Twelve semistructured interviews yield twelve knowledge-based design requirements for tutoring generative social robots, grouped into self-knowledge, user-knowledge, and context-knowledge categories.
Interna- tional Journal of Artificial Intelligence in Education35(5), 3049–3070 (Dec 2025)
2 Pith papers cite this work. Polarity classification is still indexing.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Eight teachers used a four-agent LLM system to create 212 personalized middle-school math problems; final versions had few realism or hallucination problems noted by users even though agents flagged realism issues during generation.
citing papers explorer
-
Knowledge-Based Design Requirements for Generative Social Robots in Higher Education
Twelve semistructured interviews yield twelve knowledge-based design requirements for tutoring generative social robots, grouped into self-knowledge, user-knowledge, and context-knowledge categories.
-
Mathematics Teachers Interactions with a Multi-Agent System for Personalized Problem Generation
Eight teachers used a four-agent LLM system to create 212 personalized middle-school math problems; final versions had few realism or hallucination problems noted by users even though agents flagged realism issues during generation.