Time and Trade-offs: A Preliminary Study of LLM Latency in Math Automatic Question Generation

#artificial intelligence Preprint Aug 2026

Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck

The first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing is conducted - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation.

Davide Romano, Kanak Raj, Jerrod Parker et al. · 0 citations

Preprint Aug 2026

Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors

While LLM-rewritten messages significantly improved subjective evaluations, with pragmatic messages rated as clearer and less cognitively demanding, these perceived gains did not translate into statistically significant improvements in objective debugging performance.

Alexandru-Radu Moraru, Shreyan Biswas, U. Gadiraju · 0 citations

Conference Aug 2026

Dual-Signal Explainability for LLM-Based Automated Grading and Feedback: A Pilot Study

The provision of prompt and customized feedback on student responses in descriptive questions continues to be a difficult problem for educators in virtual and hybrid education systems. The paper introduces the Explainable AI Grading Framework (XAIGF), which is a fusion of two paradigms - semantic evaluation through Lar...

Pratap P. Nayadkar, Shilpa Gite, Swati Sharma et al. · International Conference on... · 0 citations

#large language models Open access Sep 2026

Human-AI Interaction: Evaluating LLM Reasoning on Digital Logic Circuits and the Perception-Correctness Gap

Evaluating three widely used LLMs on 10 undergraduate-level digital logic questions spanning non-standard counters, JK-based state transitions, timing diagrams, frequency division, and finite-state machines suggests that they may be unreliable for core digital logic topics and can inadvertently reinforce misconceptions...

Yogeswar Reddy Thota, Setareh Rafatirad, Homayoun Houman et al. · SN Computer Science · 0 citations

Open access 2026

From Code Generation to Code Auditing: Constrained AI Scaffolding, Transfer, and Cognitive Efficiency in Debugging

Generative artificial intelligence is reshaping programming education, yet its effects on skill development depend partly on how learners interact with artificial intelligence-supported systems. This study introduces the Artificial Intelligence-Scaffolding Interaction Framework, which conceptualizes constrained, questi...

M. Yenidogan, Zeynep Cömert, Duygu Çakır · IEEE Access · 0 citations

#artificial intelligence Preprint Aug 2026

Test-Time Scaling for Scientific Equation Discovery

This work forms LLM-driven equation discovery as an iterative search process that unifies Best-of-N, sequential refinement, tree search, and evolution-style methods under a common compute-allocation view and finds that search width is the dominant allocation parameter.

Hao-Wei Lin, Hubert Lim, Xiang-Yu Wang et al. · 0 citations