Multi-agent debate for essay scoring Advocate, Skeptic and Judge agents score essays without task-specific training. Confidence signals in multi-agent debate Do token log-probabilities reveal when debating LLM agents reason badly? Teacher-in-the-loop scoring in PapyrusAI Bringing multi-agent essay scoring into a classroom writing coach, with teachers in control. ThinkingBox agent reliability benchmark A sandbox and 507-task benchmark that grades tool-using agents on final system state. Simulating students' Java errors with LLMs Can LLMs stand in for students by producing realistic buggy code? (EDM 2026) Theory-of-mind assessment chatbot A LLaMA-3 chatbot that administers the Faux Pas Recognition Test for autistic individuals. iTAG and IEEE LOM metadata extraction Automatic pedagogical metadata for slide decks and PDFs, so tutoring systems can find them. AI framework for personalized learning at scale Learner modeling, activity suggestions and facilitator support for low-cost quality education.
