Skip to content
Log in
#small language model Review Open access

Augmented Reality Supported by Deep-Learning-Oriented Pedagogy for Solar System Learning: Development and Preliminary Evaluation of Junior High School Students’ Creative Thinking

Bagas Brilian Ramadhan Mei Wulan S. Yamtinah Bayu Antrakusuma
Aug 2026 · Kognisi: Jurnal Ilmu Keguruan · 0 citations · 42 references

TL;DR

An augmented reality learning medium integrated with a deep-learning-oriented pedagogy for the Solar System topic supports the feasibility and educational promise of combining interactive AR visualization with cognitively engaging pedagogy.

Abstract

Creative thinking is increasingly recognized as a core learning outcome in science education, yet abstract astronomical concepts can be difficult for junior high school students to explore through conventional two-dimensional media. This study developed and preliminarily evaluated an augmented reality (AR) learning medium integrated with a deep-learning-oriented pedagogy for the Solar System topic. In this article, deep learning refers to an educational approach that emphasizes active knowledge construction, meaningful connections, reflection, and sustained cognitive engagement rather than artificial-intelligence deep learning. The study employed a Research and Development design using the ADDIE model. Two expert validators reviewed the product, and the implementation involved 32 Grade VII students selected through cluster random sampling from a population of 296 students at SMP Negeri 3 Karanganyar, Indonesia; a small-scale trial involved 10 students, and two science teachers provided practicality responses. Data were collected through observation, interviews, expert-validation questionnaires, student and teacher response questionnaires, and a 10-item pretest-posttest instrument adapted from the Torrance Test of Creative Thinking dimensions of fluency, flexibility, originality, and elaboration. Expert-validation coefficients were .89 for AR media, .82 for content and language, .87 for the deep-learning lesson plan, and .80 for test content. Practicality ratings reached 83% in the small-scale trial, 88% among students in the limited-scale implementation, and 91% among teachers. A paired-samples comparison indicated a significant pre-post difference (p = .001), while the mean normalized gain was .4460, representing a moderate improvement. Fluency showed the largest gain (.4683) and elaboration the smallest (.3495). The findings support the feasibility and educational promise of combining interactive AR visualization with cognitively engaging pedagogy. Because the implementation used a one-group pretest-posttest design without a control group, the results should be interpreted as preliminary evidence rather than a causal estimate of effectiveness.

DOI Semantic Scholar
Read PDF

Similar papers

#small language model Open access Aug 2026

LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences

LifeSciBench is introduced, a benchmark of 750 expert-authored tasks designed to evaluate whether language models can handle realistic life science research work, with each constituent task paired with a human expert-written rubric.

Amelia Liu, Andrew Ho, Anne Marie Droste et al. · 2 citations
#small language model Preprint Aug 2026

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

Experimental results show that CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods, while requiring significantly fewer generations and lower token cost.

Yu-Fan Wu, Yinghui He, Zhengyi Hu et al. · 1 citation
#artificial intelligence Preprint Aug 2026

TestifAI: Tomography-Based Testing for Deep Learning Systems

TestifAI, a deep learning testing framework for efficient and accurate estimation of robustness against combinations of perturbations, is proposed and partial model tomography is introduced, a novel approach to reconstructing model behaviour in a multi-perturbation space from tests that apply only a small number of perturbations.

Arooj Arif, T. Hartung, E. Botoeva et al. · 1 citation
#small language model Sep 2026

Low Carbon Scheduling of Integrated Energy System Based on Large Language Model-Embedded Multi-Agent Reinforcement Learning

The complex multi-energy coupling characteristics inherent to integrated energy system (IES) present unprecedented challenges for the implementation of low-carbon scheduling. Existing optimization methods often exhibit limitations in system scalability, algorithm adaptivity, and carbon reduction efficacy for complex IES. This paper proposes a Large Language Model (LLM)-Embedded Multi-Agent Reinforcement Learning (LEMARL) to address the aforementioned issues. The proposed method integrates the global perception capability of LLMs with the dynamic optimization capability of MARL. Specifically, the LLM-Embedded module generates high-quality reward functions and policy frameworks from a global perspective, while the MARL module leverages these LLM-generated strategies for distributed interactive iterations—greatly enhancing computation efficiency and scalability. Simulation results demonstrate that LEMARL reduces carbon emissions by 7.76% and simultaneously decreases operating costs by 4.49% in a small-scale IES. Furthermore, LEMARL also exhibits superior applicability and scalability in large-scale IES of the IEEE 141-bus power grid integrated with 51-node thermal system.

Chen Xia, Tong Gou, Yinliang Xu et al. · 1 citation
#small language model Preprint Aug 2026

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this \emph{working capability}: sustained, verifiable progress toward a real-world objective. Apodex 1.1 develops this capability along two complementary dimensions. \emph{Environment Scaling} expands the diversity and verifiability of executable file, search, and code environments, while \emph{Agentic Coordination Scaling} trains agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan. A shared execution harness and AgentOS maintain task state and provenance across tools and agents, and training turns environment trajectories and coordination traces into reliable behavior. Across complex professional work, finance, scientific research, mathematics, coding, and search, Apodex 1.1 reaches the leading performance band despite using a substantially smaller model than many frontier systems. The 35B-parameter Apodex 1.1 Mini further retains strong working capability in a locally deployable form. These results ground agentic intelligence in useful, verifiable work completed over time and advance our goal of building a \emph{Heavy-Duty Solver} for ambitious, long-running tasks.

Apodex Team B. An, B. Li, B. Wang et al. · 1 citation

Related blog posts