From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation

2026-09-29

AI Summary

Existing learner simulations require repeatedly processing historical interactions, resulting in high inference costs and limited cross-model reusability. This work proposes Learner2Skill, a framework that externalizes learning behaviors into persistent, standalone simulation skills. By integrating large language models (LLMs), skill representation learning, and executor calibration, the approach supports dynamic skill evolution and enables cross-LLM transferability through lightweight calibration, eliminating the need to reconstruct learner profiles from scratch. Experimental results demonstrate that the proposed framework more faithfully reproduces fine-grained learning behaviors while significantly reducing token consumption and effectively facilitating cross-model transfer.

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.

Problem

• Learner Simulation
• Large Language Models
• Interaction History
• Inference Cost
• Skill Reusability

Innovation

• Learner Simulation
• Reusable Skills
• Large Language Models
• Executor Calibration
• Token Efficiency