Napat Sukthong

Mr. Napat Sukthong

Department of Computer Science, Mahasarakham University, Maha Sarakham, Thailand
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2025
Verified
Conference Paper
Closed access
NSNapat Sukthong
Napat Sukthong
One of the persistent shortcomings of modern AI lies in its difficulty reasoning effectively and maintaining situational awareness in fast-changing, unpredictable settings. To address this challenge, we present a framework that combines Generative AI and Agentic AI within a unified system incorporating both spatial and temporal reasoning, guided by principles from cognitive science. The framework was evaluated in a simulated urban environment designed to pose demanding tasks involving environmental interpretation, multi-step planning, and the use of memory for informed decision-making. In these trials validated in a controlled simulation with 1,000 test cases, it achieved a task accuracy of 92.4%, outperforming several widely used baseline models. An ablation analysis revealed that spatial reasoning, temporal reasoning, and cognitive memory each contribute significantly and independently to overall performance. These findings highlight the framework’s potential and open new avenues for applications in robotics, geospatial intelligence, and the advancement of autonomous vehicle technologies.

9 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
NSNapat Sukthong
Napat Sukthong
Spatial relation predictors should respect geometric symmetry while representing un-certainty. We study relation networks in the Region Connection Calculus with eight base relations (RCC-8), combining averaging over square symmetries and pair reversal, scene-level split conformal calibration, and sound algebraic closure. We prove score equivariance and exact preservation of the complete-scene coverage event by closure for realizable ground truth. Exchangeable calibration and test scenes yield a finite-sample coverage guarantee without requiring a symmetry-invariant population. Experiments use 17,400 synthetic rectangle scenes, two classifier families, and three seeds. At nominal 90% scene coverage, the complete method obtains 89.00% empirical coverage with a multilayer perceptron and 89.13% with extremely randomized trees, with 1.554 and 1.689 labels per directed pair. Mean set sizes decrease by 6.71% and 3.81% relative to raw scene calibration; closure contributes modest additional reductions. After pair-marginal calibration, closure instead lowers pair coverage from 89.73% to 77.27% and from 90.38% to 81.50%. Increased noise or scene size compromises coverage when calibration thresholds remain unchanged. The findings identify when sound spatial propagation preserves a statistical guarantee and demonstrate why the calibration unit must match the structured prediction target.


16 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
NSNapat Sukthong
Napat Sukthong
Generative artificial intelligence (GenAI) can make introductory programming tasks easier to complete, but a working program is not evidence of durable learning. This conceptual-theoretical paper integrates research on cognitive load, metacognition, self-explanation, productive failure, appropriate reliance on automation, and recent studies of AI-assisted programming to propose a five-phase cognitive-scaffolding framework. Learners first make an unaided attempt, request bounded assistance, verify the response against requirements and independently designed tests, explain the mechanism and calibrate confidence, and then complete a related transfer task as support fades. AI literacy, ethical disclosure, privacy, and instructor orchestration operate across all phases. The framework identifies process evidence that remains inspectable when generated code is available, including problem representations, hypotheses, verification records, explanations, confidence judgments, and unaided transfer. It also states six testable propositions and an evaluation blueprint for introductory programming courses. The contribution is a bounded design logic, not a claim that the sequence has already been validated: GenAI should reduce avoidable burden while leaving consequential decisions, checks, and explanations with the learner.