StudentSim：訓練基於LLM的學生模擬器

摘要

AI導師在適應每位學生的優勢、劣勢以及偏好的引導方式時最具效用，但關於哪種引導對哪種學生有效的證據，從真實學習者身上收集既稀疏、緩慢且成本高昂。學生模擬器可作為代理提供此一訊號，然而現有方法有其局限：狀態追蹤模型雖能貼合學生行為，但在處理解釋或糾正方面卻有困難；而LLM角色扮演雖能流暢地遵循引導，卻無法可靠地匹配被模仿學生的能力。我們提出StudentSim，這是一個訓練框架，透過彙整訓練接著進行個別學生的特化，將稀疏的每學生資料轉化為個人化的模擬器。所產生的模擬器既能反映學生自身的回應，也能在導師引導下更新這些回應。我們亦提出StudentSimEval，這是一項標準化評估方案，涵蓋60名學生，橫跨西洋棋、第二語言英語寫作與數學領域，並使用公開的學習者資料集，其中包含為研究而共享的去識別化記錄。StudentSimEval衡量行為保真度(F，即模擬器與學生回應的匹配程度）以及引導回應性(R，即在導師引導下更新的容易程度）；所有方法皆以相同的記錄進行擬合與評估。在這三個領域中，StudentSim在兩項指標上皆優於GPT-5.4。在西洋棋方面，StudentSim達到F=0.51與R=0.91，相較之下GPT-5.4為0.23與0.72，Maia2則為0.45與0.27。作為概念驗證，以StudentSim作為導師強化學習的獎勵模型所訓練出的西洋棋導師，人類專家評其比無RL基線以及以GPT-5.4模擬器獎勵訓練的導師更準確、引導更佳且更具個人化。程式碼可在 https://github.com/microsoft/StudentSim 取得。

English

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-language English writing, and mathematics, using public learner datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.

StudentSim：訓練基於LLM的學生模擬器

StudentSim: Training LLM-based Student Simulators

摘要

Support