paper-with-me

Skill Mastery

1개 벤치마크 · 논문 15편 · 이 태스크의 논문 보기 →

Benchmarks

RGB-Stacking

결과 2개

Most implemented

A Generalist Agent

2022-05-12 · 구현 3개

GPT-based Open-Ended Knowledge Tracing

2022-02-21 · 구현 1개

Papers

Estimating Learners' Skill Acquisition Without Temporal Information

2026-05-22 · Ryosuke Nagai, Kyohei Atarashi, Koh Takeuchi, Jill-Jênn Vie 외 arxiv

Recent research in educational data mining, especially knowledge tracing, has focused on predicting learners' future knowledge states to support adaptive instruction. However, in many real-world educational settings, lea…

Knowledge TracingSkill Mastery

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

2026-05-09 · Min Yang, Jinghua Piao, Xu Xia, Xiaochong Lan 외 arxiv

Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rule…

Skill Mastery

Scaling Coding Agents via Atomic Skills

2026-04-06 · Yue Liu arxiv

Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting and limited generalization. To address this, we propose a novel scaling parad…

Skill Mastery

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning

2026-03-10 · Zhanyi Sun, Shuran Song arxiv

We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies. DICE-RL t…

Reinforcement LearningSkill Mastery

Problems With Large Language Models for Learner Modelling: Why LLMs Alone Fall Short for Responsible Tutoring in K--12 Education

2025-12-28 · Danial Hooshyar, Yeongwook Yang, Gustav Šíř, Tommi Kärkkäinen 외 arxiv

The rapid rise of large language model (LLM)-based tutors in K--12 education has fostered a misconception that generative models can replace traditional learner modelling for adaptive instruction. This is especially prob…

Knowledge TracingSkill Mastery

Enhanced Interpretable Knowledge Tracing for Students Performance Prediction with Human understandable Feature Space

2025-09-22 · Sein Minn, Roger Nkambou arxiv

Knowledge Tracing (KT) plays a central role in assessing students skill mastery and predicting their future performance. While deep learning based KT models achieve superior predictive accuracy compared to traditional me…

Knowledge TracingSkill Mastery

전체 15편 보기 →