Dingent: a configurable agent framework for biological database retrieval and integration

Read full text Summarise with VIRAT
Authors: Demian Kong, Bixia Tang, Shaoqi Bei, Yueyue Wu, Wenming Zhao
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Abstract AI-driven data search and integration represent an emerging research direction. Although several LLM-based backend frameworks and agentic frameworks have emerged, significant gap remains in developing a one-stop, configurable agent framework that supports various data sources and provides a web interface for efficient data retrieval using natural language. To address this, we present Dingent, a novel and configurable agent framework that facilitates data access from various resources and enables the flexible constructions of agent applications. We demonstrate its capabilities across three distinct application scenarios, achieving promising results. The Dingent framework can be readily applied to other fields, such as earth sciences and ecology, to facilitate data discovery.

Fields of Study & Subjects

Scientific Computing and Data Management Biomedical Text Mining and Ontologies Research Data Management Practices

Publication details

Journal / source
Computational and Structural Biotechnology Journal
Publication date
3 November 2026
Language
EN