Computer Science & Mathematics

Computer-using agents are increasingly capable of performing complex tasks in the digital world. However, high-quality interaction trajectories remain scarce for specialized desktop applications, where limited application knowledge, cumbersome GUI workflows, and incomplete exploration hinder automated collection. We introduce OS-Wizard, an automated trajectory collection framework. It combines tutorial-guided exploration with a hybrid GUI--Code action space, providing application-specific knowledge and simplifying GUI workflows through direct execution of application-native commands. The framework also checkpoints and revisits pivotal states during tree exploration to explore alternative workflows, complementing linear rollouts for broader coverage. We collect 10.9K trajectories comprising 54.9K state--action samples. Fine-tuning open-source base models on this corpus yields a best-performing model that improves performance on a benchmark of specialized desktop workflows by 58.2 percentage points to 64.1\%, surpassing reported human performance of 59.8\% and establishing a new state of the art. The fine-tuned model also improves performance on general desktop workflows using GUI actions only, suggesting that the collected supervision benefits general desktop tasks as well. Comparative experiments and ablations demonstrate the efficiency of trajectory collection and the importance of code actions.

Out-of-distribution (OOD) detection identifies inputs outside the training distribution. Rank-based analyses such as RankFeat and RankWeight suggest that OOD overconfidence is closely related to dominant low-rank components in feature and weight spaces. Since weight averaging operates directly in parameter space and improves model generalization, we consider it for OOD detection from a dominant-component perspective. Trainable Weight Averaging (TWA) assigns a single coefficient to each checkpoint, limiting independent control of dominant weight components. We extend TWA with leading rank-one weight components extracted by Singular Value Decomposition as correction directions, whose contributions are learned through the in-distribution classification objective. On ResNet50, our method improves over fine-tuning and standard TWA across the evaluated datasets with MSP and RankWeight, both with and without Outlier Exposure. Mahalanobis-based evaluation yields mixed results, indicating that the benefit depends on the OOD scoring protocol. Target-layer analyses with MSP and Energy favor correction near the classifier.

A common strategy for data augmentation is to apply style transfer on training images to enrich appearance variations. Recent approaches have combined style augmentation with random erasing by selectively replacing image subregions with style-transferred patches. However, existing methods rely on uniformly random region selection or fixed geometric constraints, which may fail to cover informative texture patterns and limit augmentation diversity. To address these limitations, we propose a texture-aware subregion style augmentation framework that prioritizes regions with strong texture responses for style replacement. Furthermore, we extend this framework with a hybrid region strategy that combines a texture-driven region with an auxiliary random region, implicitly enabling more diverse style perturbations. Experiments demonstrate that our approach achieves higher classification accuracy and improves robustness compared with existing style-based augmentation methods.

Agentic driving brings goal-directed reasoning, memory, tools, and adaptive interaction into automated vehicles. A vehicle can clarify a request, explain a maneuver, or prepare a driver to take control, then adapt its next action to the response. These capabilities make the vehicle an active participant in shaping the human behavior it observes. We examine how agentic interaction affects driver-state inference, trust and reliance, and human intervention in conditional automation. Established findings on attention, takeover prediction, trust-aware planning, and adaptive warnings provide useful foundations, but their applicability depends on how observations are elicited and how assistance changes the driving task. We distinguish what remains applicable, what changes under flexible interaction, and what remains unresolved across these three areas. The analysis identifies three research priorities: establishing the effects of interventions, jointly designing interaction and driving policies, and maintaining useful adaptation across repeated use and system changes. Progress should be measured through driver comprehension, appropriate reliance, and the ability to perform the required driving action in time.

Predicting the short-term future trajectory of a person from RGB-D cameras is a key capability for mobile robots navigating in dynamic and human populated environment. The key challenge to deploying learned predictors on real robots is the train-deploy pipeline gap. Training data are often prepared with an idealized, smoothed ground truth, whereas at inference, the model is fed noisy estimates from pose detectors and depth sensors. The model is therefore evaluated on an input distribution it never encountered during training. Most existing models rely on recurrent neural networks (RNNs) or transformers, which either struggle to capture short-term temporal dependencies or suffer from computational cost. We present TrajMamba, a lightweight, bidirectional state space model for short-term human trajectory prediction using an RGB-D camera. The model uses a single shared processing path for both training and deployment, aligning human pose extraction, depth back projection, and smoothing processes. It encodes a short window of persons's hip center velocities with stacked bidirectional Mamba blocks and decodes future velocities with a GRU head. On the ETH/UCY benchmark, TrajMamba reaches an average ADE of 0.29 m FDE of 0.51 m. With 262K parameters, it runs in real time on modest hardware and is deployed on a TIAGo robot with an onboard NVIDIA Jetson Orin.

We study a simple random deletion algorithm to find short circuits in regular matroids. Given a regular matroid $M$ with $m$ elements, the algorithm randomly deletes each element independently with probability $1-1/m^{Θ(1/g)}$ where $g$ is the size of a minimum circuit, and returns the remaining set $R$ of elements. We establish the following results: 1. With high probability, $R$ contains no circuit and is therefore independent. 2. For every $α$-approximate minimum circuit $C$ where $α\geq 1$, with probability at least $m^{-O(α)}$, the entire circuit $C$ survives in $R$ and moreover, the minimum number of elements that need to be removed to make $R$ independent is $O(α\log(α+2))$. This yields an algorithmic proof that the number of $α$-approximate minimum circuits is $m^{O(α)}$, improving the previous known bound of $m^{O(α^2)}$ by Gurjar and Vishnoi, and resolving a recent conjecture of Khanna, Putterman, and Song. Our results yield two immediate applications. First, we obtain very simple RNC algorithms for computing the shortest circuit, and for enumerating all $α$-approximate circuits, of a regular matroid without computing the Seymour decomposition. Second, we obtain a randomized parallel algorithm to find a basis of a regular matroid under independence-oracle access. It uses polynomially many independence-oracle queries in $O(\log m)$ adaptive rounds and succeeds with high probability. This follows from the framework of Khanna, Putterman, and Song and the improved counting bound, and extends their result from graphic matroids to regular matroids.

Change is inevitable in software systems, where requirements must continuously adapt to evolving stakeholder needs, regulations, and project scopes. Managing such changes is a fundamental software engineering challenge, as manually identifying the impact of a change request, given high requirements volume, Natural Language (NL) complexity, and intricate interdependencies, is error-prone and time-consuming. Large Language Models (LLMs) offer promising solutions for requirements change impact analysis (CIA), yet their effectiveness when enhanced with advanced techniques remains underexplored. We present DRILS, an LLM-based agentic framework for requirements Change Impact Analysis, employing a multi-agent architecture to generate candidate impact sets, with an LLM-as-a-judge promoting diversity during selection. DRILS features two key components: RE-RAG, a carefully engineered RAG technique providing focused domain context, and a requirement dependency graph (RDG) as an additional knowledge source. Evaluation across three manually curated datasets demonstrates superior performance over state-of-the-art baselines, achieving an average recall of 87.1%, precision of 76.3%, and F1 score of 81% at a lower cost. Precision gains are particularly significant, 41.1%, 83.4%, and 149.8% over the closest baseline per dataset, as higher precision directly reduces false positives and manual validation effort. We also contribute three annotated CIA datasets to support future research.

This paper introduces a novel simulation-free framework for learning unbalanced population dynamics on the Riemannian Wasserstein-Fisher-Rao (WFR) manifold, termed Variational Doob-Wasserstein Flow (VDWF), built upon the theory of the unbalanced mean-field Schrödinger bridge (MFSB). First, by independently learning a geometry model equipped with a data-dependent metric, our model captures the intrinsic geometric structure of population dynamics. Furthermore, leveraging Doob's h-transform, the proposed method incorporates boundary information to improve flow-based trajectory inference. For unbalanced transport, a growth model is employed to learn the dynamics while constructing intermediate mass samples in the WFR space without simulation. Additionally, we analyze the convergence rate of the proposed framework using a uniform Log-Sobolev inequality (LSI). Finally, we validate the proposed approach on multiple real-world datasets, demonstrating competitive performance in learning both balanced and unbalanced population dynamics compared with state-of-the-art methods.

Modeling inference workloads for transformer-based neural networks poses unique challenges due to their dynamic memory footprints, head-of-line blocking caused by heavy-tailed request distributions, and memory-dependent preemption overhead arising from the need to load/unload cache state. In this paper, we introduce a new queuing model that captures the impacts of these features on system stability and scheduling design. We show that the Gittins-index policy, which minimizes mean response time in the standard M/G/1 setting, can incur substantial preemption overhead in our model. Motivated by this limitation, we propose the Multi-Level-Priority-Threshold (MLPT) policy, that limits preemption while preserving priority for short jobs. We characterize the mean response time under MLPT and provide empirical rules-of-thumb to solve the resulting threshold-optimization problem. Our key observation is that optimal scheduling is a balance between reducing the response times of shorter jobs and limiting the overhead incurred when preemption occurs. These results provide a theoretical framework for understanding scheduling in memory constrained queuing systems for inference tasks.

Mapping CVEs to MITRE ATT&CK techniques helps defenders translate vulnerability information into hypotheses about adversary behavior. Automating this mapping is challenging because relevant evidence is fragmented across heterogeneous security sources. In addition, ATT&CK techniques can be semantically similar, and existing annotations cover a highly long-tailed subset of the technique space. Existing supervised, retrieval-based, and LLM-based approaches therefore face limitations from closed-set supervision, semantic ambiguity, or unconstrained prediction. We formulate CVE-to-ATT&CK mapping as multi-evidence constrained ranking. Our framework TRACE first integrates complementary structural and semantic evidence from multiple sources to construct a bounded, high-coverage candidate pool over the complete ATT&CK technique space. It then reranks the retained candidates by combining their accumulated evidence with CVE--technique textual interactions and frequency-aware scoring. We evaluate the framework across six public datasets with different annotation processes and vulnerability distributions. Candidate construction reduces the 201-technique ATT&CK search space by approximately 60% while retaining at least one ground-truth technique for 95.11%-100% of CVEs. These results show that combining heterogeneous security evidence with constrained ranking provides a more controlled and generalizable bridge from vulnerability information to adversary behavior.

Reduced-order models simplify fluid simulation by representing complex flows with a small number of spatial modes. Building on Laplacian Eigenfluids, we introduce Neural Eigenfluid Bases (NEB), a neural representation whose basis functions can be evaluated anywhere in space. We enforce incompressibility and impermeable boundaries directly through differential lifts and potential boundary conditions. Geometry-local orthogonalization and Rayleigh minimization then learn an ordered basis. We connect learning in potential and velocity spaces, and derive a spectral-variance relation explaining why these objectives weight approximate modes differently, even though their exact positive spectra agree. Gauge fixing reduces the number of spatial derivatives needed for potential learning, while a Dirichlet energy loss learns independent circulation fields around obstacles. With 1024 modes, both objectives keep velocity errors below 1% in periodic vortex merger. For random flows around obstacles, potential-based learning captures more initial energy and gives lower final errors than numerical Laplacian bases of the same size. The reduced state is about a thousand times smaller than the full reference model. Three-dimensional tests separate spatial reconstruction errors from errors in coefficient evolution. Precomputed Galerkin operators allow millisecond-scale updates when the same basis is reused across simulations. This provides a physically constrained basis for continuous flow reconstruction and efficient reduced-order simulation.

The brain continually learns tasks with very different computational demands. Recurrent neural networks (RNNs) have been used as dynamical surrogates for studying task solutions, with recent work extending this approach to joint training on multitask batteries. However, it remains unclear how tasks interact as these batteries grow in scale and heterogeneity: under what conditions do they transfer or interfere with one another, and how do these effects relate to task complexity and model structure? We study this question by simultaneously training hierarchical Almost-Linear RNNs (AL-RNNs) on 100 tasks spanning a wide range of cognitive demands. AL-RNNs allow us to vary the amount of nonlinearity in the recurrence, while hierarchical task features provide a low-dimensional interface for task-specific adaptation within shared dynamics. On this task battery, performance improves with both nonlinear capacity and task-feature dimensionality, with the joint hierarchical model outperforming both individually trained models and a single unstructured joint model. Many tasks are individually solvable with linear dynamics, yet cannot be solved together by a shared linear model. Through hierarchical task features, task-specific linear region usage, and task geometry, the trained model provides several related but distinct measures of task similarity that capture how computations are separated and combined within the shared backbone. Across a series of experiments, we relate these representations to individual task complexity, joint solvability, pairwise transfer learning, and leave-one-out adaptation. Together, our experiments characterize task interactions in multitask recurrent learning while demonstrating both the potential and the challenges of reusable dynamical backbones for cognitive computation.

Large language models have made remarkable strides in website development, enabling complete and interactive web experiences to be built from natural-language instructions with far less effort. Yet, non-expert users often struggle to articulate sophisticated visual and interaction designs in natural language. Meanwhile, the open web already contains a vast reservoir of such design knowledge, embodied in mature website implementations. To this end, we introduce Website-derived Visual Skill Extraction (WebViSE), a framework that automatically abstracts these implementations into reusable Visual Skills and builds a structured Skill library. To scale the library, WebViSE organizes its Skills in a multi-parent DAG and jointly evolves Skill descriptions and DAG structure using Skill-conditioned Potential Queries, enabling efficient matching between diverse user instructions and relevant Skills. The auto-evolved structure outperforms non-hierarchical LLM retrieval baselines at only 39.09% of the estimated retrieval cost with Qwen3.8-Max. For any models, WebViSE can be directly injected as plug-and-play guidance, enabling diverse models to produce more visually compelling and aesthetically refined web pages. For open-source models, WebViSE can be used to build a data-synthesis pipeline that internalizes visual design intelligence into model weights. Experiments across multiple web development benchmarks and human evaluation consistently show that WebViSE improves the visual quality and interaction fidelity of artifacts. Overall, our work establishes an automated path for extracting, organizing, and transferring design intelligence from the open web to website-building models. We release all extracted Visual Skills, the associated Skill DAG, and our code at https://github.com/YifeiSun-0710/WebViSE.

Learning-based approaches to combinatorial optimization often predict solutions directly or use predictions to restrict search, while expressive energy-based models typically rely on approximate inference. We introduce EnerGNN, a framework that learns energy functions over complete binary configurations and minimizes them under explicit hard constraints through mixed integer programming (MIP). EnerGNN combines a graph neural network encoder with an optimization-compatible readout and a nonlinear energy head, enabling exact constrained inference over the learned energy. An optimality-aware contrastive loss trains the energy to reflect solution quality and constraint violations. Across Quadratic Knapsack, Combinatorial Auctions, and a personalized cell therapy supply chain problem, EnerGNN achieves near-optimal solutions with 100% feasibility. On the supply chain problem, it achieves a 0.05% mean primal gap and a 17.4$\times$ speedup over the monolithic MIP. The learned energy also generalizes to larger instances and supports zero-shot constraint injection, adapting to changing constraints without retraining while preserving feasibility.

"Why is my period late?" Sometimes, the most useful response begins with another question. Yet conversational AI systems may respond to incomplete health queries without seeking essential context or grounding their guidance in verifiable evidence. This paper introduces HerHealthGPT, an evidence-grounded conversational AI system designed to address these challenges in women's reproductive health. HerHealthGPT integrates retrieval-augmented generation (RAG), context-aware clarification, and source validation within an interactive web interface. Rather than responding immediately to incomplete queries, the system maintains conversational context, asks targeted follow-up questions, checks for premature conclusions, and grounds its responses in retrieved evidence. We evaluate the AI components using 540 English messages derived from 90 reproductive-health cases and conduct a prototype questionnaire study with 30 adults. Evidence retrieval improves concern-category accuracy from 54.1% to 59.3% compared with fine-tuning alone. The clarification router achieves 85.6% recall and 86.2% specificity on constructed targets. In the user study, 83.3% of participants preferred the retrieval-enabled configuration, while 25 of 30 considered its follow-up questions relevant. These findings suggest that integrating evidence retrieval with interactive clarification offers a promising approach to more transparent, context-aware reproductive-health information systems, while further clinical validation remains necessary.