aiqbench analysis
CoLearn introduces an agentic tutoring framework that moves beyond static question banks by maintaining a persistent, evidence-grounded memory of student mastery and misconceptions. By leveraging a large language model as a continuous observation function within a Bayesian Knowledge Tracing variant, the system dynamically generates personalized questions that converge toward the learner's true ability level in simulation. This approach represents a significant step forward in adaptive educational AI, demonstrating measurable improvements over non-personalized methods in blind evaluations.
CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loop
arXiv:2609.21154v1 Announce Type: new Abstract: Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools instead serve fixed item banks and treat a wrong answer as a single bit of signal. We present CoLearn, an interactive, agentic tutor that supports an iterative tutoring loop: the learner practises, and the system builds an evidence-grounded memory of the learner's mastery and misconceptions. This memory is updated as evidence accumulates and is used to generate the next personalised question. CoLearn has three components: (i) a persistent learner-state memory that updates per-topic mastery with a soft-evidence variant of Bayesian Knowledge Tracing, where a large language model acts as a continuous observation function; (ii) adaptive question generation that targets the learner's weakest topic and recurring misconceptions; and (iii) an evidence view that makes personalisation visible and testable through live progress visualisation and blind A/B comparison. In blind A/B evaluation, questions conditioned on this memory are preferred over non-personalised ones 68-69% of the time, and in persona simulations with hidden ground-truth mastery the agent's belief converges toward the learner's true mastery.
Abstract:Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools instead serve fixed item banks and treat a wrong answer as a single bit of signal. We present CoLearn, an interactive, agentic tutor that supports an iterative tutoring loop: the learner practises, and the system builds an evidence-grounded memory of the learner's mastery and misconceptions. This memory is updated as evidence accumulates and is used to generate the next personalised question. CoLearn has three components: (i) a persistent learner-state memory that updates per-topic mastery with a soft-evidence variant of Bayesian Knowledge Tracing, where a large language model acts as a continuous observation function; (ii) adaptive question generation that targets the learner's weakest topic and recurring misconceptions; and (iii) an evidence view that makes personalisation visible and testable through live progress visualisation and blind A/B comparison. In blind A/B evaluation, questions conditioned on this memory are preferred over non-personalised ones 68-69% of the time, and in persona simulations with hidden ground-truth mastery the agent's belief converges toward the learner's true mastery.
Computation and Language (cs.CL)
arXiv:2609.21154 [cs.CL]
(or arXiv:2609.21154v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.21154 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 285 words
Related coverage
Facial-Expression-Aware Prompting for Empathetic LLM Tutoring
arXiv · Jul 31, 2026
SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice
arXiv · Aug 18, 2026
SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice
arXiv · Jun 4, 2026
AI should empower everyone, Meta argues in new philosophy
Quantum Zeitgeist · Sep 1, 2026