[
    {
        "id": "osp-20610",
        "type": "article-journal",
        "title": "From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation",
        "author": [
            {
                "family": "Chen",
                "given": "Zijian"
            },
            {
                "family": "Zhang",
                "given": "Zheng"
            },
            {
                "family": "Jia",
                "given": "Miao"
            },
            {
                "family": "Hu",
                "given": "Xingchen"
            },
            {
                "family": "Gao",
                "given": "Weibo"
            },
            {
                "family": "Yue",
                "given": "Linan"
            }
        ],
        "URL": "https://omanscience.com/en/articles/from-learner-behavior-to-reusable-skills-for-effective-and-efficient-learner-simulation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]