Buchumschlag

Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lee, Unggi, Bae, Jiyeong, Park, Jaehyeon, Park, Haeun, Park, Taejun, Jeon, Younghoon, Cho, Sungmin, Koh, Junbo, Jeong, Yeil, Lee, Gyeonggeon
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark
von: Lee, Unggi, et al.
Veröffentlicht: (2025)

OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language Models
von: Lee, Unggi, et al.
Veröffentlicht: (2026)

Reinforcement Learning for Special Education: Aligning LLM Tutors to Diverse Learners through Disability-Adaptive Training
von: Lee, Unggi, et al.
Veröffentlicht: (2026)

LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
von: Lee, Unggi, et al.
Veröffentlicht: (2026)

Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Education
von: Lee, Unggi, et al.
Veröffentlicht: (2026)

From Prediction to Application: Language Model-based Code Knowledge Tracing with Domain Adaptive Pre-Training and Automatic Feedback System with Pedagogical Prompting for Comprehensive Programming Education
von: Lee, Unggi, et al.
Veröffentlicht: (2024)

Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation
von: Lee, Unggi, et al.
Veröffentlicht: (2026)

ES-KT-24: A Multimodal Knowledge Tracing Benchmark Dataset with Educational Game Playing Video and Synthetic Text Generation
von: Kim, Dohee, et al.
Veröffentlicht: (2024)

Rewarding Structural Conformance of Reasoning using Process Mining
von: Lee, Yongjae, et al.
Veröffentlicht: (2025)

How to Align Large Language Models for Teaching English? Designing and Developing LLM based-Chatbot for Teaching English Conversation in EFL, Findings and Limitations
von: Park, Jaekwon, et al.
Veröffentlicht: (2024)

Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Task
von: Lee, Unggi, et al.
Veröffentlicht: (2024)

BIPED: Pedagogically Informed Tutoring System for ESL Education
von: Kwon, Soonwoo, et al.
Veröffentlicht: (2024)

ISD-Agent-Bench: A Comprehensive Benchmark for Evaluating LLM-based Instructional Design Agents
von: Jeon, YoungHoon, et al.
Veröffentlicht: (2026)

Llama-Polya: Instruction Tuning for Large Language Model based on Polya's Problem-solving
von: Lee, Unggi, et al.
Veröffentlicht: (2026)

Process Reward Models That Think
von: Khalifa, Muhammad, et al.
Veröffentlicht: (2025)

How Can Video Generative AI Transform K-12 Education? Examining Teachers' Perspectives through TPACK and TAM
von: Lee, Unggi, et al.
Veröffentlicht: (2025)

I See You: Teacher Analytics with GPT-4 Vision-Powered Observational Assessment
von: Lee, Unggi, et al.
Veröffentlicht: (2024)

Return Prediction for Mean-Variance Portfolio Selection: How Decision-Focused Learning Shapes Forecasting Models
von: Lee, Junhyeong, et al.
Veröffentlicht: (2024)

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
von: Kim, Zae Myung, et al.
Veröffentlicht: (2025)

A Cholesky decomposition-based asset selection heuristic for sparse tangent portfolio optimization
von: Bae, Hyunglip, et al.
Veröffentlicht: (2025)

Exploring the Role of Automated Feedback in Programming Education: A Systematic Literature Review
von: Jung, Yeonji, et al.
Veröffentlicht: (2026)

Pedagogical Methods for Improving Students' Creative Thinking as they Learn
von: Akhmedov Alisher Astanovich, et al.
Veröffentlicht: (2025)

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
von: Park, Yein, et al.
Veröffentlicht: (2025)

‘The Intellectual as Transgressor’: Richard Shaull and Latin American Pedagogical Thinking
von: Danilo R. Streck
Veröffentlicht: (2017)

A Pedagogical Primer: The Ethics of Credit Card Reward Programs
von: David F. Perri, et al.
Veröffentlicht: (2025)

What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning
von: Zhou, Yujin, et al.
Veröffentlicht: (2026)

NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs
von: Lee, Haeun, et al.
Veröffentlicht: (2025)

Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
von: Park, Jihyeong, et al.
Veröffentlicht: (2026)

InvThink: Premortem Reasoning for Safer Language Models
von: Kim, Yubin, et al.
Veröffentlicht: (2025)

Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning
von: Lee, Giwon, et al.
Veröffentlicht: (2025)

Think Twice: Branch-and-Rethink Reasoning Reward Model
von: Jiao, Yizhu, et al.
Veröffentlicht: (2025)

TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation
von: Jeong, Yeil, et al.
Veröffentlicht: (2026)

High School Science Profile Predicts Adults' Views on the Future of AI and STS
von: Lee, Gyeonggeon
Veröffentlicht: (2025)

Artificial Intelligence Generates Stereotypical Images of Scientists but Can Also Detect Them: A Pilot Study Using the Draw-A-Scientist Test
von: Lee, Gyeonggeon
Veröffentlicht: (2025)

From Pedagogical Spaces to Societal Transformation: Advancing Sustainability Education through the Integration of Life Skills and Critical Thinking Competencies
von: Dialogue Social Science Review
Veröffentlicht: (2025)

Integrating Generative AI in Cybersecurity Education: Case Study Insights on Pedagogical Strategies, Critical Thinking, and Responsible AI Use
von: Elkhodr, Mahmoud, et al.
Veröffentlicht: (2025)

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
von: Kim, Wonjoong, et al.
Veröffentlicht: (2026)

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems
von: Olukola, Oluseyi, et al.
Veröffentlicht: (2026)

ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models
von: Park, Seonghwan, et al.
Veröffentlicht: (2025)

Accuracy and Stability of CUR decompositions with Oversampling
von: Park, Taejun, et al.
Veröffentlicht: (2024)