Off-policy reinforcement learning in continuous control tasks depends critically on accurate $Q$-value estimates. Conservative aggregation over ensembles, such as taking the minimum, is commonly used to mitigate overestimation bias. However, these static rules are coarse, discard valuable information from the ensemble, and cannot adapt to task-specific needs or different learning regimes. We propose Directional Ensemble Aggregation (DEA), an aggregation method that adaptively combines $Q$-value estimates in actor-critic frameworks. DEA introduces two fully learnable directional parameters: one that modulates critic-side conservatism and another that guides actor-side policy exploration. Both parameters are learned using ensemble disagreement-weighted Bellman errors, which weight each sample solely by the direction of its Bellman error. This directional learning mechanism allows DEA to adjust conservatism and exploration in a data-driven way, adapting aggregation to both uncertainty levels and the phase of training. We evaluate DEA across continuous control benchmarks and learning regimes - from interactive to sample-efficient - and demonstrate its effectiveness over static ensemble strategies.

As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI research and enabling industry adoption, we present key insights and lessons learned from practical interpretability applications across diverse domains. This paper offers actionable strategies and implementation guidance tailored to organizations at varying stages of AI maturity, emphasizing the integration of interpretability as a core design principle rather than a retrospective add-on.

UML and ER diagrams are foundational in computer science education but come with challenges for learners due to the need for abstract thinking, contextual understanding, and mastery of both syntax and semantics. These complexities are difficult to address through traditional teaching methods, which often struggle to provide scalable, personalized feedback, especially in large classes. We introduce DUET (Diagrammatic UML & ER Tutor), a prototype of an LLM-based tool, which converts a reference diagram and a student-submitted diagram into a textual representation and provides structured feedback based on the differences. It uses a multi-stage LLM pipeline to compare diagrams and generate reflective feedback. Furthermore, the tool enables analytical insights for educators, aiming to foster self-directed learning and inform instructional strategies. We evaluated DUET through semi-structured interviews with six participants, including two educators and four teaching assistants. They identified strengths such as accessibility, scalability, and learning support alongside limitations, including reliability and potential misuse. Participants also suggested potential improvements, such as bulk upload functionality and interactive clarification features. DUET presents a promising direction for integrating LLMs into modeling education and offers a foundation for future classroom integration and empirical evaluation.

Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature of teacher-student interactions. We introduce EducationQ, a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios, featuring specialized agents for teaching, learning, and evaluation. Testing 14 LLMs across major AI Organizations (OpenAI, Meta, Google, Anthropic, and others) on 1,498 questions spanning 13 disciplines and 10 difficulty levels reveals that teaching effectiveness does not correlate linearly with model scale or general reasoning capabilities - with some smaller open-source models outperforming larger commercial counterparts in teaching contexts. This finding highlights a critical gap in current evaluations that prioritize knowledge recall over interactive pedagogy. Our mixed-methods evaluation, combining quantitative metrics with qualitative analysis and expert case studies, identifies distinct pedagogical strengths employed by top-performing models (e.g., sophisticated questioning strategies, adaptive feedback mechanisms). Human expert evaluations show 78% agreement with our automated qualitative analysis of effective teaching behaviors, validating our methodology. EducationQ demonstrates that LLMs-as-teachers require specialized optimization beyond simple scaling, suggesting next-generation educational AI prioritize targeted enhancement of specific pedagogical effectiveness.

This paper aims to develop a Machin e Learning (ML) - based system for detecting honey adulteration utilizing honey mineral element profiles. The proposed system comprises two phases: preprocessing and classification. The preprocessing phase involves the treatment of missing - value attributes a nd normalization. In the classification phase, we use three supervised ML models: logistic regression, d ecision tree, and random forest, to discriminate between authentic and adulterated honey. To evaluate the performance of the ML models, we use a public dataset comprising measurements of mineral element content of authentic honey, sugar syrups, and adulterated honey. Experimental findings show that mineral element content in honey provides robust discriminative information for detecting honey adulteration . Results also dem onstrate that the random forest - based classifier outperforms other classifiers on this dataset, achieving the highest cross - validation accuracy of 98.37%.

We present an automated evaluation system for assessing COBOL-to-Java code translation within IBM's watsonx Code Assistant for Z (WCA4Z). The system addresses key challenges in evaluating LLM-based translators, including model opacity and the complexity of translation quality assessment. Our approach combines analytic checkers with LLM-as-a-judge (LaaJ) techniques to deliver scalable, multi-faceted evaluations. The system supports continuous integration workflows, enables large-scale benchmarking, and reduces reliance on manual review. We describe the system architecture, evaluation strategies, and reporting mechanisms that provide actionable insights for developers and project managers, facilitating the evolution of high-quality, modernized codebases.

This paper introduces a novel benchmark, EGE-Math Solutions Assessment Benchmark, for evaluating Vision-Language Models (VLMs) on their ability to assess hand-written mathematical solutions. Unlike existing benchmarks that focus on problem solving, our approach centres on understanding student solutions, identifying mistakes, and assigning grades according to fixed criteria. We compile 122 scanned solutions from the Russian Unified State Exam (EGE) together with official expert grades, and evaluate seven modern VLMs from Google, OpenAI, Arcee AI, and Alibaba Cloud in three inference modes. The results reveal current limitations in mathematical reasoning and human-rubric alignment, opening new research avenues in AI-assisted assessment. You can find code in https://github.com/Karifannaa/Auto-check-EGE-math

This paper presents a keystroke-based framework for detecting LLM-assisted cheating in Korean, addressing key gaps in prior research regarding language coverage, cognitive context, and the granularity of LLM involvement. Our proposed dataset includes 69 participants who completed writing tasks under three conditions: Bona fide writing, paraphrasing ChatGPT responses, and transcribing ChatGPT responses. Each task spans six cognitive processes defined in Bloom's Taxonomy (remember, understand, apply, analyze, evaluate, and create). We extract interpretable temporal and rhythmic features and evaluate multiple classifiers under both Cognition-Aware and Cognition-Unaware settings. Temporal features perform well under Cognition-Aware evaluation scenarios, while rhythmic features generalize better under cross-cognition scenarios. Moreover, detecting bona fide and transcribed responses was easier than paraphrased ones for both the proposed models and human evaluators, with the models significantly outperforming the humans. Our findings affirm that keystroke dynamics facilitate reliable detection of LLM-assisted writing across varying cognitive demands and writing strategies, including paraphrasing and transcribing LLM-generated responses.

The emergence of Large Language Models (LLMs) presents transformative opportunities for education, generating numerous novel application scenarios. However, significant challenges remain: evaluation metrics vary substantially across di ff erent educational scenarios, while many emerging scenarios lack appropriate assessment metrics. To address this gap, we introduce ELMES, an open-source automated evaluation framework specifically designed for assessing LLMs in educational settings. ELMES features a modular architecture that enables researchers to create dynamic, multi-agent dialogues through simple configuration files, facilitating flexible scenario design without requiring extensive programming expertise. The framework incorporates a hybrid evaluation engine that objectively quantifies traditionally subjective pedagogical metrics using an LLM-as-a-Judge methodology. We conduct systematic benchmarking of state-of-the-art LLMs across four critical educational scenarios: Knowledge Point Explanation, Guided Problem-Solving Teaching, Interdisciplinary Lesson Plan Generation, and Contextualized Question Generation, employing fine-grained metrics developed in collaboration with education specialists. Our results demonstrate distinct capability distributions among models, revealing context-specific strengths and limitations. ELMES provides educators and researchers with an accessible evaluation framework that significantly reduces adaptation barriers for diverse educational applications while advancing the practical implementation of LLMs in pedagogy. Introduction The advent of Large Language Models (LLMs) is reshap-ing the educational paradigm with unprecedented potential [1]. Their powerful capabilities in natural language understanding and generation have paved new ways for intelligent teaching and learning. Consequently, researchers are actively exploring various avenues to leverage LLMs for educational empowerment.

We present SmartCourse, an integrated course management and AI-driven advising system for undergraduate students (specifically tailored to the Computer Science (CPS) major). SmartCourse addresses the limitations of traditional advising tools by integrating transcript and plan information for student-specific context. The system combines a command-line interface (CLI) and a Gradio web GUI for instructors and students, manages user accounts, course enrollment, grading, and four-year degree plans, and integrates a locally hosted large language model (via Ollama) for personalized course recommendations. It leverages transcript and major plan to offer contextual advice (e.g., prioritizing requirements or retakes). We evaluated the system on 25 representative advising queries and introduced custom metrics: PlanScore, PersonalScore, Lift, and Recall to assess recommendation quality across different context conditions. Experiments show that using full context yields substantially more relevant recommendations than context-omitted modes, confirming the necessity of transcript and plan information for personalized academic advising. SmartCourse thus demonstrates how transcript-aware AI can enhance academic planning.