arXiv subjects

Search papers

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

At least 1,081 records · Page 60Linked to original sources

arXiv2026

Plan Before You Trade: Inference-Time Optimization for RL Trading Agents

Reinforcement learning agents for portfolio management are typically trained and deployed as static policies, with no mechanism for policy adjustments using price forecasts at inference time. We propose FinPILOT (Financial Plugin Inference-time Learning for Optimal Trading), a plugin inference-time policy optimization framework inspired by Model Predictive Control (MPC). Under the price-taker assumption, portfolio actions do not affect future market prices, allowing a multi-step price forecaster to provide imagined market trajectories without iterative action-conditioned rollouts. At each decision step, FinPILOT uses the forecaster's predicted price trajectory to construct an allocation-based imagined return objective and optimizes the pretrained policy at inference time before executing one step of the trade. Our framework is compatible with any pretrained policy and adapts the policy using the forecaster's predictions without modifying the original RL training pipeline. Evaluated with five pretrained policies (PPO, SAC, A2C, TD3, DDPG) across DJ30 equities and foreign exchange (FX) over three rolling held-out test years (30 settings in total), FinPILOT improves Total Return in 28 of 30 settings and Sharpe ratio in 27 of 30, with gains spanning both stochastic and deterministic policies. Direct single- and multi-period portfolio optimizers supplied with the same forecasts do not reproduce these aggregate gains under our evaluation protocol. Further, using controlled forecasts at calibrated quality levels, we show that both the magnitude and consistency of FinPILOT's performance increase as forecast error is reduced.

cs.LG↗

arXiv2026

Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse

Neuroscience data are fragmented across labs, experimental paradigms, and storage formats, and data reuse often requires substantial manual effort. Standardized formats have been proposed in response, but a fundamental tension persists: formats flexible enough for diverse experiments are rarely self-explanatory, while fully descriptive datasets demand documentation and curation effort that few labs can sustain. Coding agents, which can read code and text quickly with apparent attention to details humans tend to skim, are a natural candidate to reduce this burden. To measure how well coding agents perform data reuse, we benchmark them on eight recent papers with large-scale mouse neural recordings spanning diverse recording modalities, behavioral paradigms, and formats. Given the data, code, and paper, the agents must reformat the data for a common downstream task: training a decoder from neural activity to task and behavioral variables. Evaluating the resulting solutions, however, is challenging, since many conversion decisions are under-specified and several choices are defensible. Yet a subtle but scientifically significant error can invalidate the dataset in ways aggregate metrics can miss. We therefore pair outcome-based metrics with a process-based rubric, scored by two human evaluators against manual reference solutions. We find that agents succeed on most subtasks but rarely produce a fully error-free end-to-end solution; we characterize their mistakes and suggest data-sharing practices for agent-assisted reuse. Finally, we find that agent judges are unreliable at catching errors on their own, but can automate process-based evaluation when given reference solutions.

cs.LG↗

arXiv2026

Language-Based Agent Control

This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional programming, combinations of static typing and runtime enforcement have long been used to guarantee that well-typed programs satisfy user-specified policies, including policies for access control, information flow, data provenance, and more. The key idea behind LBAC is to extend these guarantees to agentic applications by requiring agents to generate programs that are themselves well typed in the context of the surrounding scaffolding code. Unsafe programs are rejected by the type-checker before execution, allowing policies to apply uniformly across the entire application, including both agent-generated behavior and developer-written scaffolding. At the same time, LBAC preserves substantial expressiveness: agents may perform arbitrary side-effect-free computation and recursively invoke subagents, which retain full tool access subject to the same -- or potentially more restrictive -- policies. We demonstrate LBAC with three case studies: I/O sandboxing via filesystem capabilities, data provenance, and information-flow control.

cs.PL↗

arXiv2026

SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation

Modern image super-resolution methods generate detailed, visually appealing results, but they often introduce visual artifacts: unnatural patterns and texture distortions that degrade perceived quality. These defects vary widely in perceptual impact--some are barely noticeable, while others are highly disturbing--yet existing detection methods treat them equally. We propose artifact prominence as an evaluative target, defined as the fraction of viewers who judge a highlighted region to contain a noticeable artifact. We design a crowdsourced annotation protocol and construct SR-Prominence, a dataset suite containing 3,935 artifact masks from DeSRA, Open Images, Urban100, and a realistic no-ground-truth Urban100-HR setting, annotated with prominence. Re-annotating DeSRA reveals that 48.2% of its in-lab binary artifacts are not noticed by a majority of viewers. Across the suite, we audit SR artifact detectors, image-quality metrics, and SR methods. We find that classical full-reference metrics, especially SSIM and DISTS, provide surprisingly strong localized prominence signals, whereas no-reference IQA methods and specialized artifact detectors often fail to generalize across datasets and reference settings. SR-Prominence is released with an objective scoring protocol that allows new metrics to be benchmarked on our suite without further crowdsourcing. Together, the data and protocols enable SR artifact evaluation to move from binary defect presence toward perceptual impact. SR-Prominence is available at https://huggingface.co/datasets/imolodetskikh/sr-artifact-prominence.

cs.CV↗

arXiv2026

BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks

Large language model (LLM) agents increasingly automate machine-learning model building, yet biomedical benchmarks emphasize question answering, reasoning, and tool use or cover narrow slices of biomedical ML coding. We introduce BioXArena, a biomedical machine learning (BioML) coding benchmark for task-specific model building on heterogeneous, often multi-modal datasets. It contains 76 end-to-end tasks across 9 domains: sequence, single-cell, structure, network biology, chemical biology, perturbation dynamics, phenotype--disease, imaging, and text-integrated tasks. Each task packages primary-source data with hidden labels, held-out graders, and biology-aware metrics on a unified 0-to-100 scale; agents write runnable code, train models, and predict private test samples. BioXArena emphasizes realistic data interfaces: most tasks require agents to integrate multiple input sources, including 46 tasks that combine distinct modality families. We compare 18 harness--backbone configurations: general-purpose coding, biomedical, and ML agents plus our Minimal runner, all under the same controlled resource configuration. Codex with GPT-6 Astra achieves the highest task-level average score of 73.91 among 18 configurations, closely followed by Claude Code with Opus 5.5 (73.79). Matched-backbone comparisons show higher observed scores for mature coding systems than for Minimal; seven Minimal backends characterize model differences under a fixed runner. Beyond the main leaderboard, ablations, robustness checks, and scaling, runtime, and failure-mode analyses characterize how backbones, scaffolds, budgets, and domains affect BioML coding performance, exposing modeling and execution gaps across agent and LLM backbone families.

cs.CE↗

arXiv2026

Loop Quantum Kaluza-Klein Cosmology and Inflation

We present the detailed analyses of five-dimensional loop quantum Kaluza-Klein cosmology based on the symmetric reduction of the connection formulation of the full theory. The previous results in a particular scenario are extended to more general cases. The effective scalar constraint for the geometric sector of the model is derived by the systematic semi-classical analysis in both the canonical and path-integral formulations, incorporating the quantum fluctuations as a subleading-order correction. The resulting effective scalar constraint not only exhibits the correct classical limit of the quantum system, but also serves as the basis for investigating the following three distinct effective scenarios through the incorporation of matter contributions: (i) vacuum, (ii) minimally coupling with a scalar field, and (iii) coupling with the dust. In all the three effective scenarios, the big bang and potential past big rip singularities in the classical model are naturally resolved by including the leading-order quantum correction of holonomies. Moreover, the visible universe undergoes a super-inflationary phase after overcoming the classical big bang singularity, during which the phenomenologically desired 55 e-folds can be achieved by appropriate initial conditions. In the case where the subleading-order quantum fluctuation term is included as a constant, the evolutions of the five-dimensional universe in all the three effective scenarios not only achieve sufficient inflation in the visible dimensions, but also exhibit re-collapse behaviors at certain large scales. Hence the cosmic inflation may originate from the interplay between compact extra dimensions and quantum geometric effects.

gr-qc↗

arXiv2026

Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment

EEG-based visual decoding aims to establish a mapping between neural signals and visual semantics. However, it remains constrained by the dual challenges of severe information granularity mismatch and the low signal-to-noise ratio (SNR) of EEG signals. Existing approaches typically treat visual features as static, ignoring the dynamic selectivity of human vision and the frequency specificity of neural oscillations. To bridge this gap, we propose CAIA, a Cognitive-guided Adaptive blurring with Information-Constrained Alignment framework for Neural-Visual decoding. On the visual side, it simulates selective attention to adaptively reduce redundancy. Meanwhile, on the EEG side, it combines neural oscillation priors with an information-bottleneck-inspired spectral sparsity regularizer to enhance SNR. Specifically, we devise a cognitive-dynamics-based adaptive blurring mechanism that dynamically integrates center-biased and saliency-guided visual cues via cross-modal attention. Furthermore, we introduce a distribution-aware boundary calibration loss to robustly rectify alignment bias caused by outlier samples. Moreover, a cognitively guided information-screening method is proposed to select task-relevant EEG oscillations. Extensive experiments demonstrate that CAIA improves both subject-dependent and subject-independent average Top-1 and Top-5 accuracy in zero-shot brain-to-image retrieval, significantly outperforming prior methods. Our work validates that optimizing visual information density to match neural granularity offers a more interpretable and robust pathway for neural decoding.

cs.CV↗

arXiv2026

Stochastic Optimization and Data Science

This paper aims to motivate stochastic optimization problems from a statistical perspective and a statistical learning perspective, where the goal is to maximize the log-likelihood or minimize the population risk. We briefly describe the two main approaches: offline (Monte Carlo / Sample Average Approximation) and online (Stochastic Approximation) approaches -- to solve the expectation minimization problems.

math.OC↗

arXiv2026

Brain Vascular Age Prediction Using Cerebral Blood Flow Velocity and Machine Learning Algorithms

Defining vascular age in terms of physiological function has become one focal point of the extensive studies to categorize and track chronological age. Transcranial Doppler (TCD) is a method by which cerebral blood flow velocity is measured along the major arteries feeding the human brain. This study aims to use features extracted from TCD to estimate chronological age and assess accelerated aging in subjects with various brain diseases. We predict subjects with various brain diseases to present with accelerated cerebrovascular aging when tested on various regression models trained by healthy subjects. 168 healthy subjects and 277 diseased subjects with bilateral TCD recordings of the middle cerebral artery were analyzed using the Morphological Analysis and Clustering of Intracranial Pressure (MOCAIP) algorithm. MOCAIP-generated features and heart rate variability features were used as input features for regression models to predict the brain vascular age. 66 subjects with acute stroke, 27 subjects with post stroke, 26 subjects with Alzheimer's disease, 23 subjects with mild cognitive impairment, and 135 established subjects were tested against the machine learning model to assess for accelerated cerebrovascular age. The trained model, on average, predicted healthy subjects' cerebrovascular age to be 3.69 years above their chronological age. Subjects with different disease conditions exhibited varying levels of age acceleration. The differences in healthy and diseased subjects' performances suggest that features generated using TCD may be relevant when evaluating accelerated cerebrovascular aging. Moreover, imbalanced datasets have been observed to affect the performance of machine-learning-based brain age prediction models.

cs.AI↗

arXiv2026

EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models

While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, their fundamental vision-language grounding (VLG) capability in embodied scenarios remains unexplored. We present \textbf{EPIC-Bench}, \textbf{E}mbodied \textbf{P}ercept\textbf{I}on Ben\textbf{C}hmark, a fine-grained grounding benchmark designed to systematically evaluate the VLG capabilities of VLMs in real-world embodied environments. EPIC-Bench comprises 6.6k meticulously human-annotated tuples (Image, Text, Mask) spanning three core stages of the embodied interaction pipeline: Target Localization, Navigation, and Manipulation. With 23 fine-grained tasks, multi-dimensional settings and evaluation over 80 leading VLMs, EPIC-Bench provides a diagnostic analysis.

cs.CV↗

arXiv2026

A unification of graded and substructural logics

Type systems which account for resource sensitive computations can generally be split into two styles: First, substructural logics such as Linear Logic which seek to restrict weakening and contraction and reintroduce them in a controlled manner; And second, graded systems which allow weakening and contraction by default, but track the use of variables quantitatively in some algebraic structure -- usually a semiring. We present GRASS (Graded and substructural), a type system which incorporates mechanisms from both of these approaches, thus allowing maximally flexible control over variable usage. Furthermore, GRASS allows grades from an arbitrary collection of grade algebras to coexist in the same system, thus allowing different variables to be controlled with respect to different notions of resource within the same program. We develop the categorical semantics of GRASS, and find that, on the level of categorical semantics, it subsumes multiple established systems such as LNL, Adjoint Logic, and mGL.

cs.LO↗

arXiv2026

Limits of Hyperkähler Manifolds and Moduli Spaces of Sheaves on K3 Surfaces

We prove that a compact strongly Gauduchon manifold which is a limit of compact hyperkähler manifolds is bimeromorphic to a compact hyperkähler manifold. This settles a case of a conjecture of Soldatenkov and Verbitsky. A closed completion of a Gauduchon metric bounds the Dirichlet energies of nearby biholomorphisms. This bound yields a meromorphic limit map, which has degree one and is therefore a bimeromorphism onto a compact hyperkähler manifold. We apply this result to moduli spaces of stable torsion-free coherent sheaves on K3 surfaces. A Bott--Chern diagonal formula gives the $\partial\bar\partial$-lemma, and positivity of determinant classes gives Kählerness, proving Perego's conjecture.

math.AG↗

arXiv2026

Generative Recursive Reasoning

How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared transition functions. Yet existing RRMs are largely deterministic, following a single latent trajectory and converging to a single prediction. We introduce Generative Recursive reAsoning Models (GRAM), a framework that turns recursive latent reasoning into probabilistic multi-trajectory computation. GRAM models reasoning as a stochastic latent trajectory, enabling multiple hypotheses, alternative solution strategies, and inference-time scaling through both recursive depth and parallel trajectory sampling. This yields a latent-variable generative model supporting conditional reasoning via $p_θ(y \mid x)$ and, with fixed or absent inputs, unconditional generation via $p_θ(x)$. Trained with amortized variational inference, GRAM improves over deterministic recurrent and recursive baselines on structured reasoning and multi-solution constraint satisfaction tasks, while demonstrating an unconditional generation capability. https://ahn-ml.github.io/gram-website

cs.AI↗

arXiv2026

Partially reactive force field for the UiO-66 metal-organic framework

UiO-66 is the most widely studied metal-organic framework, on account of its structural tunability given by its capacity of sustaining high amounts of point defects in its structure. Its synthesis mechanism is largely unknown, with only a few works mostly focused on the formation of the Zr-oxide cluster. In this work, a partially reactive force field to model UiO-66, nb-UiO-FF, is introduced. This force field incorporates node--ligand reactivity via a Morse potential and the introduction of dummy atoms to reproduce the anisotropic charge distribution of the Zr atoms in the node. nb-UiO-FF reproduces structural features of both UiO-66 and its isoreticular analog UiO-67 as well as framework stability with or without defects, activated or filled with N,N-dimethylformamide or ethanol. Defect generation and node--ligand binding energies are comparable with density functional theory values. The force field is further employed within a molecular dynamics scheme to study the early stages of solvothermal node--ligand binding. Species with structures corresponding to motifs present in UiO-66 are observed, along with other metastable species. This force field enables studying the self-assembly of UiO-66, as well as the formation of its point defects.

cond-mat.mtrl-sci↗

arXiv2026

Deterministic Volume Estimation of Truncated Hypercubes

We present a deterministic polynomial-time algorithm for estimating the volume of a hypercube intersected by a fixed number of constraints, where each constraint is the sum of univariate functions that are each nonnegative, monotone, and convex. Such constraints include knapsack and norm-ball constraints. The case of the unit hypercube truncated by a single linear constraint (halfspace) is already #P-hard. Given a fixed number of such constraints in a given dimension, together with an error parameter, our algorithm computes a multiplicative approximation of the volume of their intersection with the unit hypercube in time polynomial in the dimension, reciprocal error, input encoding length, and output encoding length.

cs.DS↗

arXiv2026

Dynamic Video Generation: Shaping Video Generation Across Time and Space

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive resolution sampling has emerged as a promising acceleration approach by reducing latent resolution in early stages. However, scaling this idea to video generation remains challenging, as the additional temporal dimension introduces diverse spatio-temporal demands across different videos, and compressing only a single dimension often leads to limited acceleration or degraded quality. Therefore, we propose DVG, a Dynamic Video Generation framework that jointly allocates computation across time and space, automatically selecting content-aware acceleration strategies without manual tuning or retraining. DVG achieves near-lossless acceleration across models and tasks, reaching up to 7 times speedup on HunyuanVideo and HunyuanVideo-1.5, and 18 times when combined with distillation, demonstrating its potential as a key component in today's large-scale efficient video generation systems. Our code is available at https://github.com/DarrenZheng303/DVG .

cs.CV↗

arXiv2026

The Martin boundary of the Directed Landscape

In the directed landscape, the Martin boundary coincides with the horofunction boundary. We show that functions in this boundary are precisely the eternal solutions possessing a spatial growth rate, and that the minimal Martin boundary is given by the Busemann functions. Moreover, every eternal solution can be expressed as a max-plus convex combination of countably many Busemann functions. Horofunctions are exactly those eternal solutions that admit a representation in terms of at most two Busemann functions with a common growth rate. As a consequence of instability, not all horofunctions are Busemann functions, and the Martin boundary is strictly larger than its minimal part.

math.PR↗

arXiv2026

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights or evaluation environments. Life-Harness evolves from training trajectories by converting recurring interaction failures into reusable interventions across environment contracts, procedural skills, action realization, and trajectory regulation, and remains fixed for evaluation on unseen tasks. We evaluate Life-Harness across eight environments from AgentBench, $τ$-bench, $τ^2$-bench, and AppWorld using 18 open-weight backbones, and further test three frontier models on seven environments. With Qwen3-4B-Instruct, Life-Harness exceeds Meta-Harness and AHE by 28.7 and 7.5 percentage points in mean accuracy across the seven shared environments, respectively, while using 8.5\% and 68.4\% fewer optimization tokens. The evolved harnesses also benefit GPT 5.5, Opus 4.8, and Gemini 3.1 Pro, yielding an average accuracy gain of 3.5 percentage points. Code is available at https://github.com/Tianshi-Xu/Life-Harness.

cs.AI↗