Papers for

online coding platforms

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Adaptive AI tutor adjusts coding help based on learner decisions

Adaptive Scaffolding Needs Contingency: An AI Tutor That Escalates and Fades on What the Learner Does

Abstract: Coding assistants raise task performance, but learners plan and monitor less. Giving less away, the usual fix, conflates two things: how much work a system carries (cognitive load) and what the learner must decide before help arrives (metacognitive demand). Our principle, preserved metacognitive demand, holds the second constant and lets the first vary. CoMeT implements it: support rises when a learner fails at a decision point and fades on take-up. Within subjects, 131 adult learners used CoMeT, an unrestricted assistant and a question-only tutor on three Python tasks. CoMeT matched the question-only tutor's demand, delivered artifacts twice as often as the assistant, and frustrated learners less than the question-only tutor, with delegation and load unchanged. Learners often did not answer. Fading held when their turn addressed the decision under support, and CoMeT surrendered the full answer in one session in sixteen, against one in six for the question-only tutor.

Sat 19 SeptHuman-Computer InteractionMultiagent Systems
The gist
When people learn to code, sometimes they rely too much on assistants that give all the answers, which stops them from thinking deeply. The authors created an AI tutor called CoMeT that gives help when learners get stuck but gradually lets them try on their own again. In tests with adults solving Python problems, CoMeT gave helpful hints more often than a typical assistant but kept learners engaged without frustrating them. This approach balances giving enough support and encouraging independent thinking.
Open → 2609.22993v1