Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2representative citing papers
Survey of 162 vibe coders finds perceptions of AI code quality similar across experience levels but motivations, interaction styles, and quality assurance practices diverge, revealing a perception-action gap.
Plural LLM setups (expert+peer in math; role-specialized pair in writing) improve post-task math performance and preserve writing idea diversity better than single-assistant or no-AI baselines.
Studies of AITutor with 12 students reveal that layered worked examples, visual grounding, and metacognitive scaffolding reduce the cost of reasoning repair while students repurpose shortcuts as checkpoints under exam pressure.
Response-time propensities estimated from tutoring logs are stable within students and predict learning efficiency conditionally on proficiency and practice stage.
citing papers explorer
-
Guidelines for Designing AI Technologies to Support Adult Learning
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
-
From Prompting to Verification: How Experience Shapes Vibe Coding Practices
Survey of 162 vibe coders finds perceptions of AI code quality similar across experience levels but motivations, interaction styles, and quality assurance practices diverge, revealing a perception-action gap.
-
Human Thinking under Plural LLM Assistance: Mathematical Problem Solving and Open-Ended Writing
Plural LLM setups (expert+peer in math; role-specialized pair in writing) improve post-task math performance and preserve writing idea diversity better than single-assistant or no-AI baselines.
-
From Answer Generators to Reasoning Facilitators: Designing AI Tutors for Mathematical Reasoning in High-Stakes Environments
Studies of AITutor with 12 students reveal that layered worked examples, visual grounding, and metacognitive scaffolding reduce the cost of reasoning repair while students repurpose shortcuts as checkpoints under exam pressure.
-
Understanding Student Effort Using Response-Time Propensities During Problem Solving
Response-time propensities estimated from tutoring logs are stable within students and predict learning efficiency conditionally on proficiency and practice stage.