发表机构
National University of Defense Technology; Nanyang Technological University; The Hong Kong Polytechnic University; Southeast University（国防科技大学; 南洋理工大学; 香港理工大学; 东南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Learner2Skill，将学习者模拟能力外部化为可复用技能，降低推理成本并支持跨LLM复用，实验证明其更忠实且高效。
AI 中文摘要
学习者模拟旨在重现特定学习者在新任务上的行为方式。尽管大型语言模型（LLMs）能够生成日益细粒度的学习行为，现有方法往往需要反复处理不断增长的交互历史以重建学习者。这引入了额外的上下文和推理成本，并使得所获得的学习者特定模拟能力难以在不同LLM之间复用。因此，我们提出Learner2Skill，将从历史交互中获得的模拟能力外部化为一种持久且可复用的模拟技能。该技能捕获学习者当前的学习状态和反复出现的响应模式，随着新的真实交互到来而演进，并可通过轻量级的执行器校准适应新的LLM，而无需从头重建学习者。实验表明，Learner2Skill在降低总体token成本的同时，更忠实地再现了细粒度的学习者行为，并且所构建的技能可有效复用于不同的LLM执行器。
英文摘要
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.
Comments16 pages
