# Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education

arXiv: https://arxiv.org/abs/2605.15850 · HTML: https://mlsanity.com/paper/2605.15850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 97 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Beware of Metacognitive Laziness: Effects of Generative Artificial Intelligence on Learning Motivation, Processes, and Performance](https://mlsanity.com/paper/2412.09315/) (2024)
- [A Comprehensive AI Policy Education Framework for University Teaching and Learning](https://mlsanity.com/paper/2305.00280/) (2023)
- [Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure](https://mlsanity.com/paper/2410.03781/) (2024)
- [Promises and challenges of generative artificial intelligence for human learning](https://mlsanity.com/paper/2408.12143/) (2024)
- [Protecting Human Cognition in the Age of AI](https://mlsanity.com/paper/2502.12447/) (2025)
- [Reinforcement Learning Tutor Better Supported Lower Performers in a Math Task](https://mlsanity.com/paper/2304.04933/) (2023)
- [Performance and Metacognition Disconnect when Reasoning in Human-AI Interaction](https://mlsanity.com/paper/2409.16708/) (2024)
- [Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems](https://mlsanity.com/paper/2304.09821/) (2023)
- [Enhancing Critical Thinking in Generative AI Search with Metacognitive Prompts](https://mlsanity.com/paper/2505.24014/) (2025)
- [Enhancing Programming Education with ChatGPT: A Case Study on Student Perceptions and Interactions in a Python Course](https://mlsanity.com/paper/2403.15472/) (2024)
- [Plan More, Debug Less: Applying Metacognitive Theory to AI-Assisted Programming Education](https://mlsanity.com/paper/2509.03171/) (2025)
- [Investigating the Effects of LLM Use on Critical Thinking Under Time Constraints: Access Timing and Time Availability](https://mlsanity.com/paper/2603.08849/) (2026)

## Abstract (arXiv)

In recent years, generative AI (GenAI) in educational settings has become ubiquitous in university students' daily lives, despite its potential to induce over-reliance, metacognitive disengagement, and diminished learning when used unrestrictedly. While most prior research has focused on how to pedagogically scaffold its usage, the question of when to allow off-the-shelf GenAI remains understudied and lacks pedagogically grounded empirical investigation. We treat access timing itself as a form of implicit scaffolding and operationalize it through a reinforcement learning (RL) agent that decides when students should access GenAI, with a reward function grounded in metacognitive theory, cognitive load theory, and productive failure. In a mixed-methods controlled lab study with N=105 higher education students, we compared the agent's effect on learning gains and metacognitive engagement to unrestricted and fully restricted use. Results show that strategically timed GenAI access under the reinforcement learning condition improved objective post-test performance and metacognitive accuracy compared with unrestricted access, without requiring explicit metacognitive prompts or structured scaffolding. Exploratory comparisons with the fully restricted condition further suggest that timed access may reduce task errors and time on task relative to complete withholding. Overall, timing of GenAI access therefore is a tractable, theoretically grounded, and scalable pedagogical strategy that improves over completely unrestricted and withheld access, compatible with off-the-shelf tools and potentially low adoption barrier. This opens up a new research area that explores how access timing can be facilitated by educators and implemented in human-AI learning system design.