings of the 38th International Conference on Scalable Scientific Data Management, pp.1-12
ACM Other Conferences, ACM
SSDBM 2026: The International Conference on Scalable Scientific Data Management 2026 (San Diego, CA, 08/11/2026–08/13/2026)
08/11/2026

Abstract

Applied computing -- Bioinformatics Computer systems organization -- Data flow architectures Information systems -- Information extraction Information systems -- Web searching and information discovery
Biomedical researchers often need to combine evidence from heterogeneous sources, including REST APIs, form-based deep web databases, semi-structured web pages, and downloadable files. Existing workflow systems support reproducible analysis but require manually specified pipelines, while LLM-based agents can issue tool calls but often lack explicit data dependencies, provenance, and controlled exploration. We present BioWeaver, an adaptive workflow orchestration system that converts natural-language biomedical questions into executable scientific workflow graphs. Each graph represents typed retrieval, refinement, and synthesis steps over a catalog of heterogeneous connectors. During execution, BioWeaver uses Progressive Data Refinement (PDR) to expand the workflow when intermediate results reveal useful follow-up records, while a composite information-gain heuristic and human-in-the-loop checkpoints control exploration depth. A unified connector abstraction supports APIs, browser-automated forms, HTML tables, and downloadable files under a common execution model. We evaluate BioWeaver on 45 queries across two biomedical question sets with gold-standard answers. Results show that BioWeaver improves overall answer quality by 6.2–14.5% over LLM baselines and by 41.4–53.8% over a ReAct agent. Ablation studies show that runtime refinement, planner knowledge, and information-gain stopping each contribute to system effectiveness. These results suggest that adaptive workflow graphs provide a practical foundation for reproducible, source-grounded biomedical data integration across heterogeneous and deep web resources.
url
Article Landing PageView
Published (Version of record) Open

Metrics

1 Record Views

Details

Logo image