CyberAGENTS¶
Product or Programme · All products and programmes
Evidence · 4 claims (4 for) · 1 study (1 design),q1· 0 of 1 report an effect size · 4 claims rest on one study
Description¶
A custom orchestrator-worker framework developed by Hornung et al. that coordinates Challenge, Buddy, Critic, and Reward agents to deliver adaptive cybersecurity learning challenges, support, feedback, and progression.
Components¶
- CyberAGENTS four-agent learning loop: Challenge, Buddy, Critic, and Reward agents: CyberAGENTS decomposes the gamified learning loop into four specialized agents coordinated by a central orchestrator. The article states "the framework decomposes gameplay into four specialized agents: ChallengeAgent,BuddyAgent,CriticAgent, andRewardAgent," enacting the cycle of challenge, learner attempt, evaluation, and progression. Each agent maps to a gamified learning function: progressive challenges, adaptive support, structured feedback, and mastery-based progression, with the RewardAgent assigning XP across tiers from Apprentice to Legendary. (Hornung et al. (2026))
Claims¶
- LLM-as-judge evaluation scored CyberAGENTS highest on domain grounding (4.46) and agent role fidelity (4.35) [+W]
- Ablating expert-informed structural components lowered LLM-judge scores on all dimensions, with largest drops in challenge quality, intent alignment, and domain grounding [+W]
- Open-ended learner feedback revealed four themes: trust in AI scaffolding, feedback clarity, engagement, and task authenticity [+W]
- Undergraduate learners rated CyberAGENTS positively, with scenario authenticity highest and challenge difficulty alignment lowest [+W]
Related Products and Programmes¶
-
Key Sources¶
- 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. Preprint. https://arxiv.org/abs/2608.07965. doi:10.48550/arxiv.2608.07965
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
cyberagents |
title |
CyberAGENTS |
description |
A custom orchestrator-worker framework developed by Hornung et al. |
status |
review |
product_kind |
framework |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.