We present a new approach for designing risk-bounded controllers for Uncrewed Aerial Vehicles (UAVs). Existing frameworks for assessing risk of UAV operations rely on knowing the conditional probability of an incident occurring given different causes. Limited data for computing these probabilities makes real-world implementation of these frameworks difficult. Furthermore, existing frameworks do not include control methods for risk mitigation. Our approach relies on UAV dynamics, and employs reachability analysis for a probabilistic risk assessment over all feasible UAV trajectories. We use this holistic risk assessment to formulate a control optimization problem that minimally changes a UAV's existing control law to be bounded by an accepted risk threshold. We call our approach PRReach. Public and readily available UAV dynamics models and open source spatial data for mapping hazard outcomes enables practical implementation of PRReach for both offline pre-flight and online in-flight risk assessment and mitigation. We evaluate PRReach through simulation experiments on real-world data. Results show that PRReach controllers reduce risk by up to 24% offline, and up to 53% online from classical controllers.

We introduce a new reading comprehension dataset, dubbed MultiWikiQA, which covers 306 languages. The context data comes from Wikipedia articles, with questions generated by an LLM and the answers appearing verbatim in the Wikipedia articles. We conduct a crowdsourced human evaluation of the fluency of the generated questions across 30 of the languages, providing evidence that the questions are of good quality. We evaluate 6 different language models, both decoder and encoder models of varying sizes, showing that the benchmark is sufficiently difficult and that there is a large performance discrepancy amongst the languages. The dataset and survey evaluations are freely available.

Counting mitotic figures is time-intensive for pathologists and leads to inter-observer variability. Artificial intelligence (AI) promises a solution by automatically detecting mitotic figures while maintaining decision consistency. However, AI tools are susceptible to domain shift, where a significant drop in performance can occur due to differences in the training and testing sets, including morphological diversity between organs, species, and variations in staining protocols. Furthermore, the number of mitoses is much less than the count of normal nuclei, which introduces severely imbalanced data for the detection task. In this work, we formulate mitosis detection as a pixel-level segmentation and propose a teacher-student model that simultaneously addresses mitosis detection (Track 1) and atypical mitosis classification (Track 2). Our method is based on a UNet segmentation backbone that integrates domain generalization modules, namely contrastive representation learning and domain-adversarial training. A teacher-student strategy is employed to generate pixel-level pseudo-masks not only for annotated mitoses and hard negatives but also for normal nuclei, thereby enhancing feature discrimination and improving robustness against domain shift. For the classification task, we introduce a multi-scale CNN classifier that leverages feature maps from the segmentation model within a multi-task learning paradigm. On the preliminary test set, the algorithm achieved an F1 score of 0.7660 in Track 1 and balanced accuracy of 0.8414 in Track 2, demonstrating the effectiveness of integrating segmentation-based detection and classification into a unified framework for robust mitosis analysis.

Integrating generative AI such as Large Language Models into social robots has improved their ability to engage in natural, human-like communication. This study presents a method to examine their persuasive capabilities. We designed an experimental framework focused on decision making and tested it in a pilot that varied robot appearance and self-knowledge. Using qualitative analysis, we evaluated interaction quality, persuasion effectiveness, and the robot's communicative strategies. Participants generally experienced the interaction positively, describing the robot as competent, friendly, and supportive, while noting practical limits such as delayed responses and occasional speech-recognition errors. Persuasiveness was highly context dependent and shaped by robot behavior: Participants responded well to polite, reasoned suggestions and expressive gestures, but emphasized the need for more personalized, context-aware arguments and clearer social roles. These findings suggest that generative social robots can influence user decisions, but their effectiveness depends on communicative nuance and contextual relevance. We propose refinements to the framework to further study persuasive dynamics between robots and human users.

Understanding human behavior in urban environments is a crucial field within city sciences. However, collecting accurate behavioral data, particularly in newly developed areas, poses significant challenges. Recent advances in generative agents, powered by Large Language Models (LLMs), have shown promise in simulating human behaviors without relying on extensive datasets. Nevertheless, these methods often struggle with generating consistent, context-sensitive, and realistic behavioral outputs. To address these limitations, this paper introduces the Preference Chain, a novel method that integrates Graph Retrieval-Augmented Generation (RAG) with LLMs to enhance context-aware simulation of human behavior in transportation systems. Experiments conducted on the Replica dataset demonstrate that the Preference Chain outperforms standard LLM in aligning with real-world transportation mode choices. The development of the Mobility Agent highlights potential applications of proposed method in urban mobility modeling for emerging cities, personalized travel behavior analysis, and dynamic traffic forecasting. Despite limitations such as slow inference and the risk of hallucination, the method offers a promising framework for simulating complex human behavior in data-scarce environments, where traditional data-driven models struggle due to limited data availability.

This paper introduces MeLA, a Metacognitive LLM-Driven Architecture that presents a new paradigm for Automatic Heuristic Design (AHD). Traditional evolutionary methods operate directly on heuristic code; in contrast, MeLA evolves the instructional prompts used to guide a Large Language Model (LLM) in generating these heuristics. This process of "prompt evolution" is driven by a novel metacognitive framework where the system analyzes performance feedback to systematically refine its generative strategy. MeLA's architecture integrates a problem analyzer to construct an initial strategic prompt, an error diagnosis system to repair faulty code, and a metacognitive search engine that iteratively optimizes the prompt based on heuristic effectiveness. In comprehensive experiments across both benchmark and real-world problems, MeLA consistently generates more effective and robust heuristics, significantly outperforming state-of-the-art methods. Ultimately, this research demonstrates the profound potential of using cognitive science as a blueprint for AI architecture, revealing that by enabling an LLM to metacogni-tively regulate its problem-solving process, we unlock a more robust and interpretable path to AHD.

This paper introduces the Comprehensive Applicant Profile Score (CAPS), a novel multi-modal framework designed to quantitatively model and interpret holistic college admissions evaluations. CAPS decomposes applicant profiles into three interpretable components: academic performance (Standardized Academic Score, SAS), essay quality (Essay Quality Index, EQI), and extracurricular engagement (Extracurricular Impact Score, EIS). Leveraging transformer-based semantic embeddings, LLM scoring, and XGBoost regression, CAPS provides transparent and explainable evaluations aligned with human judgment. Experiments on a synthetic but realistic dataset demonstrate strong performance, achieving an EQI prediction R^2 of 0.80, classification accuracy over 75%, a macro F1 score of 0.69, and a weighted F1 score of 0.74. CAPS addresses key limitations in traditional holistic review -- particularly the opacity, inconsistency, and anxiety faced by applicants -- thus paving the way for more equitable and data-informed admissions practices.

This study investigates the potential for Large Language Models (LLMs) to scale-up Dynamic Assessment (DA). To facilitate such an investigation, we first developed DynaWrite-a modular, microservices-based grammatical tutoring application which supports multiple LLMs to generate dynamic feedback to learners of English. Initial testing of 21 LLMs, revealed GPT-4o and neural chat to have the most potential to scale-up DA in the language learning classroom. Further testing of these two candidates found both models performed similarly in their ability to accurately identify grammatical errors in user sentences. However, GPT-4o consistently outperformed neural chat in the quality of its DA by generating clear, consistent, and progressively explicit hints. Real-time responsiveness and system stability were also confirmed through detailed performance testing, with GPT-4o exhibiting sufficient speed and stability. This study shows that LLMs can be used to scale-up dynamic assessment and thus enable dynamic assessment to be delivered to larger groups than possible in traditional teacher-learner settings.

Recent math benchmarks for large language models (LLMs) such as MathArena indicate that state-of-the-art reasoning models achieve impressive performance on mathematical competitions like AIME, with the leading model, Gemini-2.5-Pro, achieving scores comparable to top human competitors. However, these benchmarks evaluate models solely based on final numerical answers, neglecting rigorous reasoning and proof generation which are essential for real-world mathematical tasks. To address this, we introduce a comprehensive evaluation of full-solution reasoning for challenging mathematical problems. Using expert human annotators, we evaluated several state-of-the-art reasoning models on the six problems from the 2025 USAMO within hours of their release. Our results reveal that all tested models struggled significantly: only Gemini-2.5-Pro achieves a non-trivial score of 25%, while all other models achieve less than 5%. Through detailed analysis of reasoning traces, we identify the most common failure modes and find several unwanted artifacts arising from the optimization strategies employed during model training. Overall, our results suggest that current LLMs are inadequate for rigorous mathematical reasoning tasks, highlighting the need for substantial improvements in reasoning and proof generation capabilities.

Abstract--Directed evolution is an iterative laboratory process of designing proteins with improved function by iteratively synthesizing new protein variants and evaluating their desired property with expensive and time-consuming biochemical screening. Machine learning methods can help select informative or promising variants for screening to increase their quality and reduce the amount of necessary screening. In this paper, we present a novel method for machine-learning-assisted directed evolution of proteins which combines Bayesian optimization with informative representation of protein variants extracted from a pre-trained protein language model. We demonstrate that the new representation based on the sequence embeddings significantly improves the performance of Bayesian optimization yielding better results with the same number of conducted screening in total. At the same time, our method outperforms the state-of-the-art machine-learning-assisted directed evolution methods with regression objective. Protein engineering (PE) is the process of designing proteins with desired properties, such as improved stability, catalytic function, or specific binding affinity [1]. PE can be leveraged in industrial applications, environmental applications, medicine, nanobiotechnology, and other fields [1]. Because the functional properties of proteins are determined by their sequence of amino acids [2], the task of PE translates to finding a sequence of amino acids with the desired properties/function.