Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...

Cognitive Learning

Cognitive Learning

Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...

Purposive Learning

Purposive Learning

E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a bonus...

Introduction to Learning

Introduction to Learning

Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...

Associative Learning

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

Reinforcement

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Modular CRISPR-Cas12a-Activated Gold Nanoparticle Assay for Rapid Visual Detection of Hepatocellular Carcinoma-Related miRNAs.

ACS sensors·2026

Same author

Biphasic Memory Impairment and Recovery After Sevoflurane Exposure Are Associated With Time-Dependent Hippocampal α5-GABAAR Remodeling.

CNS neuroscience & therapeutics·2026

Same author

Generative intelligence explores the chemical space of ten million catalysts.

Chemical science·2026

Same author

Integrating multi-omics analysis to identify potential biomarkers and regulatory networks of ischemic stroke.

Progress in neuro-psychopharmacology & biological psychiatry·2026

Same author

Comparative Study of Carbapenemase Inhibitor and NG-Test CARBA5 for the Detection of Carbapenemase of Enterobacteriaceae.

Clinical laboratory·2026

Same author

High-accuracy synchronous distortion-compensated stereo phase measuring deflectometry with orthogonal geometric constraints.

Optics express·2026

Search research articles

Related Experiment Videos

Application-driven pedagogical knowledge optimization of open-source LLMs via reinforcement learning and supervised

Navan Preet Singh¹, Xiaokun Wang², Anurag Garikipati³

¹Department of Research and Development, Forta, Houston, TX, United States.

Frontiers in Artificial Intelligence

|July 16, 2026

Summary

We optimized open-source Large Language Models (LLMs) for education using reinforcement learning (RL) and supervised fine-tuning (SFT). Our EduQwen models achieve state-of-the-art pedagogical knowledge, outperforming larger systems.

Keywords:

LLM application agentic AI digital accessibility open-source pedagogical content knowledge reinforcement learning supervised fine-tuning

Related Experiment Videos

Area of Science:

Artificial Intelligence
Educational Technology
Natural Language Processing

Background:

Large Language Models (LLMs) show promise for educational applications but require specialized optimization for pedagogical tasks.
Open-source LLMs offer transparency and customizability crucial for responsible AI development in education.
Existing general-purpose LLMs may not excel in domain-specific knowledge, such as pedagogy, without targeted training.

Purpose of the Study:

To develop and evaluate a multi-stage optimization strategy for enhancing the pedagogical knowledge of open-source LLMs.
To create a family of optimized open-source pedagogical LLMs (EduQwen) suitable for diverse educational settings, including resource-constrained environments.
To demonstrate that domain-specialized mid-sized LLMs can achieve state-of-the-art performance on pedagogical knowledge benchmarks.

Main Methods:

A multi-stage optimization combining reinforcement learning (RL) with supervised fine-tuning (SFT).
RL stage featured progressive difficulty training, challenging examples, and extended reasoning rollouts for adaptive scaffolding.
SFT stage utilized RL-trained models to synthesize high-quality, difficulty-weighted training data, with an optional second-stage RL refinement.

Main Results:

The developed EduQwen models achieved 96.52% accuracy on the Cross-Domain Pedagogical Knowledge (CDPK) Benchmark.
Established new state-of-the-art (SOTA) performance on the CDPK subset of the Pedagogy Benchmark Leaderboard.
Demonstrated a 5.97 percentage points accuracy gain over Gemini-3 Pro, the previous leader.

Conclusions:

Domain-specialized optimization of mid-sized open-source LLMs can outperform larger general-purpose systems on pedagogical tasks.
The proposed strategy offers a scalable technical approach for wider AI deployment in education, supporting pedagogical tasks.
Open-source pedagogical LLMs provide transparency, customizability, and cost-efficiency for responsible educational AI development.