Version 6.6.1 - AI-KM: Agent skills and ontology-driven knowledge modeling
This update introduces two significant capabilities: an agentic skill framework and ontology-driven knowledge modeling with retrieval. The agentic skill framework encapsulates complex AI behaviors as reusable, conversation-invokable skills, supporting both predefined expert skills and an autonomous planning mode for novel tasks. Meanwhile, the ontology-driven knowledge modeling module elevates knowledge representation from simple slice structures to formal, machine-interpretable ontologies built through natural language entity extraction. These advances enable domain experts to encode their expertise as both executable skills and structured knowledge, creating a closed loop where knowledge is represented as formal structure and applied as dynamic process.
Authors
- 熊俊芬
- Bingjie Li (ORCID: https://orcid.org/0000-0003-0294-4294)
- Songyi Wang (ORCID: https://orcid.org/0009-0001-4112-3379)
- haolin wen
- Xin Liang
- Tong Chen
Institutions
- Naval University of Engineering (CN)
- Southern University of Science and Technology (CN)
- Peng Cheng Laboratory (CN)
- Central Hospital of Wuhan (CN)
- Wuhan General Hospital of Guangzhou (CN)
Publication Details
- Journal
- SoftwareX
- Published
- 2026-07-02
- DOI
- https://doi.org/10.1016/j.softx.2026.102855
- Primary Topic
- Intelligent Tutoring Systems and Adaptive Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00