arXiv AI

Tracing Mathematical Proficiency Through Problem-Solving Processes

The paper introduces Knowledge Tracing Leveraging Problem‑Solving Process (KT‑PSP), a method that incorporates students’ problem‑solving steps to model mathematical proficiency more comprehensively than traditional knowledge tracing. It presents the KT‑PSP‑25 dataset and a new framework, StatusKT, which uses a teacher‑student‑teacher LLM pipeline to extract proficiency indicators, generate responses, and evaluate mastery. Experiments show that StatusKT improves prediction accuracy and offers interpretable explanations by explicitly modeling proficiency.

arXiv Computation and Language

Aug 31

SMRC: Aligning Large Language Models with Student Reasoning for Mathematical Error Correction

SMRC is a new method that aligns large language models with student reasoning for mathematical error correction. It treats student reasoning as a multi‑step decision problem and uses Monte Carlo Tree Search to find optimal correction paths, while a breadth‑first search guided by the model generates reward signals that are back‑propagated to supervise intermediate steps. The authors also introduce the MSEB benchmark of 158 high‑school math problems and a dual evaluation protocol focusing on solution accuracy and correct‑step retention, showing that SMRC outperforms existing methods on several datasets.

By Biaojie Zeng, Min Zhang, Juan Zhou, Fengrui Liu, Ruiyang Huang, Yu Song, Xin Lin

llms benchmarks

arXiv AI

Jul 16

Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing

arXiv:2607. 13103v1 Announce Type: cross Abstract: Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions.

By Duantengchuan Li, Yingqian Bi, Jinsong Chen, Rui Zhang, Mingwen Tong

llms benchmarks safety

arXiv AI

Aug 25

From Mastery Profile to Simulated Response: Stochastic Student Knowledge Graphs (SSKG) for Faithful LLM Student Simulation

arXiv:2608.21668v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training...

By Yuan An, Emily Wang, Benjamin Wang, Ruhma Hashmi

llms

arXiv Computation and Language

Sep 2

StudentSim: Training LLM-based Student Simulators

arXiv:2609.01591v1 Announce Type: new Abstract: AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for...

By Ke Yang, Chenglong Wang, Michel Galley, Chandan Singh, Jeevana Priya Inala, ChengXiang Zhai, Jianfeng Gao

llms reinforcement-learning

arXiv AI

Jul 28

Masked Distillation: Internalizing the Chain-of-Thought in Language Models

arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.

By Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati

llms efficiency

arXiv AI

2d ago

Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems

The paper introduces Practical Integrated Cross-consistent Knowledge Tracing (PICKT), a model that incorporates multiple feature types to improve Knowledge Tracing robustness when new questions lack interaction history. It evaluates the impact of difficulty, textual, and knowledge‑map relational features, finding that difficulty is especially informative for hard questions, while fused text and map features help estimate unseen questions by leveraging similar ones seen during training. The study concludes that prioritizing feature annotation aligned with educational service characteristics is essential for maintaining robust diagnostics in Intelligent Tutoring Systems.

By Wonbeen Lee, Channyoung Lee, Junho Sohn, Hansam Cho

arXiv AI

Aug 18

Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs

arXiv:2603. 02830v2 Announce Type: replace-cross Abstract: Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions.

By Prarthana Bhattacharyya, Joshua Mitton, Ralph Abboud, Simon Woodhead

llms efficiency

arXiv AI

Jul 7

Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing

arXiv:2607. 04572v1 Announce Type: new Abstract: Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pedagogically formatted response does not guarantee that the answer was derived from the student-facing problem.

By Bonan Shen, Dingyan Shang, Youting Wang, Tao Ning

llms

arXiv AI

Aug 5

EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners

arXiv:2608. 03206v1 Announce Type: cross Abstract: Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS).

By Unggi Lee, Sookbun Lee, Yeil Jeong, Eunjoo Lee, Minchul Shin, Hoilym Kwon

llms agents benchmarks

arXiv AI

Jul 8

SCOReD: Student-Aware CoT Optimization for Recommendation Distillation

arXiv:2607. 05734v1 Announce Type: cross Abstract: Chain-of-thought (CoT) distillation in the recommendation domain is a necessary precursor to RL training, but raw teacher traces are ill-suited to this task.

By Haz Sameen Shahgir, Yufei Li, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Yue Dong

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Jun 10

RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning

arXiv:2606. 10254v1 Announce Type: new Abstract: While Large Language Models (LLMs) have achieved near-perfect performance in \emph{solving} high-school mathematics, their ability to \emph{evaluate} the diverse reasoning processes of real human students remains under-examined.

By Yiteng Mao, Kenan Xu, Yijia Lyu, Wenhao Li, Jianlong Chen, Xiangfeng Wang

llms rag benchmarks

arXiv AI

Sep 1

MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation

arXiv:2608.29623v1 Announce Type: cross Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning...

By Yangsong Lan, Renkai Hu, HongKai Zheng, Bo Zhang, Renzhi Wang, Hongliang Dai, Piji Li

efficiency benchmarks safety

Related stories