Learner simulation skills reduce costs and improve behavior reuse
From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation
Artificial Intelligence
Summary
Repeatedly recreating how a learner behaves during new tasks can be slow and costly. The authors present Learner2Skill, which turns a learner's past behavior into a reusable skill. This skill captures how the learner currently behaves and can adapt over time without starting from scratch. It works with different language models, saving time and computing resources while better copying a learner’s behavior.
What this means in practice
- •For adaptive learning platform developers: Use reusable learner skills to simulate user responses efficiently as learners progress without processing full interaction histories each time.
- •For ai model deployment teams: Calibrate learner simulation skills once and reuse them across different large language model executors to reduce inference costs in personalized systems.
Authors
Zijian Chen, Zheng Zhang, Miao Jia, Xingchen Hu, Weibo Gao, Linan Yue
Abstract
Learner simulation aims to reproduce how a particular learner behaves on new tasks. Although Large Language Models (LLMs) can generate increasingly fine-grained learning behaviors, existing approaches often need to repeatedly process a growing interaction history to reconstruct the learner. This introduces additional context and inference costs and makes the acquired learner-specific simulation capability difficult to reuse across different LLMs. We therefore propose Learner2Skill, which externalizes the simulation capability acquired from historical interactions into a persistent and reusable Simulation Skill. The Skill captures the learner's current learning state and recurring response patterns, evolves as new real interactions arrive, and can be adapted to a new LLM through lightweight executor calibration without reconstructing the learner from scratch. Experiments show that Learner2Skill more faithfully reproduces fine-grained learner behavior while reducing overall token cost, and that the same constructed Skills can be effectively reused across different LLM executors.