arXiv:2603.12180v2 Announce Type: replace-cross Abstract: Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test […]
Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
arXiv:2603.19782v1 Announce Type: new Abstract: Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational approaches are misaligned with this reality, framing discovery as isolated, task-specific predictions rather than continuous interaction with the physical world. Here, we argue for […]
Mathematical Modeling of Cancer-Bacterial Therapy: Analysis and Numerical Simulation via Physics-Informed Neural Networks
arXiv:2603.19326v1 Announce Type: new Abstract: Bacterial cancer therapy exploits anaerobic bacteria’s ability to target hypoxia tumor regions, yet the interactions among tumor growth, bacterial colonization, oxygen levels, immunosuppressive cytokines, and bacterial communication remain poorly quantified. We present a mathematical model of five coupled nonlinear reaction-diffusion equations in a two-dimensional tissue domain. We proved the global […]
ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
arXiv:2603.19676v1 Announce Type: cross Abstract: Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To address this limitation, we introduce ATHENA, a model-agnostic, test-time adaptive steering framework that improves object count fidelity without modifying model architectures or requiring retraining. ATHENA leverages intermediate representations […]
Modelling the passive and active response of skeletal muscles within the adapted Voigt representation framework
arXiv:2603.19723v1 Announce Type: cross Abstract: We present a constitutive model for the passive and active response of skeletal muscles. At variance with more classical approaches, the model is developed exploiting adapted Voigt representations of strain and stress tensors within the context of nonlinear Cauchy elasticity. This framework allows us to identify non-trivial stress-strain relations in […]
Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
arXiv:2603.19852v1 Announce Type: cross Abstract: Deep learning-based online mapping has emerged as a cornerstone of autonomous driving, yet these models frequently fail to generalize beyond familiar environments. We propose a framework to identify and measure the underlying failure modes by disentangling two effects: Memorization of input features and overfitting to known map geometries. We propose […]
Multimodal branched transport infers anatomically aligned brain reaction maps
arXiv:2603.19761v1 Announce Type: cross Abstract: How external stimulation is transformed into distributed reaction patterns remains unresolved at the level of propagation architecture. Existing large-scale control models quantify transition costs on prescribed networks but do not infer the routing map itself from source and target activity. Here we combine task-related blood-oxygen-level-dependent responses, source-reconstructed electrophysiology and tractography-derived […]
Problem difficulty and waiting time shape the level of detail and temporal organization of visual strategies in human planning
arXiv:2603.19881v1 Announce Type: new Abstract: Planning entails identifying sequences of actions to reach a goal, yet we still have incomplete knowledge of how problem constraints, such as difficulty and available time, influence the visual strategies supporting plan construction, both in terms of coverage of the to-be-executed plans and its temporal organization. To fill this gap, […]
Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs
arXiv:2603.19970v1 Announce Type: cross Abstract: Although recent generative models can produce time series with close marginal distributions, they often face a fundamental tension between preserving global temporal structure and modeling stochastic local variations, particularly for highly volatile signals with weak or irregular periodicity. Direct distribution matching in such settings can amplify noise or suppress meaningful […]
Ternary Gamma Semirings: From Neural Implementation to Categorical Foundations
arXiv:2603.19317v1 Announce Type: cross Abstract: This paper establishes a theoretical framework connecting neural network learning with abstract algebraic structures. We first present a minimal counterexample demonstrating that standard neural networks completely fail on compositional generalization tasks (0% accuracy). By introducing a logical constraint — the Ternary Gamma Semiring — the same architecture learns a perfectly […]
Utility-Guided Agent Orchestration for Efficient LLM Tool Use
arXiv:2603.19896v1 Announce Type: new Abstract: Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. […]
A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints
arXiv:2603.19322v1 Announce Type: cross Abstract: While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient issue in backpropagation, the difficulty of enforcing intricate constraints with discrete variables, and the inability in generating solutions with non-same-parameter-same-decision […]