# Research Papers — 2025-10 · bundle page 18 of 217 > Full-text markdown of papers #851–900 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/18 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/17.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/19.md) ### Evaluating the Role of Verifiers in Test-Time Scaling for Legal Reasoning Tasks Authors: Davide Romano, Jonathan Schwarz, Daniele Giofré Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25623v2 Test-time scaling (TTS) techniques can improve the performance of large language models (LLMs) at the expense of additional computation and latency. While TTS has proven effective in formal domains such as mathematics and programming, its value in argumentative domains such as law remains underexplored. We present an empirical study of verifier-based TTS methods for legal multiple-choice QA (MCQA) across five benchmarks. Using a family of 7 reward models, we evaluate both outcome-level (Best-of-$N$) and process-level (tree search) verification under realistic low-$N$ budgets. Our analysis systematically investigates how verifier utility is affected by key properties such as domain specialization, model size, and supervision type (process-supervised PRMs vs. outcome-only ORMs), even when applied across different roles. --- ### FARSIQA: Faithful and Advanced RAG System for Islamic Question Answering Authors: Mohammad Aghajani Asl, Behrooz Minaei Bidgoli Published: 2025-10-29 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.25621v1 The advent of Large Language Models (LLMs) has revolutionized Natural Language Processing, yet their application in high-stakes, specialized domains like religious question answering is hindered by challenges like hallucination and unfaithfulness to authoritative sources. This issue is particularly critical for the Persian-speaking Muslim community, where accuracy and trustworthiness are paramount. Existing Retrieval-Augmented Generation (RAG) systems, relying on simplistic single-pass pipelines, fall short on complex, multi-hop queries requiring multi-step reasoning and evidence aggregation. To address this gap, we introduce FARSIQA, a novel, end-to-end system for Faithful Advanced Question Answering in the Persian Islamic domain. FARSIQA is built upon our innovative FAIR-RAG architecture: a Faithful, Adaptive, Iterative Refinement framework for RAG. FAIR-RAG employs a dynamic, self-correcting process: it adaptively decomposes complex queries, assesses evidence sufficiency, and enters an iterative loop to generate sub-queries, progressively filling information gaps. Operating on a curated knowledge base of over one million authoritative Islamic documents, FARSIQA demonstrates superior performance. Rigorous evaluation on the challenging IslamicPCQA benchmark shows state-of-the-art performance: the system achieves a remarkable 97.0% in Negative Rejection - a 40-point improvement over baselines - and a high Answer Correctness score of 74.3%. Our work establishes a new standard for Persian Islamic QA and validates that our iterative, adaptive architecture is crucial for building faithful, reliable AI systems in sensitive domains. --- ### Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization Authors: Nikita Kachaev, Mikhail Kolosov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.25616v1 The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for action models with broader generalization. Yet when these VLMs are adapted to the action modality, it remains unclear to what extent their original VL representations and knowledge are preserved. In this work, we conduct a systematic study of representation retention during VLA fine-tuning, showing that naive action fine-tuning leads to degradation of visual representations. To characterize and measure these effects, we probe VLA's hidden representations and analyze attention maps, further, we design a set of targeted tasks and methods that contrast VLA models with their counterpart VLMs, isolating changes in VL capabilities induced by action fine-tuning. We further evaluate a range of strategies for aligning visual representations and introduce a simple yet effective method that mitigates degradation and yields improved generalization to out-of-distribution (OOD) scenarios. Taken together, our analysis clarifies the trade-off between action fine-tuning and the degradation of VL representations and highlights practical approaches to recover inherited VL capabilities. Code is publicly available: https://blind-vla-paper.github.io --- ### Counterfactual-based Agent Influence Ranker for Agentic AI Workflows Authors: Amit Giloni, Chiara Picardi, Roy Betser, Shamik Bose, Aishvariya Priya Rathina Sabapathy, Roman Vainshtein Published: 2025-10-29 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2510.25612v1 An Agentic AI Workflow (AAW), also known as an LLM-based multi-agent system, is an autonomous system that assembles several LLM-based agents to work collaboratively towards a shared goal. The high autonomy, widespread adoption, and growing interest in such AAWs highlight the need for a deeper understanding of their operations, from both quality and security aspects. To this day, there are no existing methods to assess the influence of each agent on the AAW's final output. Adopting techniques from related fields is not feasible since existing methods perform only static structural analysis, which is unsuitable for inference time execution. We present Counterfactual-based Agent Influence Ranker (CAIR) - the first method for assessing the influence level of each agent on the AAW's output and determining which agents are the most influential. By performing counterfactual analysis, CAIR provides a task-agnostic analysis that can be used both offline and at inference time. We evaluate CAIR using an AAWs dataset of our creation, containing 30 different use cases with 230 different functionalities. Our evaluation showed that CAIR produces consistent rankings, outperforms baseline methods, and can easily enhance the effectiveness and relevancy of downstream tasks. --- ### Revisiting GAN with Bayes-Optimal Discrimination Authors: Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero Published: 2025-10-29 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2510.25609v3 We propose an alternative to the standard GAN training approach, in which the discriminator is a binary classifier trained by cross-entropy to distinguish real samples from generated ones. Instead, we directly target the discrimination Bayes error rate (BER). To this end, we use the recently proposed Bayes optimal learning threshold (BOLT) loss and train the generator to maximize a surrogate of the discrimination BER. This viewpoint gives a unified perspective on GAN training: different objectives can be interpreted as parameterized bounds on the discrimination BER that describe a trade-off between smoothness and tightness. We show that, under balanced class priors, maximizing the surrogate BER with an unconstrained discriminator minimizes the total variation between the data and generator distributions. By constraining the discriminator to be $1$-Lipschitz, the proposed maximization objective defines a discrepancy that is upper-bounded by the Wasserstein-1 distance, thereby linking it to Wasserstein GAN. Experiments on several image-generation datasets under matched architectures and optimization settings show that GAN training using the surrogate BER improves sample quality and coverage over standard baselines. This analysis suggests that the proposed Bayesian viewpoint can achieve a better trade-off between training stability and convergence of the generator to the data distribution. --- ### INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats Authors: Mengzhao Chen, Meng Wu, Hui Jin, Zhihang Yuan, Jing Liu, Chaoyi Zhang, Yunshui Li, Jie Huang, Jin Ma, Zeyue Xue, Zhiheng Liu, Xingyan Bin et al. Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25602v1 Modern AI hardware, such as Nvidia's Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats to handle the pervasive activation outliers in Large Language Models (LLMs). Despite this industry trend, a unified comparison of FP and integer (INT) quantization across varying granularities has been missing, leaving algorithm and hardware co-design without clear guidance. This paper fills that gap by systematically investigating the trade-offs between FP and INT formats. We reveal a critical performance crossover: while FP excels in coarse-grained quantization, the comparison at fine-grained (block-wise) levels is more nuanced. Our comprehensive comparison demonstrates that for popular 8-bit fine-grained formats (e.g., MX with block size 32), MXINT8 is superior to its FP counterpart in both algorithmic accuracy and hardware efficiency. However, for 4-bit formats, FP (e.g., MXFP4, NVFP4) often holds an accuracy advantage , though we show that NVINT4 can surpass NVFP4 when outlier-mitigation techniques like Hadamard rotation are applied. We also introduce a symmetric clipping method that resolves gradient bias in fine-grained low-bit INT training, enabling nearly lossless performance for MXINT8 training. These findings challenge the current hardware trajectory, demonstrating that a one-size-fits-all FP approach is suboptimal and advocating that fine-grained INT formats, particularly MXINT8, offer a better balance of accuracy, power, and efficiency for future AI accelerators. --- ### Uncertainty Quantification for Regression: A Unified Framework based on kernel scores Authors: Christopher Bülte, Yusuf Sale, Gitta Kutyniok, Eyke Hüllermeier Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25599v2 Regression tasks, notably in safety-critical domains, require reliable uncertainty quantification, yet the literature remains largely classification-focused. To address this, we introduce a family of measures for total, aleatoric, and epistemic uncertainty in multivariate regression based on strictly proper kernel scores. The framework provides a principled recipe for designing new uncertainty measures whose behavior, such as tail sensitivity or out-of-distribution responsiveness, is governed by the choice of the underlying kernel, while also encompassing existing measures under a joint analysis. We prove explicit correspondences between properties of the kernel and behavior of resulting uncertainty measures, yielding concrete design guidelines for practitioners. Extensive experiments across structured regression tasks, including spatial and functional domains, demonstrate effectiveness on downstream tasks such as out-of-distribution detection and active learning, and reveal that different kernel choices lead to distinct trade-offs, offering practitioners guidance for task-specific selection. --- ### Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry Authors: Run Peng, Ziqiao Ma, Amy Pang, Sikai Li, Zhang Xi-Jia, Yingzhuo Yu, Cristian-Paul Bara, Joyce Chai Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25595v2 While Large Language Model (LLM) agents are often approached from the angle of action planning/generation to accomplish a goal (e.g., given by language descriptions), their abilities to collaborate with each other to achieve a joint goal are not well explored. To address this limitation, this paper studies LLM agents in task collaboration, particularly under the condition of information asymmetry, where agents have disparities in their knowledge and skills and need to work together to complete a shared task. We extend Einstein Puzzles, a classical symbolic puzzle, to a table-top game. In this game, two LLM agents must reason, communicate, and act to satisfy spatial and relational constraints required to solve the puzzle. We apply a fine-tuning-plus-verifier framework in which LLM agents are equipped with various communication strategies and verification signals from the environment. Empirical results highlight the critical importance of aligned communication, especially when agents possess both information-seeking and -providing capabilities. Interestingly, agents without communication can still achieve high task performance; however, further analysis reveals a lack of true rule understanding and lower trust from human evaluators. Instead, by integrating an environment-based verifier, we enhance agents' ability to comprehend task rules and complete tasks, promoting both safer and more interpretable collaboration in AI systems. https://github.com/Roihn/EinsteinPuzzles --- ### Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning Authors: Arani Roy, Marco P. Apolinario, Shristi Das Biswas, Kaushik Roy Published: 2025-10-29 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2510.25594v1 Training deep neural networks (DNNs) with backpropagation (BP) achieves state-of-the-art accuracy but requires global error propagation and full parameterization, leading to substantial memory and computational overhead. Direct Feedback Alignment (DFA) enables local, parallelizable updates with lower memory requirements but is limited by unstructured feedback and poor scalability in deeper architectures, specially convolutional neural networks. To address these limitations, we propose a structured local learning framework that operates directly on low-rank manifolds defined by the Singular Value Decomposition (SVD) of weight matrices. Each layer is trained in its decomposed form, with updates applied to the SVD components using a composite loss that integrates cross-entropy, subspace alignment, and orthogonality regularization. Feedback matrices are constructed to match the SVD structure, ensuring consistent alignment between forward and feedback pathways. Our method reduces the number of trainable parameters relative to the original DFA model, without relying on pruning or post hoc compression. Experiments on CIFAR-10, CIFAR-100, and ImageNet show that our method achieves accuracy comparable to that of BP. Ablation studies confirm the importance of each loss term in the low-rank setting. These results establish local learning on low-rank manifolds as a principled and scalable alternative to full-rank gradient-based training. --- ### Generalized Sobolev IPM for Graph-Based Measures Authors: Tam Le, Truyen Nguyen, Hideitsu Hino, Kenji Fukumizu Published: 2025-10-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.25591v1 We study the Sobolev IPM problem for measures supported on a graph metric space, where critic function is constrained to lie within the unit ball defined by Sobolev norm. While Le et al. (2025) achieved scalable computation by relating Sobolev norm to weighted $L^p$-norm, the resulting framework remains intrinsically bound to $L^p$ geometric structure, limiting its ability to incorporate alternative structural priors beyond the $L^p$ geometry paradigm. To overcome this limitation, we propose to generalize Sobolev IPM through the lens of \emph{Orlicz geometric structure}, which employs convex functions to capture nuanced geometric relationships, building upon recent advances in optimal transport theory -- particularly Orlicz-Wasserstein (OW) and generalized Sobolev transport -- that have proven instrumental in advancing machine learning methodologies. This generalization encompasses classical Sobolev IPM as a special case while accommodating diverse geometric priors beyond traditional $L^p$ structure. It however brings up significant computational hurdles that compound those already inherent in Sobolev IPM. To address these challenges, we establish a novel theoretical connection between Orlicz-Sobolev norm and Musielak norm which facilitates a novel regularization for the generalized Sobolev IPM (GSI). By further exploiting the underlying graph structure, we show that GSI with Musielak regularization (GSI-M) reduces to a simple \emph{univariate optimization} problem, achieving remarkably computational efficiency. Empirically, GSI-M is several-order faster than the popular OW in computation, and demonstrates its practical advantages in comparing probability measures on a given graph for document classification and several tasks in topological data analysis. --- ### RegionE: Adaptive Region-Aware Generation for Efficient Image Editing Authors: Pengtao Chen, Xianfang Zeng, Maosen Zhao, Mingzhu Shen, Peng Ye, Bangyin Xiang, Zhibo Wang, Wei Cheng, Gang Yu, Tao Chen Published: 2025-10-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.25590v1 Recently, instruction-based image editing (IIE) has received widespread attention. In practice, IIE often modifies only specific regions of an image, while the remaining areas largely remain unchanged. Although these two types of regions differ significantly in generation difficulty and computational redundancy, existing IIE models do not account for this distinction, instead applying a uniform generation process across the entire image. This motivates us to propose RegionE, an adaptive, region-aware generation framework that accelerates IIE tasks without additional training. Specifically, the RegionE framework consists of three main components: 1) Adaptive Region Partition. We observed that the trajectory of unedited regions is straight, allowing for multi-step denoised predictions to be inferred in a single step. Therefore, in the early denoising stages, we partition the image into edited and unedited regions based on the difference between the final estimated result and the reference image. 2) Region-Aware Generation. After distinguishing the regions, we replace multi-step denoising with one-step prediction for unedited areas. For edited regions, the trajectory is curved, requiring local iterative denoising. To improve the efficiency and quality of local iterative generation, we propose the Region-Instruction KV Cache, which reduces computational cost while incorporating global information. 3) Adaptive Velocity Decay Cache. Observing that adjacent timesteps in edited regions exhibit strong velocity similarity, we further propose an adaptive velocity decay cache to accelerate the local denoising process. We applied RegionE to state-of-the-art IIE base models, including Step1X-Edit, FLUX.1 Kontext, and Qwen-Image-Edit. RegionE achieved acceleration factors of 2.57, 2.41, and 2.06. Evaluations by GPT-4o confirmed that semantic and perceptual fidelity were well preserved. --- ### Standardization of Psychiatric Diagnoses -- Role of Fine-tuned LLM Consortium and OpenAI-gpt-oss Reasoning LLM Enabled Decision Support System Authors: Eranga Bandara, Ross Gore, Atmaram Yarlagadda, Anita H. Clayton, Preston Samuel, Christopher K. Rhea, Sachin Shetty Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25588v1 The diagnosis of most mental disorders, including psychiatric evaluations, primarily depends on dialogues between psychiatrists and patients. This subjective process can lead to variability in diagnoses across clinicians and patients, resulting in inconsistencies and challenges in achieving reliable outcomes. To address these issues and standardize psychiatric diagnoses, we propose a Fine-Tuned Large Language Model (LLM) Consortium and OpenAI-gpt-oss Reasoning LLM-enabled Decision Support System for the clinical diagnosis of mental disorders. Our approach leverages fine-tuned LLMs trained on conversational datasets involving psychiatrist-patient interactions focused on mental health conditions (e.g., depression). The diagnostic predictions from individual models are aggregated through a consensus-based decision-making process, refined by the OpenAI-gpt-oss reasoning LLM. We propose a novel method for deploying LLM agents that orchestrate communication between the LLM consortium and the reasoning LLM, ensuring transparency, reliability, and responsible AI across the entire diagnostic workflow. Experimental results demonstrate the transformative potential of combining fine-tuned LLMs with a reasoning model to create a robust and highly accurate diagnostic system for mental health assessment. A prototype of the proposed platform, integrating three fine-tuned LLMs with the OpenAI-gpt-oss reasoning LLM, was developed in collaboration with the U.S. Army Medical Research Team in Norfolk, Virginia, USA. To the best of our knowledge, this work represents the first application of a fine-tuned LLM consortium integrated with a reasoning LLM for clinical mental health diagnosis paving the way for next-generation AI-powered eHealth systems aimed at standardizing psychiatric diagnoses. --- ### Learning-Augmented Online Bidding in Stochastic Settings Authors: Spyros Angelopoulos, Bertrand Simon Published: 2025-10-29 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2510.25582v1 Online bidding is a classic optimization problem, with several applications in online decision-making, the design of interruptible systems, and the analysis of approximation algorithms. In this work, we study online bidding under learning-augmented settings that incorporate stochasticity, in either the prediction oracle or the algorithm itself. In the first part, we study bidding under distributional predictions, and find Pareto-optimal algorithms that offer the best-possible tradeoff between the consistency and the robustness of the algorithm. In the second part, we study the power and limitations of randomized bidding algorithms, by presenting upper and lower bounds on the consistency/robustness tradeoffs. Previous works focused predominantly on oracles that do not leverage stochastic information on the quality of the prediction, and deterministic algorithms. --- ### Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models Authors: Harm Lameris, Shree Harsha Bokkahalli Satish, Joakim Gustafson, Éva Székely Published: 2025-10-29 Categories: eess.AS, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.25577v2 Recent advances in Speech Foundation Models (SFMs) enable direct processing of raw audio, allowing models to respond to subtle paralinguistic variation. However, how these models interpret non-lexical cues remains largely unstudied. We introduce VQ-Bench, a controlled evaluation suite featuring a parallel dataset of synthesized modal, breathy, creaky, and end-creak phonation types. We evaluate SFM sensitivity through open-ended generation across four ecologically valid domains, alongside speech emotion recognition. Our results reveal performance gaps: while a leading commercial API failed basic biometric sanity checks, other models exhibited systematic shifts in agency, empathy, and leadership based on phonation. Our findings also highlight gender asymmetries in salary and leadership endorsements, demonstrating that SFMs may mirror or amplify human social biases. This work establishes a reproducible framework for ensuring responsible paralinguistic interpretation in speech-based AI. --- ### Monitoring the calibration of probability forecasts with an application to concept drift detection involving image classification Authors: Christopher T. Franck, Anne R. Driscoll, Zoe Szajnfarber, William H. Woodall Published: 2025-10-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.25573v2 Machine learning approaches for image classification have led to impressive advances in that field. For example, convolutional neural networks are able to achieve remarkable image classification accuracy across a wide range of applications in industry, defense, and other areas. While these machine learning models boast impressive accuracy, a related concern is how to assess and maintain calibration in the predictions these models make. A classification model is said to be well calibrated if its predicted probabilities correspond with the rates events actually occur. While there are many available methods to assess machine learning calibration and recalibrate faulty predictions, less effort has been spent on developing approaches that continually monitor predictive models for potential loss of calibration as time passes. We propose a cumulative sum-based approach with dynamic limits that enable detection of miscalibration in both traditional process monitoring and concept drift applications. This enables early detection of operational context changes that impact image classification performance in the field. The proposed chart can be used broadly in any situation where the user needs to monitor probability predictions over time for potential lapses in calibration. Importantly, our method operates on probability predictions and event outcomes and does not require under-the-hood access to the machine learning model. --- ### Perturbation Bounds for Low-Rank Inverse Approximations under Noise Authors: Phuc Tran, Nisheeth K. Vishnoi Published: 2025-10-29 Categories: cs.LG, cs.DS, math.NA, math.SP, math.ST arXiv: https://arxiv.org/abs/2510.25571v1 Low-rank pseudoinverses are widely used to approximate matrix inverses in scalable machine learning, optimization, and scientific computing. However, real-world matrices are often observed with noise, arising from sampling, sketching, and quantization. The spectral-norm robustness of low-rank inverse approximations remains poorly understood. We systematically study the spectral-norm error $\| (\tilde{A}^{-1})_p - A_p^{-1} \|$ for an $n\times n$ symmetric matrix $A$, where $A_p^{-1}$ denotes the best rank-\(p\) approximation of $A^{-1}$, and $\tilde{A} = A + E$ is a noisy observation. Under mild assumptions on the noise, we derive sharp non-asymptotic perturbation bounds that reveal how the error scales with the eigengap, spectral decay, and noise alignment with low-curvature directions of $A$. Our analysis introduces a novel application of contour integral techniques to the \emph{non-entire} function $f(z) = 1/z$, yielding bounds that improve over naive adaptations of classical full-inverse bounds by up to a factor of $\sqrt{n}$. Empirically, our bounds closely track the true perturbation error across a variety of real-world and synthetic matrices, while estimates based on classical results tend to significantly overpredict. These findings offer practical, spectrum-aware guarantees for low-rank inverse approximations in noisy computational environments. --- ### A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes Authors: Benjamin Leblanc, Pascal Germain Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25569v1 PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formulation, it only provides guarantees on the expected risk of a randomly sampled hypothesis. This requires stochastic predictions at test time, making PAC-Bayes unusable in many practical situations where a single deterministic hypothesis must be deployed. We propose a unified framework to extract guarantees holding for a single hypothesis from stochastic PAC-Bayesian guarantees. We present a general oracle bound and derive from it a numerical bound and a specialization to majority vote. We empirically show that our approach consistently outperforms popular baselines (by up to a factor of 2) when it comes to generalization bounds on deterministic classifiers. --- ### PitchFlower: A flow-based neural audio codec with pitch controllability Authors: Diego Torres, Axel Roebel, Nicolas Obin Published: 2025-10-29 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2510.25566v3 We present PitchFlower, a flow-based neural audio codec with explicit pitch controllability. Our approach promotes pitch disentanglement through a simple perturbation: during training, F0 contours are flattened and randomly shifted at the input, while the true F0 is provided as conditioning to regenerate the original audio. A vector-quantization bottleneck prevents pitch recovery, and a flow-based decoder generates high quality audio. Experiments show that PitchFlower achieves accurate pitch control at the level of DSP baselines but at much higher audio quality, and performs on par with state-of-the-art neural approaches. Notably, despite using WORLD-transformed audio for training, our method filters out the vocoder's inherent artifacts, revealing a strong resilience of deep generative modeling to input degradation. This finding suggests that our framework provides a simple and extensible path that could be extended to other speech attributes. --- ### Leveraging an Atmospheric Foundational Model for Subregional Sea Surface Temperature Forecasting Authors: Víctor Medina, Giovanny A. Cuervo-Londoño, Javier Sánchez Published: 2025-10-29 Categories: cs.LG, cs.AI, physics.ao-ph arXiv: https://arxiv.org/abs/2510.25563v1 The accurate prediction of oceanographic variables is crucial for understanding climate change, managing marine resources, and optimizing maritime activities. Traditional ocean forecasting relies on numerical models; however, these approaches face limitations in terms of computational cost and scalability. In this study, we adapt Aurora, a foundational deep learning model originally designed for atmospheric forecasting, to predict sea surface temperature (SST) in the Canary Upwelling System. By fine-tuning this model with high-resolution oceanographic reanalysis data, we demonstrate its ability to capture complex spatiotemporal patterns while reducing computational demands. Our methodology involves a staged fine-tuning process, incorporating latitude-weighted error metrics and optimizing hyperparameters for efficient learning. The experimental results show that the model achieves a low RMSE of 0.119K, maintaining high anomaly correlation coefficients (ACC $\approx 0.997$). The model successfully reproduces large-scale SST structures but faces challenges in capturing finer details in coastal regions. This work contributes to the field of data-driven ocean forecasting by demonstrating the feasibility of using deep learning models pre-trained in different domains for oceanic applications. Future improvements include integrating additional oceanographic variables, increasing spatial resolution, and exploring physics-informed neural networks to enhance interpretability and understanding. These advancements can improve climate modeling and ocean prediction accuracy, supporting decision-making in environmental and economic sectors. --- ### Hybrid Quantum-Classical Recurrent Neural Networks Authors: Wenduan Xu Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.CL, quant-ph arXiv: https://arxiv.org/abs/2510.25557v2 We present a hybrid quantum-classical recurrent neural network (QRNN) architecture in which the recurrent core is realized as a parametrized quantum circuit (PQC) controlled by a classical feedforward network. The hidden state is the quantum state of an $n$-qubit PQC in an exponentially large Hilbert space $\mathbb{C}^{2^n}$, which serves as a coherent recurrent quantum memory. The PQC is unitary by construction, making the hidden-state evolution norm-preserving without external constraints. At each timestep, mid-circuit Pauli expectation-value readouts are combined with the input embedding and processed by the feedforward network, which provides explicit classical nonlinearity. The outputs parametrize the PQC, which updates the hidden state via unitary dynamics. The QRNN is compact and physically consistent, and it unifies (i) unitary recurrence as a high-capacity memory, (ii) partial observation via mid-circuit readouts, and (iii) nonlinear classical control for input-conditioned parametrization. We evaluate the model in simulation with up to 14 qubits on sentiment analysis, MNIST, permuted MNIST, copying memory, and language modeling. For sequence-to-sequence learning, we further devise a soft attention mechanism over the mid-circuit readouts and show its effectiveness for machine translation. To our knowledge, this is the first model (RNN or otherwise) grounded in quantum operations to achieve competitive performance against strong classical baselines across a broad class of sequence-learning tasks. --- ### Robust variable selection for spatial point processes observed with noise Authors: Dominik Sturm, Ivo F. Sbalzarini Published: 2025-10-29 Categories: stat.ME, cs.LG, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2510.25550v1 We propose a method for variable selection in the intensity function of spatial point processes that combines sparsity-promoting estimation with noise-robust model selection. As high-resolution spatial data becomes increasingly available through remote sensing and automated image analysis, identifying spatial covariates that influence the localization of events is crucial to understand the underlying mechanism. However, results from automated acquisition techniques are often noisy, for example due to measurement uncertainties or detection errors, which leads to spurious displacements and missed events. We study the impact of such noise on sparse point-process estimation across different models, including Poisson and Thomas processes. To improve noise robustness, we propose to use stability selection based on point-process subsampling and to incorporate a non-convex best-subset penalty to enhance model-selection performance. In extensive simulations, we demonstrate that such an approach reliably recovers true covariates under diverse noise scenarios and improves both selection accuracy and stability. We then apply the proposed method to a forestry data set, analyzing the distribution of trees in relation to elevation and soil nutrients in a tropical rain forest. This shows the practical utility of the method, which provides a systematic framework for robust variable selection in spatial point-process models under noise, without requiring additional knowledge of the process. --- ### Error Bounds and Optimal Schedules for Masked Diffusions with Factorized Approximations Authors: Hugo Lavenant, Giacomo Zanella Published: 2025-10-29 Categories: stat.ML, cs.IT, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2510.25544v2 Recently proposed generative models for discrete data, such as Masked Diffusion Models (MDMs), exploit conditional independence approximations to reduce the computational cost of popular Auto-Regressive Models (ARMs), at the price of some bias in the sampling distribution. We study the resulting computation-vs-accuracy trade-off, providing general error bounds (in relative entropy) that depend only on the average number of tokens generated per iteration and are independent of the data dimensionality (i.e. sequence length), thus supporting the empirical success of MDMs. We then investigate the gain obtained by using non-constant schedule sizes (i.e. varying the number of unmasked tokens during the generation process) and identify the optimal schedule as a function of a so-called information profile of the data distribution, thus allowing for a principled optimization of schedule sizes. We define methods directly as sampling algorithms and do not use classical derivations as time-reversed diffusion processes, leading us to simple and transparent proofs. --- ### Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information Authors: Yuan Cheng, Yu Huang, Zhe Xiong, Yingbin Liang, Vincent Y. F. Tan Published: 2025-10-29 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2510.25542v1 Uncovering hidden graph structures underlying real-world data is a critical challenge with broad applications across scientific domains. Recently, transformer-based models leveraging the attention mechanism have demonstrated strong empirical success in capturing complex dependencies within graphs. However, the theoretical understanding of their training dynamics has been limited to tree-like graphs, where each node depends on a single parent. Extending provable guarantees to more general directed acyclic graphs (DAGs) -- which involve multiple parents per node -- remains challenging, primarily due to the difficulty in designing training objectives that enable different attention heads to separately learn multiple different parent relationships. In this work, we address this problem by introducing a novel information-theoretic metric: the kernel-guided mutual information (KG-MI), based on the $f$-divergence. Our objective combines KG-MI with a multi-head attention framework, where each head is associated with a distinct marginal transition kernel to model diverse parent-child dependencies effectively. We prove that, given sequences generated by a $K$-parent DAG, training a single-layer, multi-head transformer via gradient ascent converges to the global optimum in polynomial time. Furthermore, we characterize the attention score patterns at convergence. In addition, when particularizing the $f$-divergence to the KL divergence, the learned attention scores accurately reflect the ground-truth adjacency matrix, thereby provably recovering the underlying graph structure. Experimental results validate our theoretical findings. --- ### TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation Authors: Bangde Du, Minghao Guo, Songming He, Ziyi Ye, Xi Zhu, Weihang Su, Shuqi Zhu, Yujia Zhou, Yongfeng Zhang, Qingyao Ai, Yiqun Liu Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25536v2 Large Language Models (LLMs) are exhibiting emergent human-like abilities and are increasingly envisioned as the foundation for simulating an individual's communication style, behavioral tendencies, and personality traits. However, current evaluations of LLM-based persona simulation remain limited: most rely on synthetic dialogues, lack systematic frameworks, and lack analysis of the capability requirement. To address these limitations, we introduce TwinVoice, a comprehensive benchmark for assessing persona simulation across diverse real-world contexts. TwinVoice encompasses three dimensions: Social Persona (public social interactions), Interpersonal Persona (private dialogues), and Narrative Persona (role-based expression). It further decomposes the evaluation of LLM performance into six fundamental capabilities, including opinion consistency, memory recall, logical reasoning, lexical fidelity, persona tone, and syntactic style. Experimental results reveal that while advanced models achieve moderate accuracy in persona simulation, they still fall short of capabilities such as syntactic style and memory recall. Consequently, the average performance achieved by LLMs remains considerably below the human baseline. --- ### Using latent representations to link disjoint longitudinal data for mixed-effects regression Authors: Clemens Schächter, Maren Hackenberg, Michelle Pfaffenlehner, Félix B. Tambe-Ndonfack, Thorsten Schmidt, Astrid Pechmann, Janbernd Kirschner, Jan Hasenauer, Harald Binder Published: 2025-10-29 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25531v2 Many rare diseases offer limited established treatment options, leading patients to switch therapies when new medications emerge. To analyze the impact of such treatment switches within the low sample size limitations of rare disease trials, it is important to use all available data sources. This, however, is complicated when usage of measurement instruments change during the observation period, for example when instruments are adapted to specific age ranges. The resulting disjoint longitudinal data trajectories, complicate the application of traditional modeling approaches like mixed-effects regression. We tackle this by mapping observations of each instrument to a aligned low-dimensional temporal trajectory, enabling longitudinal modeling across instruments. Specifically, we employ a set of variational autoencoder architectures to embed item values into a shared latent space for each time point. Temporal disease dynamics and treatment switch effects are then captured through a mixed-effects regression model applied to latent representations. To enable statistical inference, we present a novel statistical testing approach that accounts for the joint parameter estimation of mixed-effects regression and variational autoencoders. The methodology is applied to quantify the impact of treatment switches for patients with spinal muscular atrophy. Here, our approach aligns motor performance items from different measurement instruments for mixed-effects regression and maps estimated effects back to the observed item level to quantify the treatment switch effect. Our approach allows for model selection as well as for assessing effects of treatment switching. The results highlight the potential of modeling in joint latent representations for addressing small data challenges. --- ### Off-policy Reinforcement Learning with Model-based Exploration Augmentation Authors: Likun Wang, Xiangteng Zhang, Yinuo Wang, Guojian Zhan, Wenxuan Wang, Haoyu Gao, Jingliang Duan, Shengbo Eben Li Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25529v1 Exploration is fundamental to reinforcement learning (RL), as it determines how effectively an agent discovers and exploits the underlying structure of its environment to achieve optimal performance. Existing exploration methods generally fall into two categories: active exploration and passive exploration. The former introduces stochasticity into the policy but struggles in high-dimensional environments, while the latter adaptively prioritizes transitions in the replay buffer to enhance exploration, yet remains constrained by limited sample diversity. To address the limitation in passive exploration, we propose Modelic Generative Exploration (MoGE), which augments exploration through the generation of under-explored critical states and synthesis of dynamics-consistent experiences through transition models. MoGE is composed of two components: (1) a diffusion-based generator that synthesizes critical states under the guidance of a utility function evaluating each state's potential influence on policy exploration, and (2) a one-step imagination world model for constructing critical transitions based on the critical states for agent learning. Our method adopts a modular formulation that aligns with the principles of off-policy learning, allowing seamless integration with existing algorithms to improve exploration without altering their core structures. Empirical results on OpenAI Gym and DeepMind Control Suite reveal that MoGE effectively bridges exploration and policy learning, leading to remarkable gains in both sample efficiency and performance across complex control tasks. --- ### Zero Reinforcement Learning Towards General Domains Authors: Yuyuan Zeng, Yufei Huang, Can Xu, Qingfeng Sun, Jianfeng Yan, Guanghui Xu, Tao Yang, Fengzong Lian Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25528v1 Zero Reinforcement Learning (Zero-RL) has proven to be an effective approach for enhancing the reasoning capabilities of large language models (LLMs) by directly applying reinforcement learning with verifiable rewards on pretrained models, without the need for a supervised fine-tuning phase. However, current research on zero-RL primarily focuses on domains with easily verifiable reward signals, such as mathematics, programming, and other reasoning tasks. The challenge of eliciting reasoning abilities in more diverse scenarios, where verification is not straightforward, remains underexplored. To address this gap, we propose a novel zero-RL paradigm designed to improve a model's reasoning ability across both verifiable and non-verifiable domains. By combining verifiable rewards with a generative reward model, we conduct multi-task zero-RL training across both domains, facilitating the transfer of reasoning capabilities between them. Furthermore, to mitigate reward hacking in the generative reward model, we design a smooth length penalty that encourages the generation of more comprehensive thinking tokens in general domains. Experimental results on Qwen3-8B-Base and Qwen3-14B-Base demonstrate that our approach achieves superior reasoning performance, not only on tasks requiring extensive reasoning but also on more general tasks. --- ### Comparative Study of UNet-based Architectures for Liver Tumor Segmentation in Multi-Phase Contrast-Enhanced Computed Tomography Authors: Doan-Van-Anh Ly, Thanh-Hai Le, Thi-Thu-Hien Pham Published: 2025-10-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.25522v5 Segmentation of liver structures in multi-phase contrast-enhanced computed tomography (CECT) plays a crucial role in computer-aided diagnosis and treatment planning. In this study, we investigate the performance of UNet-based architectures for liver tumor segmentation, evaluating ResNet, Transformer-based, and State-space (Mamba) backbones initialized with pretrained weights. Our comparative analysis reveals that despite the theoretical advantages of modern architectures in modeling long-range dependencies, ResNet-based models demonstrated superior sample efficiency on this dataset. This suggests that the inherent inductive biases of Convolutional Neural Networks (CNNs) remain advantageous for generalizing on limited medical data compared to data-hungry alternatives. To further improve segmentation quality, we introduce attention mechanisms into the backbone, finding that the Convolutional Block Attention Module (CBAM) yields the optimal configuration. The ResNetUNet3+ with CBAM achieved the highest nominal performance with a Dice score of 0.755 and IoU of 0.662, while also delivering the most precise boundary delineation (lowest HD95 of 77.911). Critically, while statistical testing indicated that the improvement in mean Dice score was not significant (p > 0.05) compared to the baseline, the proposed model exhibited greater stability (lower standard deviation) and higher specificity (0.926). These findings demonstrate that classical ResNet architectures, when enhanced with modern attention modules, provide a robust and statistically comparable alternative to emerging methods, offering a stable direction for liver tumor segmentation in clinical practice. --- ### Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation Authors: Thomas Cook, Richard Osuagwu, Liman Tsatiashvili, Vrynsia Vrynsia, Koustav Ghosal, Maraim Masoud, Riccardo Mattivi Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25518v1 Retrieval-Augmented Generation (RAG) systems often face limitations in specialized domains such as fintech, where domain-specific ontologies, dense terminology, and acronyms complicate effective retrieval and synthesis. This paper introduces an agentic RAG architecture designed to address these challenges through a modular pipeline of specialized agents. The proposed system supports intelligent query reformulation, iterative sub-query decomposition guided by keyphrase extraction, contextual acronym resolution, and cross-encoder-based context re-ranking. We evaluate our approach against a standard RAG baseline using a curated dataset of 85 question--answer--reference triples derived from an enterprise fintech knowledge base. Experimental results demonstrate that the agentic RAG system outperforms the baseline in retrieval precision and relevance, albeit with increased latency. These findings suggest that structured, multi-agent methodologies offer a promising direction for enhancing retrieval robustness in complex, domain-specific settings. --- ### Predicate Renaming via Large Language Models Authors: Elisabetta Gentili, Tony Ribeiro, Fabrizio Riguzzi, Katsumi Inoue Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25517v1 In this paper, we address the problem of giving names to predicates in logic rules using Large Language Models (LLMs). In the context of Inductive Logic Programming, various rule generation methods produce rules containing unnamed predicates, with Predicate Invention being a key example. This hinders the readability, interpretability, and reusability of the logic theory. Leveraging recent advancements in LLMs development, we explore their ability to process natural language and code to provide semantically meaningful suggestions for giving a name to unnamed predicates. The evaluation of our approach on some hand-crafted logic rules indicates that LLMs hold potential for this task. --- ### Convergence of off-policy TD(0) with linear function approximation for reversible Markov chains Authors: Maik Overmars, Jasper Goseling, Richard Boucherie Published: 2025-10-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.25514v1 We study the convergence of off-policy TD(0) with linear function approximation when used to approximate the expected discounted reward in a Markov chain. It is well known that the combination of off-policy learning and function approximation can lead to divergence of the algorithm. Existing results for this setting modify the algorithm, for instance by reweighing the updates using importance sampling. This establishes convergence at the expense of additional complexity. In contrast, our approach is to analyse the standard algorithm, but to restrict our attention to the class of reversible Markov chains. We demonstrate convergence under this mild reversibility condition on the structure of the chain, which in many applications can be assumed using domain knowledge. In particular, we establish a convergence guarantee under an upper bound on the discount factor in terms of the difference between the on-policy and off-policy process. This improves upon known results in the literature that state that convergence holds for a sufficiently small discount factor by establishing an explicit bound. Convergence is with probability one and achieves projected Bellman error equal to zero. To obtain these results, we adapt the stochastic approximation framework that was used by Tsitsiklis and Van Roy (1997 for the on-policy case, to the off-policy case. We illustrate our results using different types of reversible Markov chains, such as one-dimensional random walks and random walks on a weighted graph. --- ### FaCT: Faithful Concept Traces for Explaining Neural Network Decisions Authors: Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer, Bernt Schiele Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.25512v2 Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to understand their workings, yet they are not always faithful to the model. Further, they make restrictive assumptions on the concepts a model learns, such as class-specificity, small spatial extent, or alignment to human expectations. In this work, we put emphasis on the faithfulness of such concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations. Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced. We also leverage foundation models to propose a new concept-consistency metric, C$^2$-Score, that can be used to evaluate concept-based methods. We show that, compared to prior work, our concepts are quantitatively more consistent and users find our concepts to be more interpretable, all while retaining competitive ImageNet performance. --- ### MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL Authors: Zekun Xu, Siyu Xia, Chuhuai Yue, Jiajun Chai, Mingxue Tian, Xiaohan Wang, Wei Lin, Haoxuan Li, Guojun Yin Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25510v1 As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, which restricts real-time error correction. However, integrating multi-turn tool invocation along with dynamic feedback could significantly improve adaptability and robustness, ultimately enhancing model performance. To address these issues, we propose MTIR-SQL, an innovative Multi-turn Tool-Integrated Reasoning reinforcement learning framework for Text-to-SQL. Our approach introduces an execution-aware multi-turn reasoning paradigm that seamlessly incorporates database execution feedback at each reasoning step, enabling context-sensitive query generation and progressive refinement throughout the reasoning process. The framework extends the GRPO algorithm to accommodate complex multi-turn interaction scenarios. Considering the training instability characteristics of MTIR and the potential for significant Deviation of model distribution from the initial model, we enhance the GRPO algorithm by adding a trajectory filtering mechanism and removing KL loss constraints. Experimental results demonstrate that MTIR-SQL, with 4B parameters, achieves \textbf{64.4}\% accuracy in the BIRD Dev and 84.6% execution accuracy in the SPIDER Dev, significantly outperforming existing approaches. --- ### Support Vector Machine-Based Burnout Risk Prediction with an Interactive Interface for Organizational Use Authors: Bruno W. G. Teodosio, Mário J. O. T. Lira, Pedro H. M. Araújo, Lucas R. C. Farias Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25509v1 Burnout is a psychological syndrome marked by emotional exhaustion, depersonalization, and reduced personal accomplishment, with a significant impact on individual well-being and organizational performance. This study proposes a machine learning approach to predict burnout risk using the HackerEarth Employee Burnout Challenge dataset. Three supervised algorithms were evaluated: nearest neighbors (KNN), random forest, and support vector machine (SVM), with model performance evaluated through 30-fold cross-validation using the determination coefficient (R2). Among the models tested, SVM achieved the highest predictive performance (R2 = 0.84) and was statistically superior to KNN and Random Forest based on paired $t$-tests. To ensure practical applicability, an interactive interface was developed using Streamlit, allowing non-technical users to input data and receive burnout risk predictions. The results highlight the potential of machine learning to support early detection of burnout and promote data-driven mental health strategies in organizational settings. --- ### Distributional Evaluation of Generative Models via Relative Density Ratio Authors: Yuliang Xu, Yun Wei, Li Ma Published: 2025-10-29 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2510.25507v2 We propose a function-valued evaluation metric for generative models based on the relative density ratio (RDR) designed to characterize distributional differences between real and generated samples. As an evaluation metric, the RDR function preserves $φ$-divergence between two distributions, enables sample-level evaluation that facilitates downstream investigations of feature-specific distributional differences, and has a bounded range that affords clear interpretability and numerical stability. Function estimation of the RDR is achieved efficiently through optimization on the variational form of $φ$-divergence. We provide theoretical convergence rate guarantees for general estimators based on M-estimator theory, as well as the convergence rate of neural network-based estimators when the true ratio is in the anisotropic Besov space. We demonstrate the power of the proposed RDR-based evaluation through numerical experiments on MNIST, CelebA64, and the American Gut project microbiome data. We show that the estimated RDR enables not only effective overall comparison of competing generative models, but also a convenient way to reveal the underlying nature of goodness-of-fit. This enables one to assess support overlap, coverage, and fidelity while pinpointing regions of the sample space where generators concentrate and revealing the features that drive the most salient distributional differences. --- ### Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies Authors: Florian Angermeir, Maximilian Amougou, Mark Kreitz, Andreas Bauer, Matthias Linhuber, Davide Fucci, Fabiola Moyón C., Daniel Mendez, Tony Gorschek Published: 2025-10-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.25506v3 Large Language Models have gained remarkable interest in industry and academia. The increasing interest in LLMs in academia is also reflected in the number of publications on this topic over the last years. For instance, alone 78 of the around 425 publications at ICSE 2024 performed experiments with LLMs. Conducting empirical studies with LLMs remains challenging and raises questions on how to achieve reproducible results, for both researchers and practitioners. One important step towards excelling in empirical research on LLM and their application is to first understand to what extent current research results are eventually reproducible and what factors may impede reproducibility. This investigation is within the scope of our work. We contribute an analysis of the reproducibility of LLM-centric studies, provide insights into the factors impeding reproducibility, and discuss suggestions on how to improve the current state. In particular, we studied the 85 articles describing LLM-centric studies, published at ICSE 2024 and ASE 2024. Of the 85 articles, 18 provided research artefacts and used OpenAI models. We attempted to replicate those 18 studies. Of the 18 studies, only five were sufficiently complete and executable. For none of the five studies, we were able to fully reproduce the results. Two studies seemed to be partially reproducible, and three studies did not seem to be reproducible. Our results highlight not only the need for stricter research artefact evaluations but also for more robust study designs to ensure the reproducible value of future publications. --- ### Multi-Objective Search: Algorithms, Applications, and Emerging Directions Authors: Oren Salzman, Carlos Hernández Ulloa, Ariel Felner, Sven Koenig Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25504v1 Multi-objective search (MOS) has emerged as a unifying framework for planning and decision-making problems where multiple, often conflicting, criteria must be balanced. While the problem has been studied for decades, recent years have seen renewed interest in the topic across AI applications such as robotics, transportation, and operations research, reflecting the reality that real-world systems rarely optimize a single measure. This paper surveys developments in MOS while highlighting cross-disciplinary opportunities, and outlines open challenges that define the emerging frontier of MOS --- ### TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting Authors: Vladyslav Moroshan, Julien Siems, Arber Zela, Timur Carstensen, Frank Hutter Published: 2025-10-29 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2510.25502v4 Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperforming on challenging benchmarks. This paper presents TempoPFN, a univariate time series foundation model based on linear Recurrent Neural Networks (RNNs) pre-trained exclusively on synthetic data. The model uses a GatedDeltaProduct architecture with state-weaving for fully parallelizable training across sequence lengths, eliminating the need for windowing or summarization techniques while maintaining robust temporal state-tracking. Our comprehensive synthetic data pipeline unifies diverse generators, including stochastic differential equations, Gaussian processes, and audio synthesis, with novel augmentations. In zero-shot evaluations on the Gift-Eval, fev-bench and Chronos-ZS benchmarks, TempoPFN achieves top-tier competitive performance, outperforming all existing synthetic-only approaches and surpassing the majority of models trained on real-world data, while being more efficient than existing baselines by leveraging fully parallelizable training and inference. We open-source our complete data generation pipeline and training code, providing a reproducible foundation for future research. --- ### Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI Authors: Luca Andolfi, Eleonora Giunchiglia Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25497v3 Neurosymbolic AI is growing in popularity thanks to its ability to combine neural perception and symbolic reasoning in end-to-end trainable models. However, recent findings reveal these are prone to shortcut reasoning, i.e., to learning unindented concepts--or neural predicates--which exploit spurious correlations to satisfy the symbolic constraints. In this paper, we address reasoning shortcuts at their root cause and we introduce Prototypical Neurosymbolic architectures. These models are able to satisfy the symbolic constraints (be right) because they have learnt the correct basic concepts (for the right reasons) and not because of spurious correlations, even in extremely low data regimes. Leveraging the theory of prototypical learning, we demonstrate that we can effectively avoid reasoning shortcuts by training the models to satisfy the background knowledge while taking into account the similarity of the input with respect to the handful of labelled datapoints. We extensively validate our approach on the recently proposed rsbench benchmark suite in a variety of settings and tasks with very scarce supervision: we show significant improvements in learning the right concepts both in synthetic tasks (MNIST-EvenOdd and Kand-Logic) and real-world, high-stake ones (BDD-OIA). Our findings pave the way to prototype grounding as an effective, annotation-efficient strategy for safe and reliable neurosymbolic learning. --- ### Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks Authors: Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25480v1 Robust validation metrics remain essential in contemporary deep learning, not only to detect overfitting and poor generalization, but also to monitor training dynamics. In the supervised classification setting, we investigate whether interactions between training data and model weights can yield such a metric that both tracks generalization during training and attributes performance to individual training samples. We introduce Gradient-Weight Alignment (GWA), quantifying the coherence between per-sample gradients and model weights. We show that effective learning corresponds to coherent alignment, while misalignment indicates deteriorating generalization. GWA is efficiently computable during training and reflects both sample-specific contributions and dataset-wide learning dynamics. Extensive experiments show that GWA accurately predicts optimal early stopping, enables principled model comparisons, and identifies influential training samples, providing a validation-set-free approach for model analysis directly from the training data. --- ### An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminated Authors: Willem Fourie Published: 2025-10-29 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.25471v2 Instrumental goals such as resource acquisition, power-seeking, and self-preservation are key to contemporary AI alignment research, yet the phenomenon's ontology remains under-theorised. This article develops an ontological account of instrumental goals and draws out governance-relevant distinctions for advanced AI systems. After systematising the dominant alignment literature on instrumental goals we offer an exploratory Aristotelian framework that treats advanced AI systems as complex artefacts whose ends are externally imposed through design, training and deployment. On a structural reading, Aristotle's notion of hypothetical necessity explains why, given an imposed end pursued over extended horizons in particular environments, certain enabling conditions become conditionally required, thereby yielding robust instrumental tendencies. On a contingent reading, accidental causation and chance-like intersections among training regimes, user inputs, infrastructure and deployment contexts can generate instrumental-goal-like behaviours not entailed by the imposed end-structure. This dual-aspect ontology motivates for governance and management approaches that treat instrumental goals as features of advanced AI systems to be managed rather than anomalies eliminable by technical interventions. --- ### An In-Depth Analysis of Cyber Attacks in Secured Platforms Authors: Parick Ozoh, John K Omoniyi, Bukola Ibitoye Published: 2025-10-29 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25470v1 There is an increase in global malware threats. To address this, an encryption-type ransomware has been introduced on the Android operating system. The challenges associated with malicious threats in phone use have become a pressing issue in mobile communication, disrupting user experiences and posing significant privacy threats. This study surveys commonly used machine learning techniques for detecting malicious threats in phones and examines their performance. The majority of past research focuses on customer feedback and reviews, with concerns that people might create false reviews to promote or devalue products and services for personal gain. Hence, the development of techniques for detecting malicious threats using machine learning has been a key focus. This paper presents a comprehensive comparative study of current research on the issue of malicious threats and methods for tackling these challenges. Nevertheless, a huge amount of information is required by these methods, presenting a challenge for developing robust, specialized automated anti-malware systems. This research describes the Android Applications dataset, and the accuracy of the techniques is measured using the accuracy levels of the metrics employed in this study. --- ### SPADE: Sparsity Adaptive Depth Estimator for Zero-Shot, Real-Time, Monocular Depth Estimation in Underwater Environments Authors: Hongjie Zhang, Gideon Billings, Stefan B. Williams Published: 2025-10-29 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2510.25463v1 Underwater infrastructure requires frequent inspection and maintenance due to harsh marine conditions. Current reliance on human divers or remotely operated vehicles is limited by perceptual and operational challenges, especially around complex structures or in turbid water. Enhancing the spatial awareness of underwater vehicles is key to reducing piloting risks and enabling greater autonomy. To address these challenges, we present SPADE: SParsity Adaptive Depth Estimator, a monocular depth estimation pipeline that combines pre-trained relative depth estimator with sparse depth priors to produce dense, metric scale depth maps. Our two-stage approach first scales the relative depth map with the sparse depth points, then refines the final metric prediction with our proposed Cascade Conv-Deformable Transformer blocks. Our approach achieves improved accuracy and generalisation over state-of-the-art baselines and runs efficiently at over 15 FPS on embedded hardware, promising to support practical underwater inspection and intervention. This work has been submitted to IEEE Journal of Oceanic Engineering Special Issue of AUV 2026. --- ### Fine-Tuned Language Models for Domain-Specific Summarization and Tagging Authors: Jun Wang, Fuming Lin, Yuyu Chen Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25460v1 This paper presents a pipeline integrating fine-tuned large language models (LLMs) with named entity recognition (NER) for efficient domain-specific text summarization and tagging. The authors address the challenge posed by rapidly evolving sub-cultural languages and slang, which complicate automated information extraction and law enforcement monitoring. By leveraging the LLaMA Factory framework, the study fine-tunes LLMs on both generalpurpose and custom domain-specific datasets, particularly in the political and security domains. The models are evaluated using BLEU and ROUGE metrics, demonstrating that instruction fine-tuning significantly enhances summarization and tagging accuracy, especially for specialized corpora. Notably, the LLaMA3-8B-Instruct model, despite its initial limitations in Chinese comprehension, outperforms its Chinese-trained counterpart after domainspecific fine-tuning, suggesting that underlying reasoning capabilities can transfer across languages. The pipeline enables concise summaries and structured entity tagging, facilitating rapid document categorization and distribution. This approach proves scalable and adaptable for real-time applications, supporting efficient information management and the ongoing need to capture emerging language trends. The integration of LLMs and NER offers a robust solution for transforming unstructured text into actionable insights, crucial for modern knowledge management and security operations. --- ### Scalable Utility-Aware Multiclass Calibration Authors: Mahmoud Hegazy, Michael I. Jordan, Aymeric Dieuleveut Published: 2025-10-29 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2510.25458v1 Ensuring that classifiers are well-calibrated, i.e., their predictions align with observed frequencies, is a minimal and fundamental requirement for classifiers to be viewed as trustworthy. Existing methods for assessing multiclass calibration often focus on specific aspects associated with prediction (e.g., top-class confidence, class-wise calibration) or utilize computationally challenging variational formulations. In this work, we study scalable \emph{evaluation} of multiclass calibration. To this end, we propose utility calibration, a general framework that measures the calibration error relative to a specific utility function that encapsulates the goals or decision criteria relevant to the end user. We demonstrate how this framework can unify and re-interpret several existing calibration metrics, particularly allowing for more robust versions of the top-class and class-wise calibration metrics, and, going beyond such binarized approaches, toward assessing calibration for richer classes of downstream utilities. --- ### Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions Authors: Mohamad Abou Ali, Fadi Dornaika Published: 2025-10-29 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25445v1 Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual retrofitting. This survey cuts through this confusion by introducing a novel dual-paradigm framework that categorizes agentic systems into two distinct lineages: the Symbolic/Classical (relying on algorithmic planning and persistent state) and the Neural/Generative (leveraging stochastic generation and prompt-driven orchestration). Through a systematic PRISMA-based review of 90 studies (2018--2025), we provide a comprehensive analysis structured around this framework across three dimensions: (1) the theoretical foundations and architectural principles defining each paradigm; (2) domain-specific implementations in healthcare, finance, and robotics, demonstrating how application constraints dictate paradigm selection; and (3) paradigm-specific ethical and governance challenges, revealing divergent risks and mitigation strategies. Our analysis reveals that the choice of paradigm is strategic: symbolic systems dominate safety-critical domains (e.g., healthcare), while neural systems prevail in adaptive, data-rich environments (e.g., finance). Furthermore, we identify critical research gaps, including a significant deficit in governance models for symbolic systems and a pressing need for hybrid neuro-symbolic architectures. The findings culminate in a strategic roadmap arguing that the future of Agentic AI lies not in the dominance of one paradigm, but in their intentional integration to create systems that are both adaptable and reliable. This work provides the essential conceptual toolkit to guide future research, development, and policy toward robust and trustworthy hybrid intelligent systems. --- ### Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs Authors: Fei Wei, Daoyuan Chen, Ce Wang, Yilun Huang, Yushuo Chen, Xuchen Pan, Yaliang Li, Bolin Ding Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25441v2 Large Language Models (LLMs) excel as passive responders, but teaching them to be proactive, goal-oriented partners, a critical capability in high-stakes domains, remains a major challenge. Current paradigms either myopically optimize single-turn attributes or rely on brittle, high-cost user simulators, creating a persistent ``reality gap''. To bridge this gap, we introduce \texttt{Learn-to-Ask}, a general, simulator-free framework for learning and deploying proactive dialogue agents \textit{directly from offline expert data}, bypassing the need to model complex user dynamics. Our key insight is to reframe the offline policy learning problem by leveraging the \textbf{observed future} of each expert trajectory. This allows us to infer a dense, turn-by-turn reward signal grounded in the expert's revealed strategy, decomposing the intractable long-horizon problem into a series of supervised learning tasks, and training a policy to output a structured \texttt{(action, state_assessment)} tuple, governing both \textbf{what to ask} and, crucially, \textbf{when to stop}. To ensure reward fidelity, our Automated Grader Calibration pipeline systematically purges noise from the LLM-based reward model with minimal human supervision. Empirically, we demonstrate the efficacy of \texttt{Learn-to-Ask} in a real-world medical dataset, using LLMs of varying sizes up to 32B. Our approach culminates in the successful deployment of LLMs into a live, large-scale online AI service. In rigorous in-house evaluations, our model was launched and achieved performance even superior to human experts, proving our framework's ability to translate offline data into tangible, real-world impact. We hope this work provides a practical and economically viable blueprint for transforming passive LLMs into proactive, goal-oriented LLM applications. --- ### More than a Moment: Towards Coherent Sequences of Audio Descriptions Authors: Eshika Khandelwal, Junyu Xie, Tengda Han, Max Bain, Arsha Nagrani, Andrew Zisserman, Gül Varol, Makarand Tapaswi Published: 2025-10-29 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2510.25440v1 Audio Descriptions (ADs) convey essential on-screen information, allowing visually impaired audiences to follow videos. To be effective, ADs must form a coherent sequence that helps listeners to visualise the unfolding scene, rather than describing isolated moments. However, most automatic methods generate each AD independently, often resulting in repetitive, incoherent descriptions. To address this, we propose a training-free method, CoherentAD, that first generates multiple candidate descriptions for each AD time interval, and then performs auto-regressive selection across the sequence to form a coherent and informative narrative. To evaluate AD sequences holistically, we introduce a sequence-level metric, StoryRecall, which measures how well the predicted ADs convey the ground truth narrative, alongside repetition metrics that capture the redundancy across consecutive AD outputs. Our method produces coherent AD sequences with enhanced narrative understanding, outperforming prior approaches that rely on independent generations. --- ### A Critical Study of Automatic Evaluation in Sign Language Translation Authors: Shakib Yazdani, Yasser Hamidullah, Cristina España-Bonet, Eleftherios Avramidis, Josef van Genabith Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25434v2 Automatic evaluation metrics are crucial for advancing sign language translation (SLT). Current SLT evaluation metrics, such as BLEU and ROUGE, are only text-based, and it remains unclear to what extent text-based metrics can reliably capture the quality of SLT outputs. To address this gap, we investigate the limitations of text-based SLT evaluation metrics by analyzing six metrics, including BLEU, chrF, and ROUGE, as well as BLEURT on the one hand, and large language model (LLM)-based evaluators such as G-Eval and GEMBA zero-shot direct assessment on the other hand. Specifically, we assess the consistency and robustness of these metrics under three controlled conditions: paraphrasing, hallucinations in model outputs, and variations in sentence length. Our analysis highlights the limitations of lexical overlap metrics and demonstrates that while LLM-based evaluators better capture semantic equivalence often missed by conventional metrics, they can also exhibit bias toward LLM-paraphrased translations. Moreover, although all metrics are able to detect hallucinations, BLEU tends to be overly sensitive, whereas BLEURT and LLM-based evaluators are comparatively lenient toward subtle cases. This motivates the need for multimodal evaluation frameworks that extend beyond text-based metrics to enable a more holistic assessment of SLT outputs. --- ### Depth and Autonomy: A Framework for Evaluating LLM Applications in Social Science Research Authors: Ali Sanaei, Ali Rajabzadeh Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25432v1 Large language models (LLMs) are increasingly utilized by researchers across a wide range of domains, and qualitative social science is no exception; however, this adoption faces persistent challenges, including interpretive bias, low reliability, and weak auditability. We introduce a framework that situates LLM usage along two dimensions, interpretive depth and autonomy, thereby offering a straightforward way to classify LLM applications in qualitative research and to derive practical design recommendations. We present the state of the literature with respect to these two dimensions, based on all published social science papers available on Web of Science that use LLMs as a tool and not strictly as the subject of study. Rather than granting models expansive freedom, our approach encourages researchers to decompose tasks into manageable segments, much as they would when delegating work to capable undergraduate research assistants. By maintaining low levels of autonomy and selectively increasing interpretive depth only where warranted and under supervision, one can plausibly reap the benefits of LLMs while preserving transparency and reliability. ---