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

• URL: http://arxiv.org/abs/2601.14560v1
• Date: Wed, 21 Jan 2026 00:58:49 GMT
• Title: Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education
• Abstract summary: Large language models (LLMs) are increasingly deployed as intelligent tutoring systems.<n>Recent works have proposed reinforcement learning approaches for training LLM tutors, but these methods focus solely on optimizing visible responses.<n>We introduce PedagogicalRL-Thinking, a framework that extends pedagogical alignment to reasoning LLMs in education.
• Score: 6.168298906927059
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed as intelligent tutoring systems, yet research on optimizing LLMs specifically for educational contexts remains limited. Recent works have proposed reinforcement learning approaches for training LLM tutors, but these methods focus solely on optimizing visible responses while neglecting the model's internal thinking process. We introduce PedagogicalRL-Thinking, a framework that extends pedagogical alignment to reasoning LLMs in education through two novel approaches: (1) Pedagogical Reasoning Prompting, which guides internal reasoning using domain-specific educational theory rather than generic instructions; and (2) Thinking Reward, which explicitly evaluates and reinforces the pedagogical quality of the model's reasoning traces. Our experiments reveal that domain-specific, theory-grounded prompting outperforms generic prompting, and that Thinking Reward is most effective when combined with pedagogical prompting. Furthermore, models trained only on mathematics tutoring dialogues show improved performance on educational benchmarks not seen during training, while preserving the base model's factual knowledge. Our quantitative and qualitative analyses reveal that pedagogical thinking reward produces systematic reasoning trace changes, with increased pedagogical reasoning and more structured instructional decision-making in the tutor's thinking process.

Related papers

• INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning [61.60016491769943]
  In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding.<n>We propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI) with a stage-wise preference training strategy.<n>Experiments across multiple model scales and families demonstrate consistent improvements, even surpassing larger open-source models.
  arXiv  Detail & Related papers  (2026-08-27T03:24:03Z)
• Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework [18.26798940982428]
  The capacity of Large Language Models to reason about pedagogical intent within instructional communication remains underexplored.<n>We propose the textbfAdaptive Pedagogical Vigilance (APV) framework, a novel computational formalism.<n>APV formalizes the problem via a Bayesian Pedagogical Intent Inference Engine (PIIE)
  arXiv  Detail & Related papers  (2026-07-02T01:26:09Z)
• ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models [76.28894983518164]
  Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs)<n>They often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers.<n>We introduce ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains.
  arXiv  Detail & Related papers  (2025-08-17T14:50:23Z)
• Partnering with AI: A Pedagogical Feedback System for LLM Integration into Programming Education [21.37197118335639]
  This paper introduces a novel framework for large language models (LLMs)-driven feedback generation.<n>Our findings suggest that teachers consider that, when aligned with the framework, LLMs can effectively support students.<n>However, we found several limitations, such as its inability to adapt feedback to dynamic classroom contexts.
  arXiv  Detail & Related papers  (2025-07-01T03:48:48Z)
• Improving Student-AI Interaction Through Pedagogical Prompting: An Example in Computer Science Education [1.1517315048749441]
  Large language model (LLM) applications have sparked both excitement and concern.<n>Recent studies consistently highlight students' (mis)use of LLMs can hinder learning outcomes.<n>This work aims to teach students how to effectively prompt LLMs to improve their learning.
  arXiv  Detail & Related papers  (2025-06-23T20:39:17Z)
• A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models [103.88578274567784]
  Motivation-enhanced Reinforcement Finetuning (MeRF) is an intuitive yet effective method enhancing reinforcement finetuning of Large Reasoning Models.<n>MeRF directly injects the reward specification into the prompt, which serves as an in-context motivation for the model to be aware of the optimization objective.<n>MeRF achieves substantial performance gains over RLVR baseline.
  arXiv  Detail & Related papers  (2025-06-23T10:37:57Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [93.00629872970364]
  Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks.<n>We introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions.<n>We study whether difficult problems -- those yielding no RL signals and mixed-quality reasoning traces -- can still be effectively used for training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark [6.024228339466189]
  Large reasoning models (LRMs) show strong performance in structured domains such as mathematics and programming.<n>LRMs often lack pedagogical coherence and realistic teaching behaviors.<n>We introduce Pedagogy-R1, a framework that adapts LRMs for classroom use through three innovations.
  arXiv  Detail & Related papers  (2025-05-24T02:18:35Z)
• From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning [82.50157695987558]
  Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy.<n>We propose an online reinforcement learning (RL)-based alignment framework that can quickly adapt LLMs into effective tutors.
  arXiv  Detail & Related papers  (2025-05-21T15:00:07Z)
• Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training [86.70255651945602]
  We introduce a novel inference-time steering methodology called Reinforcing Cognitive Experts (RICE)<n>RICE aims to improve reasoning performance without additional training or complexs.<n> Empirical evaluations with leading MoE-based LRMs demonstrate noticeable and consistent improvements in reasoning accuracy, cognitive efficiency, and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-05-20T17:59:16Z)
• EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework [9.76455227840645]
  Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging.<n>We introduce EducationQ, a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios.
  arXiv  Detail & Related papers  (2025-04-21T07:48:20Z)
• Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues [46.60683274479208]
  We introduce an approach to train large language models (LLMs) to generate tutor utterances that maximize the likelihood of student correctness.<n>We show that tutor utterances generated by our model lead to significantly higher chances of correct student responses.
  arXiv  Detail & Related papers  (2025-03-09T03:38:55Z)
• MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors [82.91830877219822]
  We present MathTutorBench, an open-source benchmark for holistic tutoring model evaluation.<n>MathTutorBench contains datasets and metrics that broadly cover tutor abilities as defined by learning sciences research in dialog-based teaching.<n>We evaluate a wide set of closed- and open-weight models and find that subject expertise, indicated by solving ability, does not immediately translate to good teaching.
  arXiv  Detail & Related papers  (2025-02-26T08:43:47Z)
• LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement [93.38736019287224]
  "LLMs-as-Instructors" framework autonomously enhances the training of smaller target models. Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model. Within this framework, we implement two strategies: "Learning from Error," which focuses solely on incorrect responses to tailor training data, and "Learning from Error by Contrast", which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors.
  arXiv  Detail & Related papers  (2024-06-29T17:16:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.