CyberAGENTS: Structured Autonomy for Agentic Gamified Learning in Cybersecurity

Synthesis: Hornung et al. (2026) present CyberAGENTS, an agentic framework for gamified cybersecurity learning that enables structured autonomy through ontology-guided validation, schema-governed behavioral control, and competency-based progression. The learning loop is decomposed into four specialized agents (challenge, support, evaluation, reward), each governed by behavioral schemas, with a cybersecurity ontology validating all generated content before display. Classroom deployment with undergraduates, complemented by expert evaluation, found improved engagement, clearer feedback interpretation, and greater learner trust when behavioral schemas and ontology validation are active. The work connects to Agentic AI, CS Education, and Pedagogical Safety themes.

Grounding Agentic Gamification in Learning Science

Gamification is especially effective in learning domains requiring active problem-solving and iterative skill-building, such as cybersecurity education. Generative AI agents offer adaptive delivery at scale but introduce risks: inconsistent behavior, hallucinated reasoning, and misalignment with pedagogical frameworks.

Structured Autonomy

CyberAGENTS is organized around a competency-based progression model that structures topics by difficulty and prerequisite relationships. The learning loop is decomposed into four specialized agents — challenge, support, evaluation, reward — each governed by behavioral schemas that encode operational modes and progression logic, bounding autonomy without eliminating generative flexibility. A cybersecurity ontology validates all generated content prior to display, enforcing domain-consistent reasoning and safety constraints.

Findings

Classroom deployment with undergraduate students, complemented by expert evaluations from educators and domain specialists, indicated improved engagement, clearer feedback interpretation, and greater learner trust in AI-generated responses when behavioral schemas and ontology validation are active. Preliminary comparisons with an unconstrained configuration support the role of structured control in stabilizing instructional behavior.

Connected Concepts

Connected Articles

Citation

Hornung, I., Marasinghe Arachchige, D., Kumarage, T., Agrawal, G., Deng, Y., Chen, Y.-C., & Liu, H. (2026). CyberAGENTS: Structured autonomy for agentic gamified learning in cybersecurity. arXiv:2608.07965.