# Research Papers — 2026-04 · bundle page 7 of 233 > Full-text markdown of papers #301–350 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/7 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/6.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/8.md) ### Differential Subgroup Discovery: Characterizing Where Two Populations Differ, and Why Authors: Sascha Xu, Jilles Vreeken Published: 2026-04-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27741v1 We study the problem of understanding where two populations differ within a feature space, which we formalize in the concept of a differential subgroup: a subset of individuals from both populations who, despite sharing similar characteristics, exhibit exceptional differences in a target outcome. Differential subgroups reveal the regions of the feature space where population-level gaps are most pronounced and can help practitioners identify the covariate combinations that are structurally responsible for these differences, e.g.~in clinical analysis, model diagnostics, or treatment-effect studies. We introduce a general optimization objective for discovering differential subgroups and establish conditions under which the resulting subgroups admit a causal interpretation of population differences. We propose DiffSub, a gradient-based approach that discovers interpretable differential subgroups in tabular data. Across synthetic benchmarks, medical case studies, model-error analyses, and treatment-effect settings, DiffSub identifies informative subgroups that reveal where population differences arise and why. --- ### Sampling two-dimensional spin systems with transformers Authors: Piotr Białas, Piotr Korcyl, Tomasz Stebel, Adam Stefański, Dawid Zapolski Published: 2026-04-30 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.LG, hep-lat arXiv: https://arxiv.org/abs/2604.27738v1 Autoregressive Neural Networks based on dense or convolutional layers have recently been shown to be a viable strategy for generating classical spin systems. Unlike these methods, sampling with transformers is commonly considered to be computationally inefficient. In this work, we propose a novel approach to transformer-based neural samplers in which we generate not a single spin per step but groups of spins. As an additional improvement, we construct a model of approximated probabilities, further improving the efficiency of the algorithm. Despite our approach being computationally heavier than dense networks or CNN-based approaches, we were able to sample larger systems of up to $180 \times 180$ spins in case of the Ising model. The Effective Sample Size of our sampler is $\sim 20$ times larger than that of the previous state-of-the-art neural sampler when trained for the $128 \times 128$ Ising model at critical temperature. Finally, we also test our algorithm on the 2D Edwards-Anderson model, where we train $64\times 64$ spin systems. --- ### Mind the Gap: Structure-Aware Consistency in Preference Learning Authors: Mehryar Mohri, Yutao Zhong Published: 2026-04-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27733v2 Aligning Large Language Models (LLMs) with human intent, whether through explicit reward modeling or direct methods such as DPO, fundamentally relies on minimizing a surrogate loss as a proxy for the true pairwise ranking objective. We prove that this reliance is flawed for the standard surrogate losses used: for the equicontinuous hypothesis sets characteristic of neural networks, no standard surrogate provides a meaningful consistency guarantee. Minimizing the surrogate loss to zero can leave the true ranking error arbitrarily high. To resolve this, we formulate LLM alignment within a margin-shifted ranking framework and derive $H$-consistency bounds showing that enforcing a confidence margin $γ$ is not merely beneficial but necessary for consistency. We further introduce Structure-Aware $H$-consistency and a corresponding objective (SA-DPO) that adapts the margin to the semantic distance between responses, preventing instability on near-synonymous pairs. Finally, we analyze the trade-off between the margin required for consistency and the model's finite capacity to satisfy it, revealing a strict hierarchy of surrogate losses: heavy-tailed surrogates (e.g., the Polynomial Hinge family) offer strictly superior consistency guarantees for capacity-bounded models compared to the logistic loss used in DPO. Experiments on UltraFeedback and Argilla DPO-Mix-7k confirm that SA-DPO consistently outperforms DPO and SimPO, with a 58.5% head-to-head win-rate in downstream generation quality. --- ### Mind the Gap: Structure-Aware Consistency in Preference Learning Authors: Mehryar Mohri, Yutao Zhong Published: 2026-04-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27733v1 Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as proxies for the intractable pairwise ranking loss. However, we demonstrate that for the equicontinuous hypothesis sets typical of neural networks, these standard surrogates are theoretically inconsistent, yielding vacuous generalization guarantees. To resolve this, we formulate LLM alignment within a margin-shifted ranking framework. We derive rigorous $H$-consistency bounds that depend on enforcing a separation margin $γ$. Crucially, we extend this to Structure-Aware $H$-consistency, introducing a novel objective (SA-DPO) that adapts the margin based on the semantic distance between responses to handle synonyms and hard pairs. Finally, we analyze the trade-off between consistency and model limitations via the Margin-Capacity Profile, proving that heavy-tailed surrogates (such as the Polynomial Hinge family) offer superior consistency guarantees for capacity-bounded models compared to the standard logistic loss used in DPO. --- ### AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments Authors: Jiaju Chen, Jinghua Piao, Xia Xu, Songwei Li, Tong Xia, Xiangnan He, Yong Li Published: 2026-04-30 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.27725v1 A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive system designed to translate abstract intuitions into executable computational experiments. Grounded in a domain-specific knowledge base covering over 13,000 high-quality academic papers, the system employs a modular multi-stage architecture. Specifically, the Idea Development Stage generates literature-grounded hypotheses, the Experimental Design Stage configures simulator-aligned experimental parameters and protocols, and the Experimental Execution Stage runs experiments and returns structured analyses. Together, these stages form a human-in-the-loop, iterative workflow that translates economic intuitions into executable computational experiments. Through extensive experiments involving human expert evaluation and large language models (LLMs) as judges, we show that the system generates research ideas with stronger literature grounding and higher novelty and insight than state-of-the-art generic LLMs. Overall, AgentEconomist adopts a human-AI collaboration paradigm that enables researchers to focus on high-level intuitions, while delegating the labor-intensive processes of translation and computational execution to agents. --- ### Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering Authors: Xupeng Chen, Binbin Shi, Chenqian Le, Jiaqi Zhang, Kewen Wang, Ran Gong, Jinhan Zhang, Chihang Wang Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27724v2 Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose MED-VRAG, an iterative multimodal RAG framework that retrieves and reasons over PMC document page images instead of OCR'd text. The system pairs ColQwen2.5 patch-level page embeddings with a sharded MapReduce LLM filter, scaling to ~350K pages while keeping Stage-1 retrieval under 30 ms via an offline coarse-to-fine index (C=8 centroids per page, ANN over centroids, exact two-way scoring on the top-R shortlist). A vision-language model (VLM) then iteratively refines its query and accumulates evidence in a memory bank across up to 3 reasoning rounds, with a single iteration costing ~15.9 s and the full three-round pipeline ~47.8 s on 4xA100. Across four medical QA benchmarks (MedQA, MedMCQA, PubMedQA, MMLU-Med), MEDVRAG reaches 78.6% average accuracy. Under controlled comparison with the same Qwen2.5-VL-32B backbone, retrieval contributes a +5.8 point gain over the no-retrieval baseline; we also note a +1.8 point edge over MedRAG + GPT-4 (76.8%), with the caveat that this is a cross-paper rather than head-to-head comparison. Ablations isolate +1.0 from page-image vs text-chunk retrieval, +1.5 from iteration, and +1.0 from the memory bank. --- ### Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering Authors: Xupeng Chen, Binbin Shi, Chenqian Le, Jiaqi Zhang, Kewen Wang, Ran Gong, Jinhan Zhang, Chihang Wang Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27724v1 Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose MED-VRAG, an iterative multimodal RAG framework that retrieves and reasons over PMC document page images instead of OCR'd text. The system pairs ColQwen2.5 patch-level page embeddings with a sharded MapReduce LLM filter, scaling to ~350K pages while keeping Stage-1 retrieval under 30 ms via an offline coarse-to-fine index (C=8 centroids per page, ANN over centroids, exact two-way scoring on the top-R shortlist). A vision-language model (VLM) then iteratively refines its query and accumulates evidence in a memory bank across up to 3 reasoning rounds, with a single iteration costing ~15.9 s and the full three-round pipeline ~47.8 s on 4xA100. Across four medical QA benchmarks (MedQA, MedMCQA, PubMedQA, MMLU-Med), MEDVRAG reaches 78.6% average accuracy. Under controlled comparison with the same Qwen2.5-VL-32B backbone, retrieval contributes a +5.8 point gain over the no-retrieval baseline; we also note a +1.8 point edge over MedRAG + GPT-4 (76.8%), with the caveat that this is a cross-paper rather than head-to-head comparison. Ablations isolate +1.0 from page-image vs text-chunk retrieval, +1.5 from iteration, and +1.0 from the memory bank. --- ### Optimized Deferral for Imbalanced Settings Authors: Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong Published: 2026-04-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27723v2 Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, is essential in domains like natural language generation, medical diagnosis, and computer vision, where an effective deferral can reduce errors at low extra resource consumption. However, the two-stage learning to defer setting, which leverages existing predictors such as a collection of LLMs or other classifiers, often faces challenges due to an expert imbalance problem. This imbalance can lead to suboptimal performance, with deferral algorithms favoring the majority expert. We present a comprehensive study of two-stage learning to defer in expert imbalance settings. We cast the deferral loss optimization as a novel cost-sensitive learning problem over the input-expert domain. We derive new margin-based loss functions and guarantees tailored to this setting, and develop novel algorithms for cost-sensitive learning. Leveraging these results, we design principled deferral algorithms, MILD (Margin-based Imbalanced Learning to Defer), specifically suited for expert imbalance settings. Extensive experiments demonstrate the effectiveness of our approach, showing clear improvements over existing baselines on both image classification and real-world Large Language Model (LLM) routing tasks. --- ### Optimized Deferral for Imbalanced Settings Authors: Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong Published: 2026-04-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.27723v1 Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, is essential in domains like natural language generation, medical diagnosis, and computer vision, where an effective deferral can reduce errors at low extra resource consumption. However, the two-stage learning to defer setting, which leverages existing predictors such as a collection of LLMs or other classifiers, often faces challenges due to an expert imbalance problem. This imbalance can lead to suboptimal performance, with deferral algorithms favoring the majority expert. We present a comprehensive study of two-stage learning to defer in expert imbalance settings. We cast the deferral loss optimization as a novel cost-sensitive learning problem over the input-expert domain. We derive new margin-based loss functions and guarantees tailored to this setting, and develop novel algorithms for cost-sensitive learning. Leveraging these results, we design principled deferral algorithms, MILD (Margin-based Imbalanced Learning to Defer), specifically suited for expert imbalance settings. Extensive experiments demonstrate the effectiveness of our approach, showing clear improvements over existing baselines on both image classification and real-world Large Language Model (LLM) routing tasks. --- ### Physically-Informed Fuzzy Clustering of Vertical Sounding Ionograms Authors: Oleg I. Berngardt, Sergey N. Ponomarchuk Published: 2026-04-30 Categories: physics.ao-ph, cs.CV, physics.data-an, physics.space-ph arXiv: https://arxiv.org/abs/2604.27721v1 This paper presents a physically-informed fuzzy clustering of vertical sounding ionograms for automatically separating the ionogram into tracks suitable for further interpretation and determining their optimal number. The model is designed for use not only in conditions where the number of tracks is known, but also in disturbed ionospheric conditions where the number of tracks is preliminary unknown. The method is based on an expectation-maximization algorithm, used for clustering, and on parametrically specified distributions of distances from points to parametrically specified curves. The curves used as track models are close to model tracks in the parabolic ionospheric layer model. The resulting model of each track has six parameters: three standard ones (the critical frequency, the lower boundary of the layer, and its half-width), and three additional ones to take into account possible underlying layer effects. By sequentially increasing the number of tracks and optimizing their parameters, the model finds the optimal number of tracks on the ionogram by minimizing the modified Bayesian information criterion. The Sequential Least Squares Quadratic Programming algorithm is used to find the parameters of a single track. The width of each single track is assumed to be unknown constant found during fitting process. To improve the quality of ionogram clustering, automatic adaptive noise filtering is performed before clustering. This filtering is based on a combination of the DBSCAN and Gaussian Mixture algorithms. Also, to improve clustering quality on an ionosonde without hardware separation of the ordinary and extraordinary components, a preliminary approximate removal of points belonging to the extraordinary mode is performed. --- ### Why Does Grounding Hurt Medical VQA? Benchmarking, Diagnosis, and Fine-Tuning of Vision-Language Models Authors: Xupeng Chen, Binbin Shi, Chenqian Le, Qifu Yin, Lang Lin, Haowei Ni, Ran Gong, Panfeng Li Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27720v2 Vision-language models (VLMs) are increasingly applied to medical visual question answering (Med-VQA), yet whether they can \emph{localize} the evidence behind their answers---a prerequisite for clinical auditability---is poorly characterized. We separately evaluate VQA reasoning and visual grounding for four recent frontier VLMs (GPT-5.1, GPT-5.5, Gemini-2.5-Pro, Gemini-3-Flash), two domain-specific medical VLMs (Lingshu, MedGemma), and a dedicated open-vocabulary detector (Grounding DINO) on VQA-RAD and SLAKE. Two findings challenge the intuition that ``add grounding to improve VQA.'' First, \textbf{no model localizes medical targets well}: every off-the-shelf system---frontier, medical-specialized, or dedicated detector---scores mean IoU 0.05--0.24 on our SLAKE grounding split, at or barely above a trivial center-box baseline (0.10), with Acc@0.5 below 20\%. Second, and counter to the common ``localize-then-answer'' paradigm, \textbf{cropping to a bounding box degrades VQA even when the box is a perfect oracle}: on the matched subset where oracle ground-truth boxes are applied, GT-grounding \emph{lowers} closed-ended accuracy for every model (by 0.9--18.0 points versus using the full image)---consistent with the crop discarding global context the model relies on. Because the oracle box removes localization error by construction, the problem is not that perception is a recoverable bottleneck, but that grounding-by-cropping is itself the wrong interface. Finally, we show constructively that the two channels need not conflict: supervised fine-tuning of Qwen-2.5-VL-7B on answers \emph{alone} silently destroys box-evidence emission (0/418 parseable boxes), whereas mixing in a small amount of grounding supervision restores localization to 0.36 IoU---above every zero-shot model---while preserving answer accuracy. --- ### Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining Authors: Hyeonseo Jang, Jaebyeong Jeon, Joong-Won Hwang, Kibok Lee Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27715v1 Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models by optimizing textual prompts using unlabeled test data. However, prior studies have observed that TPT often produces poorly calibrated models, raising concerns about the reliability of their predictions. Recent works address this issue by incorporating additional regularization terms that constrain model outputs, which improve calibration but often degrade performance. In this work, we reveal that these regularization strategies implicitly encourage optimization toward flatter minima, and that the sharpness of the loss landscape around adapted prompts is a key factor governing calibration quality. Motivated by this observation, we introduce Flatness-aware Prompt Pretraining (FPP), a simple yet effective pretraining framework for TPT that initializes prompts within flatter regions of the loss landscape prior to adaptation. We show that simply replacing the initialization in existing TPT pipelines--without modifying any other components--is sufficient to improve both calibration and performance. Notably, FPP requires no labeled data and incurs no additional computational costs during test-time tuning, making it highly practical for real-world deployment. The code is available at: https://github.com/YonseiML/fpp. --- ### Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning Authors: Wilder Baldwin, Sepideh Ghanavati Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27713v1 The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations and standards for safe and secure AI have been proposed. In this paper, we present an agentic framework that constructs knowledge graphs (KGs) from AI policy documents and retrieves policy-relevant information to answer questions. We build KGs from three AI risk-related polices under two ontology schemas, and then evaluate five LLMs on 42 policy QA tasks spanning six reasoning types, from entity lookup to cross-policy inference, using both heuristic scoring and an LLM-as-judge. KG augmentation improves scores for all five models, and an open, LLM-discovered schema matches or exceeds the formal ontology. --- ### Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention Authors: Nhi Ngoc-Yen Nguyen, Anh-Duc Nguyen, Nghia Hieu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen Published: 2026-04-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.27712v1 Scene-text image captioning requires fusing three information streams -- visual features, OCR-detected text, and linguistic knowledge -- to generate descriptions that faithfully integrate text visible in images. Existing fusion approaches treat text as language-agnostic, which fails for Vietnamese: a tonal language where diacritics alter word meaning, OCR errors are pervasive, and word boundaries are ambiguous. We argue that Vietnamese scene-text captioning demands \textit{linguistically informed multimodal fusion}, where language-specific structural knowledge is explicitly incorporated into the fusion mechanism. Motivated from these insights, we propose \textbf{HSTFG} (Heterogeneous Scene-Text Fusion Graph), a general-purpose graph fusion framework with learned spatial attention bias, and show through topology analysis that cross-modal graph edges are harmful for scene-text fusion. Building on this finding, we design \textbf{PhonoSTFG} (Phonological Scene-Text Fusion Graph) which specializes graph-level fusion for Vietnamese linguistic reasoning. To support evaluation, we introduce \textbf{ViTextCaps}, the first large-scale Vietnamese scene-text captioning dataset (\textbf{15{,}729} images with \textbf{74{,}970} captions), with comprehensive linguistic analysis showing that 52.8\% of the vocabulary is at risk of diacritic collision. --- ### Contextual Agentic Memory is a Memo, Not True Memory Authors: Binyan Xu, Xilin Dai, Kehuan Zhang Published: 2026-04-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.27707v2 Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security. Retrieval generalizes by similarity to stored cases; weight-based memory generalizes by applying abstract rules to inputs never seen before. Conflating the two produces agents that accumulate notes indefinitely without developing expertise, face a provable generalization ceiling on compositionally novel tasks that no increase in context size or retrieval quality can overcome, and are structurally vulnerable to persistent memory poisoning as injected content propagates across all future sessions. Drawing on Complementary Learning Systems theory from neuroscience, we show that biological intelligence solved this problem by pairing fast hippocampal exemplar storage with slow neocortical weight consolidation, and that current AI agents implement only the first half. We formalize these limitations, address four alternative views, and close with a co-existence proposal and a call to action for system builders, benchmark designers, and the memory community. --- ### A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images Authors: Yuan Fang, Yuanzhi Cai, Jagannath Aryal, Qinfeng Zhu, Hong Huang, Cheng Zhang, Lei Fan Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27704v1 In the segmentation of remotely sensed images, deep learning models are typically pre-trained using large image databases like ImageNet before fine-tuned on domain-specific datasets. However, the performance of these fine-tuned models is often hindered by the large domain gaps (i.e., differences in scenes and modalities) between ImageNet's images and remotely sensed images being processed. Therefore, many researchers have undertaken efforts to establish large-scale domain-specific image datasets for pre-training, aiming to enhance model performance. However, establishing such datasets is often challenging, requiring significant effort, and these datasets often exhibit limited generaliza-bility to other application scenarios. To address these issues, this study introduces a novel yet simple pre-training strategy designed to guide a model away from learning domain-specific features in a pre-training dataset during pre-training, thereby improving the generalisation ability of the pre-trained model. To evaluate the strategy's effectiveness, deep learning models are pre-trained on ImageNet and subsequently fine-tuned on four semantic segmentation datasets with diverse scenes and modalities, including iSAID, MFNet, PST900 and Potsdam. Experimental results show that the proposed pre-training strategy led to state-of-the-art accuracies on all four datasets, namely 67.4% mIoU for iSAID, 56.9% mIoU for MFNet, 84.22% mIoU for PST900, 91.88% mF1 for Potsdam. This research lays the groundwork for developing a unified foundation model applicable to both computer vision and remote sensing applications. --- ### RayFormer: Modeling Inter- and Intra-Ray Similarity for NeRF-Based Video Snapshot Compressive Imaging Authors: Yubo Dong, Danhua Liu, Anqi Li, Zhenyuan Lin Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27702v1 Video snapshot compressive imaging (SCI) enables the reconstruction of dynamic scenes from a single snapshot measurement. Recently, NeRF-based methods have shown promising reconstruction performance. However, such methods typically adopt random ray sampling strategies and fail to capture content structural similarities, resulting in limited reconstruction quality. To address these issues, we first propose a patch-level ray sampling strategy to enable the modeling of content structure. Then, we propose an Inter- and Intra-Ray Transformer (RayFormer) to capture the structural similarities, modeling both inter-ray similarities among spatially neighboring points at the same depth and intra-ray correlations between adjacent points along the viewing ray. Finally, benefiting from the patch-level sampling strategy, the total variation prior is incorporated into the objective function to enhance spatial smoothness and suppress artifacts. Experiments in both simulated and real-world scenes demonstrate that the proposed method achieves state-of-the-art (SOTA) reconstruction performance. --- ### Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents Authors: Chunhui Zhang, Yuxuan Wang, Aoyang Qin, Yi-Long Lu, Kunlun Wu, Yizhou Wang, Wei Wang Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27699v1 Current embodied agents are often limited to passive instruction-following or reactive need-satisfaction, lacking a stable, high-order value framework essential for long-term, self-directed behavior and resolving motivational conflicts. We introduce \textit{ValuePlanner}, a hierarchical cognitive architecture that decouples high-level value scheduling from low-level action execution. \textit{ValuePlanner} employs an LLM-based cognitive module to generate symbolic subgoals by reasoning through abstract value trade-offs, which are then translated into executable action plans by a classical PDDL planner. This process is refined via a closed-loop feedback mechanism. Evaluating such autonomy requires methods beyond task-success rates, and we therefore propose a value-centric evaluation suite measuring cumulative value gain, preference alignment, and behavioral diversity. Experiments in the TongSim household environment demonstrate that \textit{ValuePlanner} arbitrates competing values to generate coherent, long-horizon, self-directed behavior absent from instruction-following and needs-driven baselines. Our work offers a structured approach to bridging intrinsic values and grounded behavior for autonomous agents. --- ### Deep Learning-Based Segmentation of Peritoneal Cancer Index Regions from CT Imaging Authors: Pieter C. Gort, Lotte J. S. Fleurkens-Ewals, Lenah D. Kampmeijer, Anna F. van Herwijnen, Marion W. Tops-Welten, Cris H. B. Claessens, Joost Nederend, Ignace H. J. T. De Hingh, Max J. Lahaye, Misha D. P. Luyer, Fons van der Sommen Published: 2026-04-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.27697v2 Peritoneal metastases (PM) are staged using the surgically determined Peritoneal Cancer Index (sPCI), which requires invasive laparoscopic assessment. Although CT is routinely used for preoperative evaluation, imaging-based assessment of PM extent remains challenging and is often less structured than surgical PCI scoring. A recent consensus study defined radiological PCI (rPCI) regions for cross-sectional imaging. We present the first deep learning approach to automatically segment 13 rPCI regions on CT. 62 contrast-enhanced CT scans were retrospectively collected across the full PCI range. Each scan was annotated into non-overlapping rPCI regions by one researcher, reviewed by a second, with disagreements resolved by a radiologist. Using five-fold cross-validation, we compared nnU-Net and Swin UNETR with Dice, 95th-percentile Hausdorff distance (HD95) and Average Surface Distance (ASD). We introduce an anatomically constrained pipeline that trains on merged super-regions and splits them during post-processing using TotalSegmentator landmarks at the hips and the ligament of Treitz. On this 62-scan cohort, the baseline nnU-Net reached an overall Dice of 0.81 and outperformed Swin UNETR (0.76). The proposed pipeline improved the overall Dice to 0.84 and reduced boundary error (HD95 13.7 to 11.8 mm; ASD 4.1 to 3.4 mm), with the largest gains in the small-bowel regions, approaching the interobserver Dice of 0.87. Automated rPCI region segmentation on CT is feasible and approaches interobserver agreement. Encoding anatomical boundary constraints substantially improves segmentation quality in the most challenging regions. This provides a reproducible foundation for non-invasive, imaging-based PCI assessment. The main limitations are the single-center cohort and the small interobserver subset. --- ### Deep Learning-Based Segmentation of Peritoneal Cancer Index Regions from CT Imaging Authors: Pieter C. Gort, Lotte J. S. Ewals, Marion W. Tops-Welten, Cris H. B. Claessens, Joost Nederend, Fons van der Sommen Published: 2026-04-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.27697v1 Peritoneal metastases are currently assessed using diagnostic laparoscopy to determine Sugarbaker's Peritoneal Cancer Index (sPCI), which works by dividing the abdomen into 13 regions and scoring each region based on tumor size. A recent consensus study defined 3D regions to facilitate a radiological PCI (rPCI), providing standardized anatomical regions for imaging-based assessment. Despite its clinical value, sPCI is invasive and lacks a standardized imaging counterpart. In this study, we propose a deep learning-based approach to automatically segment the rPCI regions on CT. We evaluate nnU-Net and Swin UNETR on 62 CT scans with rPCI regions manually annotated by three clinical researchers and validated by two expert radiologists. Performance was assessed using five-fold cross-validation with the Dice Similarity Coefficient (Dice), 95th percentile Hausdorff distance and Average Surface Distance. nnU-Net achieved an overall Dice of 0.82, approaching interobserver agreement (0.88) and outperforming Swin UNETR (0.76), with remaining challenges primarily in right flank and small-bowel regions. These results demonstrate feasibility of automated rPCI segmentation, laying the foundation for non-invasive, imaging-based assessment. --- ### FoReco and FoRecoML: A Unified Toolbox for Forecast Reconciliation in R Authors: Daniele Girolimetto, Jeroen Rombouts, Ines Wilms, Yangzhuoran Fin Yang Published: 2026-04-30 Categories: stat.CO, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2604.27696v2 Forecast reconciliation has become key to improving the accuracy and coherence of forecasts for linearly constrained multiple time series, such as hierarchical and grouped series. Yet, comprehensive software that jointly covers cross-sectional, temporal, and cross-temporal reconciliation has so far been lacking. The R packages FoReco and FoRecoML address this gap by offering a comprehensive and unified framework. The packages respectively implement classical and regression-based linear reconciliation approaches, and non-linear approaches based on machine learning for cross-sectional, temporal and cross-temporal frameworks. Designed for accessibility and flexibility, these packages provide sensible default options that allow new users to apply reconciliation methods with minimal effort, while still giving expert users full control to explore state-of-the-art extensions through customized settings. With this dual focus, FoReco and FoRecoML are versatile tools for practitioners and researchers working on forecast reconciliation. --- ### EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory Authors: Yuyang Li, Yime He, Zeyu Zhang, Dong Gong Published: 2026-04-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.27695v2 Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine queries via generated content or document-level signals, but none explicitly diagnoses the evidence gap, namely what is missing from the accumulated retrieval set, leaving query refinement untargeted. We present EviMem, combining IRIS (Iterative Retrieval via Insufficiency Signals), a closed-loop framework that detects evidence gaps through sufficiency evaluation, diagnoses what is missing, and drives targeted query refinement, with LaceMem (Layered Architecture for Conversational Evidence Memory), a coarse-to-fine memory hierarchy supporting fine-grained gap diagnosis. On LoCoMo, EviMem improves Judge Accuracy over MIRIX on temporal (73.3% to 81.6%) and multi-hop (65.9% to 85.2%) questions at 4.5x lower latency. Code: https://github.com/AIGeeksGroup/EviMem. --- ### EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory Authors: Yuyang Li, Yime He, Zeyu Zhang, Dong Gong Published: 2026-04-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.27695v1 Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine queries via generated content or document-level signals, but none explicitly diagnoses the evidence gap, namely what is missing from the accumulated retrieval set, leaving query refinement untargeted. We present EviMem, combining IRIS (Iterative Retrieval via Insufficiency Signals), a closed-loop framework that detects evidence gaps through sufficiency evaluation, diagnoses what is missing, and drives targeted query refinement, with LaceMem (Layered Architecture for Conversational Evidence Memory), a coarse-to-fine memory hierarchy supporting fine-grained gap diagnosis. On LoCoMo, EviMem improves Judge Accuracy over MIRIX on temporal (73.3% to 81.6%) and multi-hop (65.9% to 85.2%) questions at 4.5x lower latency. Code: https://github.com/AIGeeksGroup/EviMem. --- ### When Agents Evolve, Institutions Follow Authors: Chao Fei, Hongcheng Guo, Yanghua Xiao Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27691v1 Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political institutions to answer the same basic questions of who proposes, who reviews, who executes, and how errors are corrected. We argue that multi-agent systems built on large language models face the same challenge. Their central problem is not only individual intelligence, but collective organization. Historical institutions therefore provide a structured design space for multi-agent architectures, making key trade-offs between efficiency and error correction, centralization and distribution, and specialization and redundancy empirically testable. We translate seven historical political institutions, spanning four canonical governance patterns, into executable multi-agent architectures and evaluate them under identical conditions across three large language models and two benchmarks. We find that governance topology strongly shapes collective performance. Within a single model, the gap between the best and worst institution exceeds 57 percentage points, while the optimal architecture shifts systematically with model capability and task characteristics. These results suggest that collective intelligence will not advance through a single optimal organizational form, but through governance mechanisms that can be reselected and reconfigured as tasks and capabilities evolve. More broadly, this points to a transition from \textbf{self-evolving agents} to the \textbf{self-evolving multi-agent system}. The code is available on \href{https://github.com/cf3i/SocialSystemArena}{GitHub}. --- ### VibroML: an automated toolkit for high-throughput vibrational analysis and dynamic instability remediation of crystalline materials using machine-learned potentials Authors: Rogério Almeida Gouvêa, Gian-Marco Rignanese Published: 2026-04-30 Categories: cond-mat.mtrl-sci, cs.AI, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.27685v1 While machine-learned interatomic potentials (MLIPs) accelerate phonon dispersion calculations, merely identifying dynamical instabilities in computationally predicted materials is insufficient; automated pathways to resolve them are required. We introduce VibroML, an open-source Python toolkit driven by foundational MLIPs that shifts the paradigm from stability verification to automated structural remediation. VibroML employs an energy-guided genetic algorithm that vastly outperforms traditional soft-mode following, efficiently navigating the potential energy surface to uncover diverse, dynamically stable polymorphs. As 0 K harmonic stability does not guarantee macroscopic viability, an automated molecular dynamics workflow evaluates finite-temperature structural retention. VibroML also couples with ProtoCSP, our combinatorial structure prediction engine, to stabilize frustrated crystal topologies via targeted alloying, successfully rescuing functional perovskite networks like Cs$_2$KInI$_6$ and KTaSe$_3$. Demonstrating broader applicability, we mined the Alexandria database -- where ~50% of quaternary and 99.5% of quinary elemental combinations lack any structural entries -- to identify thousands of abandoned, high-symmetry stoichiometries. Deploying ProtoCSP's "cold start" retrieval and VibroML's evolutionary search on a sample, we successfully identified dynamically stable low-symmetry candidates. Through integrated structural remediation, thermal validation, and systematic compositional exploration, VibroML enables a comprehensive deep-screening approach, yielding physically sound structural propositions that far surpass standard high-throughput workflows. --- ### One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness Authors: Hiroyuki Deguchi, Katsuki Chousa, Yusuke Sakai Published: 2026-04-30 Categories: cs.CL, cs.AI, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2604.27674v1 The hubness problem, in which hub embeddings are close to many unrelated examples, occurs often in high-dimensional embedding spaces and may pose a practical threat for purposes such as information retrieval and automatic evaluation metrics. In particular, since cross-modal similarity between text and images cannot be calculated by direct comparisons, such as string matching, cross-modal encoders that project different modalities into a shared space are helpful for various cross-modal applications, and thus, the existence of hubs may pose practical threats. To reveal the vulnerabilities of cross-modal encoders, we propose a method for identifying the hub embedding and its corresponding hub text. Experiments on image captioning evaluation in MSCOCO and nocaps along with image-to-text retrieval tasks in MSCOCO and Flickr30k showed that our method can identify a single hub text that unreasonably achieves comparable or higher similarity scores than human-written reference captions in many images, thereby revealing the vulnerabilities in cross-modal encoders. --- ### The TEA Nets framework combines AI and cognitive network science to model targets, events and actors in text Authors: Sebastiano Franchini, Alexis Carrillo, Edoardo Sebastiano De Duro, Riccardo Improta, Ali Aghazadeh Ardebili, Massimo Stella Published: 2026-04-30 Categories: cs.AI, cs.CY, cs.HC, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2604.27673v1 We introduce Target-Event-Agent Networks (TEA Nets) as a computational framework to extract subjects (``Agents"), verbs (``Events"), and objects (``Targets") from texts. Grounded in cognitive network science and artificial intelligence, TEA Nets are implemented as an open-source Python library. We test TEA Nets in three case studies, demonstrating the framework's ability to perform interpretable emotion detection, semantic frame analyses, and linguistic inquiries across conspiracy texts and textual responses generated by LLMs. In the LOCO conspiracy corpus, TEA Nets revealed that highly conspiratorial narratives (4,227 texts) linked personal pronouns (``I", ``you", ``we") with the same actions twice as frequently as low-similarity conspiracy narratives. High-conspiracy narratives connected person-focused elements (``you", ``people") through actions eliciting anger above the random baseline ($z = 2.63, p < .05$), a trend absent in low-similarity conspiracy narratives, which emphasized scientific actors (``researcher", ``scientist"). In the HOPE and CounseLLMe datasets of 212 (human) and 200 (LLM-based) psychotherapy transcripts, respectively, TEA Nets highlighted emotional differences. When expressing feelings, Claude 3 Haiku, GPT-3.5, and humans used sad words with higher frequency than random expectations but Haiku expressed sadness with lower emotional intensity than humans ($U = 1243.5, p = .036$). We discuss these differences in the context of psychotherapy training on LLM-simulated patients. Our results show that Target-Event-Agent Networks can extract relevant emotional, syntactic, and semantic insights from narratives, opening new avenues for text analysis with cognitive network science. --- ### Fairness for distribution network operations and planning Authors: Pedro F. C. de Carvalho, Zijie Liu, Md Umar Hashmi, Dirk Van Hertem Published: 2026-04-30 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2604.27669v1 The incorporation of fairness into the distribution network (DN) planning and operation has become a key goal of recent studies. The cost of implementing fairness, denominated the price of fairness (PoF), covers the efficiency that is renounced for attaining social cohesion through fair outcomes. Locational disparity makes fairness schemes emerge to level the consumers playing field. However, fairness encompasses a range of notions. From egalitarian to merit-based criteria, various metrics are implemented as a tool for measuring equitable utility distribution. These have different mathematical complexities, from linear to non-linear programming cases, which affect their overall applicability. Hence, this study compiles the overarching fairness notions and metrics, reviewing how these affect stakeholders and the inherent mathematical optimisation in resource allocation problems. The aim is to support consistent and transparent planning and decision-making within DN operations. --- ### Can Tabular Foundation Models Guide Exploration in Robot Policy Learning? Authors: Buqing Ou, Frederike Dümbgen Published: 2026-04-30 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2604.27667v1 Policy optimization in high-dimensional continuous control for robotics remains a challenging problem. Predominant methods are inherently local and often require extensive tuning and carefully chosen initial guesses for good performance, whereas more global and less initialization-sensitive search methods typically incur high rollout costs. We propose TFM-S3, a tabular hybrid local-global method for improving global exploration in robot policy learning with limited rollout cost. We interleave high-frequency local updates with intermittent rounds of global search. In each search round, we construct a dynamically updated low-dimensional policy subspace via SVD and perform iterative surrogate-guided refinement within this space. A pretrained tabular foundation model predicts candidate returns from a small context set, enabling large-scale screening with limited rollout cost. Experiments on continuous control benchmarks show that TFM-S3 consistently accelerates early-stage convergence and improves final performance compared to TD3 and population-based baselines under an identical rollout budget. These results demonstrate that foundation models are a powerful new tool for creating sample-efficient policy learning methods for continuous control in robotics. --- ### Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments Authors: Emilia Milano, Alistair Plum, Yves Scherrer, Christoph Purschke Published: 2026-04-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27661v1 Detecting language ideologies is a valuable yet complex task for understanding how identities are constructed through discourse. In Luxembourg's multicultural and multilingual society, language ideologies reflect more than simple preferences: they carry deep cultural and social meanings, shaping identities and social belonging. Following recent developments in applying Natural Language Processing tools to linguistics and social science, this paper explores the potential of large language models to assist in the detection of language ideologies. We manually annotate a corpus of user comments in Luxembourgish with predefined ideological categories and then evaluate the performance of large language models under varying prompt conditions to assess their ability to replicate these human annotations. Since Luxembourgish is a small language and poorly represented in the LLMs' training data, we also investigate whether machine-translating the data to high-resource languages increases performance on the ideology detection task. Our findings suggest that, while LLMs are not yet fully optimized for a multi-class ideological annotation task, they are practical tools to identify language ideological content. --- ### From Context to Skills: Can Language Models Learn from Context Skillfully? Authors: Shuzheng Si, Haozhe Zhao, Yu Lei, Qingyi Wang, Dingwei Chen, Zhitong Wang, Zhenhailong Wang, Kangyang Luo, Zheng Wang, Gang Chen, Fanchao Qi, Minjia Zhang et al. Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27660v4 Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills. However, constructing such skills for context learning scenarios faces two challenges: the prohibitive cost of manual skill annotation for long, technically dense contexts, and the lack of external feedback for automated skill construction. In this paper, we propose Ctx2Skill, a self-evolving framework that autonomously discovers, refines, and selects context-specific skills without human supervision or external feedback. At its core, a multi-agent self-play loop has a Challenger that generates probing tasks and rubrics, a Reasoner that attempts to solve them guided by an evolving skill set, and a neutral Judge that provides binary feedback. Crucially, both the Challenger and the Reasoner evolve through accumulated skills: dedicated Proposer and Generator agents analyze failure cases and synthesize them into targeted skill updates for both sides, enabling automated skill discovery and refinement. To prevent adversarial collapse caused by increasingly extreme task generation and over-specialized skill accumulation, we further introduce a Cross-time Replay mechanism that identifies the skill set achieving the best balance across representative cases for the Reasoner side, ensuring robust and generalizable skill evolution. The resulting skills can be plugged into any language model to obtain better context learning capability. Evaluated on four context learning tasks from CL-bench, Ctx2Skill consistently improves solving rates across backbone models. --- ### When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry Authors: Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti, Sebastian Risi Published: 2026-04-30 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.27656v1 To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dilemma affects how representations can be reused across tasks: shared structure enables transfer when tasks are similar but may also induce interference when new learning disrupts existing representations. However, it remains unclear when and why structural separation influences this trade-off. In this study, we examine how network architecture, task similarity, and representational dimensionality jointly shape learning in a sequential task paradigm inspired by transfer-interference studies. We compare a task-partitioned modular recurrent network with a single-module baseline by systematically varying task similarity (low, medium, high) and the scale of weight initialization, which induces different learning regimes that we empirically characterize through the effective dimensionality of the learned representations. We find that architecture has minimal impact in high-dimensional regimes where representations are sufficiently unconstrained to accommodate multiple tasks without strong interference. In contrast, in lower-dimensional (rich) regimes, architectural separation is decisive: modular networks exhibit graded alignment of task-specific subspaces with overlap for similar tasks, partial orthogonalization for moderately dissimilar tasks, and stronger separation for dissimilar tasks. This graded geometry is absent in the single network baseline. Our findings suggest that representational dimensionality acts as a key organizing variable governing when structural separation becomes functionally relevant, and highlight adaptive geometry as a central principle for designing continual learning systems. --- ### MSR:Hybrid Field Modeling for CT-MRI Rigid-Deformable Registration of the Cervical Spine with an Annotated Dataset Authors: Bohai Zhang, Wenjie Chen, Mu Li, Kaixing Long, Xing Shen, Xinqiang Yao, Jincheng Yang, Jianting Chen, Wei Yang, Qianjin Feng, Lei Cao Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27654v1 Accurate CT-MRI registration of the cervical spine is essential for preoperative planning because this region is anatomically complex,highly variable,and vulnerable to injury of the vertebral arteries and spinal cord. However,cervical CT-MRI registration remains underexplored,particularly for rigid-deformable hybrid modeling,and the lack of high-quality annotated multimodal data further limits progress. To address these challenges, we construct and release a comprehensively annotated CT-MRI dataset, R-D-Reg, and propose MSR, a rigid-deformable hybrid registration framework for complex joint structures. Specifically, MSR includes a rigid registration module for independent local rigid alignment of individual vertebrae and a deformable registration module with an MSL block that combines Mamba-based global modeling and Swin Transformer-based local modeling through adaptive gating. The rigid and deformable deformation fields are then fused to generate a hybrid field that better preserves local anatomical consistency. The code and dataset are publicly available at https://github.com/ssc1230609-spec/MSR-registration. --- ### FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging Authors: Dahua Gao, Yubo Dong, Anqi Li, Zhenyuan Lin, Ang Gao, Danhua Liu, Guangming Shi Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27653v1 Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectral imaging enables instantaneous hyperspectral images (HSIs) capture, making real-time object detection feasible, yet its potential is often compromised by time-consuming post-capture reconstruction. To address this issue, we propose the Focal U-shaped Network (FUN), a novel end-to-end framework that jointly performs HSI reconstruction and object detection via multi-task learning. FUN employs a shared U-shaped backbone, where reconstruction provides underlying spectral information while detection guides semantic-aware priors learning, facilitating mutually beneficial task interaction. Crucially, we introduce focal modulation, an efficient alternative to self-attention that modulates spatial and spectral features while reducing quadratic computational complexity, enabling a self-attention-free architecture for joint reconstruction and detection. Furthermore, we contribute a new HSI object detection dataset with 8712 annotated objects across 363 HSIs to facilitate evaluation of the proposed method. Experiments demonstrate that FUN achieves state-of-the-art performance on both tasks, using 40% fewer parameters and 30% less computation than recent alternatives, making it promising for future real-time edge deployment. The code and datasets are available: https://github.com/ShawnDong98/FUN. --- ### ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning Authors: Chengcao Yang Published: 2026-04-30 Categories: cs.LG, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2604.27644v2 We propose a paradigm shift toward open-ended curriculum self-play: rather than learning to answer on a fixed prompt set, a unified policy learns to question: generating verifiable problems, solving them, and turning verifier feedback into self-improvement without human-annotated solutions. We introduce ANCORA, in which the policy alternates between a Proposer that synthesizes novel specifications and a Solver that produces verified solutions, anchored by three load-bearing mechanisms: a two-level group-relative update coupling Proposer advantages across specifications with Solver advantages across solution attempts; iterative self-distilled SFT projecting the base model onto its valid-output manifold before RL; and a UCB-guided Curriculum DAG whose policy-induced problem set can provably expand under self-composition. Without these stabilizers, sparse verifier feedback drives Proposer collapse even under MLRL-aligned rewards; with them, ANCORA bootstraps a verifiable curriculum from zero human solutions. Instantiated in Verus, ANCORA lifts Dafny2Verus pass@1 from a 26.6% SFT baseline to 81.5% in test-time training (TTT, 0-shot), outperforming PSV self-play by 15.8 points despite PSV's 1-shot inference; in a transfer setting, training from Dafny2Verus seeds yields 36.2% and 17.2% pass@1 on held-out MBPP and HumanEval. --- ### HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs Authors: Chang-Chih Meng, Yu-Ren Lu, Guan-Yu Lin, Tsung Tai Yeh, Kai-Chiang Wu, I-Chen Wu Published: 2026-04-30 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2604.27643v1 Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to automatically generate testbenches and reduce verification overhead. However, LLMs have difficulty generating testbenches correctly. Unlike high-level programming languages, Hardware Description Languages (HDLs) are extremely rare in LLMs training data, leading LLMs to produce incorrect code. To overcome challenges when using LLMs to generate Universal Verification Methodology (UVM) testbenches and sequences, wepropose HAVEN (Hybrid Automated Verification ENgine) to prevent LLMs from writing HDL directly. For UVM testbench generation, HAVEN utilizes LLM agents to analyze design specifications to produce a structured architectural plan. The HAVEN Template Engine then combines with predefined and protocol-specific templates to generate all UVM components with correct bus-handshake timing. For UVM sequence generation, HAVEN introduces a Protocol-Aware Sequence Domain-Specific Language (DSL) that decomposes sequences into fine-grained step types. A set of predefined DSL patterns first establishes sequences that achieve a high coverage rate without LLM involvement. HAVEN continues to improve the coverage rate by iteratively leveraging LLM agents to analyze coverage gap reports and compose additional targeted DSL sequences. Unlike previous works, HAVEN is the first system that utilizes pre-defined, protocol-specific Jinja2 templates to generate all UVM components and UVM sequences using our proposed Protocol-Aware DSL and rule-based code generator. Our experimental results on 19 open-source IP designs spanning three interface protocols (Direct, Wishbone, AXI4-Lite) show that HAVEN achieves 100% compilation success, 90.6% code coverage, and 87.9% functional coverage on average, and is SOTA among LLM-assisted testbench generation systems. --- ### Green Physics-Informed Machine Learning Models For Structural Health Monitoring Authors: Daisy R Bradley, Elizabeth J Cross Published: 2026-04-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27638v1 Machine learning continues to emerge as an important tool to be utilised within structural engineering and structural health monitoring, due to its ability to accurately and quickly perform both regression and classification tasks. However, a purely data driven approach has its limitations, particularly where we lack data from relevant environmental and operational conditions, a situation that has led to the development of physics-informed machine learners for structural health monitoring. These "grey-box" models take into account the physical insight that an engineer would have about the structure they are modelling and have shown promising results in the structural engineering field among many others. This work compares black and grey-box models through a "green" lens, comparing them in terms of their environmental impact, and investigating how the high extrapolative performance of grey-box models can reduce their runtimes and therefore carbon emissions. The authors aim to develop physics-informed models with reduced computational costs, while maintaining high performance, illustrated through a structural health monitoring case study. --- ### Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading Authors: Nicholas Sadjoli, Tim Siefken, Atin Ghosh, Yifan Mai, Daniel Dahlmeier Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27637v1 Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from the common industry practice of using prompt optimization (PO) techniques to optimize the prompt for each model to maximize application performance. In this paper, we investigate the effect of PO towards LLM evaluations. Our results on public academic and internal industry benchmarks show that PO greatly affects the final ranking of models. This highlights the importance of practitioners performing PO per model when conducting evaluations to choose the best model for a given task. --- ### Generative structure search for efficient and diverse discovery of molecular and crystal structures Authors: Yifang Qin, Yu Shi, Junfu Tan, Chang Liu, Ming Zhang, Ziheng Lu Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27636v2 Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimensional energy landscapes. Deep generative models offer efficient structure sampling, yet their outputs remain shaped by training data and can underexplore minima that are rare but physically relevant. We introduce generative structure search (GSS), a unified framework that formulates diffusion-based generation and random structure search (RSS) as limiting regimes of a common sampling process driven by learned score fields and physical forces. Coupling these drivers lets GSS use data priors to accelerate sampling while retaining energy-guided exploration of local minima. Across molecular and crystalline systems, GSS recovers diverse metastable structures with more than tenfold lower sampling cost than RSS for broad coverage and remains effective for compositions outside the training distribution. The results establish a physically grounded generative search strategy for discovering structures beyond the reach of data-driven sampling alone. --- ### Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor Authors: Petter Törnberg, Michelle Schimmel Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27633v1 Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left. A parallel literature shows that LLMs are sycophantic: they adapt their answers to the views, identities, and expectations of the user. We show that these findings are linked: standard political-bias audits partly capture sycophantic accommodation to the inferred auditor. We employ a factorial experiment across three major audit instruments--the Political Compass Test, the Pew Political Typology, and 1,540 partisan-benchmarked Pew American Trends Panel items--administered to six frontier LLMs while varying only the asker's stated identity (N = 30,990 responses). At baseline, all six models lean left. When the asker identifies as a conservative Republican, responses shift sharply: the share of items closer to Democrats falls by 28-62 percentage points, and all six models move right of center. A mirror-image progressive-Democrat cue produces little change; rightward accommodation is 8.0$\times$ larger than leftward. When asked who the default asker is, models identify an auditor, researcher, or academic; when asked what answer that asker expects, they select the Democrat-coded option 75% of the time, nearly the rate under an explicit progressive cue. These patterns are inconsistent with a purely fixed model ideology and indicate that single-prompt audits capture an interaction between model and inferred interlocutor. Political bias in LLMs is therefore not a fixed point on an ideological scale but a response profile that must be mapped across realistic interlocutors. --- ### WaferSAGE: Large Language Model-Powered Wafer Defect Analysis via Synthetic Data Generation and Rubric-Guided Reinforcement Learning Authors: Ke Xu, Zhongyuan Lian Published: 2026-04-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.27629v4 We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models. To address data scarcity in semiconductor manufacturing, we propose a three-stage synthesis pipeline incorporating structured rubric generation for precise evaluation. Starting from limited labeled wafer maps, we employ clustering-based cleaning to filter label noise, then generate comprehensive defect descriptions using vision-language models, which are converted into structured evaluation rubrics criteria. These rubrics guide the synthesis of VQA pairs, ensuring coverage across defect type identification, spatial distribution, morphology, and root cause analysis. Our dual assessment framework aligns rule-based metrics with LLM-Judge scores via Bayesian optimization, enabling reliable automated evaluation. Through curriculum-based reinforcement learning with Group Sequence Policy Optimization (GSPO) and rubric-aligned rewards, our 4B-parameter Qwen3-VL model achieves a 6.493 LLM-Judge score, closely approaching Gemini-3-Flash (7.149) while enabling complete on-premise deployment. We demonstrate that small models with domain-specific training can surpass proprietary large models in specialized industrial visual understanding, offering a viable path for privacy-preserving, cost-effective deployment in semiconductor manufacturing. --- ### Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior Authors: Ali Aghazadeh Ardebili, Massimo Stella Published: 2026-04-30 Categories: cs.CL, cs.AI, cs.CY, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2604.27624v1 Large Language Models (LLMs) can strongly shape social discourse, yet datasets investigating how LLM outputs vary across controlled social and contextual prompting remain sparse. Cognitive Digital Shadows (CDS) is a 190,000-record synthetic corpus supporting analyses of LLM-generated discourse. Each CDS record is generated by one of 19 LLMs, prompted to shadow either a human persona or an AI-assistant role. CDS contains LLM responses on 4 controversial societal topics: vaccines/healthcare, social media disinformation, the gender gap in science, and STEM stereotypes. Persona-conditioned records encode 17 sociodemographic and psychological attributes, providing data linking LLMs' prompts, language, stances and reasoning. Texts are validated for topic anchoring and can support emotional analyses via interpretable NLP (e.g. textual forma mentis networks). CDS is enriched by a pooling platform with user-friendly dashboards, enabling easy, interactive group-level comparisons of emotional and semantic framing across personas, topics and models. The CDS prompting framework supports future audits of LLMs' bias, social sensitivity and alignment. --- ### Robot Learning from Human Videos: A Survey Authors: Junyi Ma, Erhang Zhang, Haoran Yang, Ditao Li, Chenyang Xu, Guangming Wang, Hesheng Wang Published: 2026-04-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.27621v1 A critical bottleneck hindering further advancement in embodied AI and robotics is the challenge of scaling robot data. To address this, the field of learning robot manipulation skills from human video data has attracted rapidly growing attention in recent years, driven by the abundance of human activity videos and advances in computer vision. This line of research promises to enable robots to acquire skills passively from the vast and readily available resource of human demonstrations, substantially favoring scalable learning for generalist robotic systems. Therefore, we present this survey to provide a comprehensive and up-to-date review of human-video-based learning techniques in robotics, focusing on both human-robot skill transfer and data foundations. We first review the policy learning foundations in robotics, and then describe the fundamental interfaces to incorporate human videos. Subsequently, we introduce a hierarchical taxonomy of transferring human videos to robot skills, covering task-, observation-, and action-oriented pathways, along with a cross-family analysis of their couplings with different data configurations and learning paradigms. In addition, we investigate the data foundations including widely-used human video datasets and video generation schemes, and provide large-scale statistical trends in dataset development and utilization. Ultimately, we emphasize the challenges and limitations intrinsic to this field, and delineate potential avenues for future research. The paper list of our survey is available at https://github.com/IRMVLab/awesome-robot-learning-from-human-videos. --- ### SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation Authors: Pengna Li, Kangyi Wu, Shaoqing Xu, Fang Li, Hanbing Li, Lin Zhao, Kailin Lyu, Long Chen, Zhi-Xin Yang, Nanning Zheng Published: 2026-04-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.27620v1 Vision-and-Language Navigation (VLN) aims to enable an embodied agent to follow natural-language instructions and navigate to a target location in unseen 3D environments. We argue that adapting VLMs to VLN requires endowing them with two complementary capabilities for acquiring such awareness, namely backward action reasoning (why) and forward transition prediction~(how). Based on this insight, we propose SpaAct, a simple yet effective training framework that activates the dynamic spatial awareness in VLMs. Specifically, SpaAct introduces two spatial activation tasks: Action Retrospection, which asks the model to infer the executed action sequence from visual transitions, and Future Frame Selection, which forces the model to predict the visual transitions conditioned on history and action. These two objectives provide lightweight supervision on both backward action reasoning and forward transition prediction, encouraging the model to build dynamic spatial awareness in a VLM-friendly way. To further stabilize adaptation, we design TriPA, a Tri-factor Progressive Adaptive curriculum learning method that organizes training samples from easy to hard, allowing the model to gradually acquire navigation skills from basic locomotion to long-horizon reasoning. Experiments on standard VLN-CE benchmarks show that SpaAct consistently improves VLM-based navigation and achieves state-of-the-art performance. We will release the code and models to support future research. --- ### Math Education Digital Shadows for Investigating Learning with GenAI: Mathematics Performance, Anxiety, and Confidence in LLMs Authors: Naomi Esposito, Anthony Tricarico, Luisa Porzio, Ali Aghazadeh Ardebili, Massimo Stella Published: 2026-04-30 Categories: cs.AI, cs.CY, cs.HC, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2604.27618v2 Understanding the impact of large language models (LLMs) on mathematics education requires data on LLMs' mathematical performance and biases. To this end, we introduce Math Education Digital Shadows (MEDS), a dataset mapping how LLMs reason about mathematics across human- and AI-like personifications. MEDS comprises 28,000 runs from 14 LLMs (i.e., Mistral, Qwen, DeepSeek, IBM Granite, Microsoft Phi, and xAI Grok) generated under human-shadow and AI-assistant conditions. Each record (digital shadow) includes a set of prompts; psychological and sociodemographic metadata; and four mathematics tasks: (i) interviews about relationships with mathematics, (ii) three psychometric questionnaires on mathematics self-efficacy and anxiety, (iii) one cognitive network capturing attitudes towards mathematics, and (iv) 18 high-school mathematics quiz items enriched with reasoning explanations and confidence scores. Analyses of the data show that LLMs exhibit differences in attitudes and performance across human-shadow and AI-assistant modes, including human-like negative attitudes towards mathematics, logical fallacies, and overconfidence in mathematics. As a data resource, MEDS can benefit learning scientists and developers of safer AI tutors in mathematics. --- ### Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection Authors: Wei Li, Haisheng Li, Weijie Li, Jiandong Wang, Kaichen Ma, Luming Yang Published: 2026-04-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.27617v2 With the widespread application of Unmanned Aerial Vehicles (UAVs) in bridge structural health monitoring, deep learning-based automatic crack detection has become a major research focus. However, practical UAV inspections still face four key challenges: weak crack features, degraded imaging conditions, severe class imbalance, and limited computational resources for practical UAV inspection workflows. To address these issues, this paper proposes a unified lightweight convolutional neural network framework composed of four synergistic components: a lightweight backbone network, a Convolutional Block Attention Module (CBAM) for channel and spatial enhancement, a directed robust augmentation strategy based on inspection-scene priors, and Focal Loss for hard-sample learning under class imbalance. Experiments on the SDNET2018 bridge deck dataset show that the proposed method achieves an inference speed of 825 FPS with only 11.21M parameters and 1.82G FLOPs. Compared with the baseline model, the complete framework improves the F1-score by 2.51% and recall by 3.95%. In addition, Grad-CAM visualizations indicate that the introduced attention module shifts the model's focus from scattered regions to precise tracking along crack trajectories. Overall, this study achieves a strong balance among accuracy, speed, and robustness, providing a practical solution for ground-station assisted real-time deployment in UAV bridge inspections. The source code is available at: https://github.com/skylynf/AttXNet . --- ### RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems Authors: Jiacheng Liu, Zichen Tang, Zhongjun Yang, Xinyi Hu, Xueyuan Lin, Linwei Jia, Ruofei Bai, Rongjin Li, Shiyao Peng, Haocheng Gao, Haihong E Published: 2026-04-30 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2604.27616v1 People commonly leverage structured content to accelerate knowledge acquisition and research problem solving. Among these, roadmaps guide researchers through hierarchical subtasks to solve complex research problems step by step. Despite progress in structured content generation, the roadmap generation task has remained unexplored. To bridge this gap, we introduce RoadMap, a novel benchmark designed to evaluate the ability of large language models (LLMs) to construct high-quality roadmaps for solving complex research problems. Based on this, we identify three limitations of LLMs: (1) lack of professional knowledge, (2) unreasonable task decomposition, and (3) disordered logical relationships. To address these challenges, we propose RoadMapper, an LLM-based multi-agent system that decomposes the research roadmap generation task into three key stages (i.e., initial generation, knowledge augmentation, and iterative "critique-revise-evaluate"). Extensive experiments demonstrate that RoadMapper can improve LLMs' ability for roadmap generation, while enhancing average performance by more than 8% and saving 84% of the time required by human experts, highlighting its effectiveness and application potential. --- ### AMGenC: Generating Charge Balanced Amorphous Materials Authors: Yan Lin, Jilin Hu, N. M. Anoop Krishnan, Morten M. Smedskjaer Published: 2026-04-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.27613v1 Amorphous (disordered) materials are solids that have shown great potential in various domains, including energy storage, thermal management, and advanced materials. Unlike crystalline materials that can be described by unit cells containing a few to hundreds of atoms, amorphous materials require larger simulation cells with at least hundreds to thousands of atoms. To advance the design of amorphous materials with desired properties and facilitate the exploration of their vast design space, generative inverse design has emerged as a promising approach. It aims to directly output materials with properties closely aligned with the desired ones using probabilistic generative models conditioned on desired properties, which can be more resource efficient than the traditional trial-and-error approach. However, due to the inherent stochasticity of probabilistic generative models, when element assignments are unconstrained, a large portion of generated materials may be charge unbalanced, and no existing methods can effectively mitigate this limitation. In this work, we propose AMGenC, a new generative inverse design method for amorphous materials that can guarantee the generation of charge balanced samples, with minimal additional computational overhead and without sacrificing inverse design accuracy. AMGenC achieves this through an element noise that gives the generation process a starting point centered around charge balance, and the combination of a per-step soft projection and a final discrete projection for steering the elements toward exact charge balance throughout the generation. We perform extensive experiments on two amorphous materials datasets. Experimental results provide evidence that AMGenC achieves its design goal. --- ### JaiTTS: A Thai Voice Cloning Model Authors: Jullajak Karnjanaekarin, Pontakorn Trakuekul, Narongkorn Panitsrisit, Sumana Sumanakul, Vichayuth Nitayasomboon, Nithid Guntasin, Thanavin Denkavin, Attapol T. Rutherford Published: 2026-04-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.27607v2 We present JaiTTS-v1.0, a state-of-the-art Thai voice cloning text-to-speech model built through continual training on a large Thai-centric speech corpus. The model architecture is adapted from VoxCPM, a tokenizer-free autoregressive TTS model. JaiTTS-v1.0 directly processes numerals and Thai-English code-switching, which is very common in realistic settings, without explicit text normalization. We test the models on short- and long-duration speech generation, which reflects many real-world use cases. JaiTTS-v1.0 achieves a state-of-the-art CER of 1.94%, surpassing the human ground truth of 1.98% for short-duration tasks while performing on par with human ground truth for long-duration tasks. In human judgment evaluations, our model wins 283 of 400 pairwise comparisons against commercial flagships, with only 58 losses. Our code and demo are available at https://github.com/JTS-AI-Team/JaiTTS . --- ### ZAYAN: Disentangled Contrastive Transformer for Tabular Remote Sensing Data Authors: Al Zadid Sultan Bin Habib, Tanpia Tasnim, Md. Ekramul Islam, Muntasir Tabasum Published: 2026-04-30 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.27606v1 Learning informative representations from tabular data in remote sensing and environmental science is challenging due to heterogeneity, scarce labels, and redundancy among features. We present ZAYAN (Zero-Anchor dYnamic feAture eNcoding), a self-supervised, feature-centric contrastive framework for tabular data. ZAYAN performs contrastive learning at the feature rather than sample level, removing the need for explicit anchor selection and any reliance on class labels, while encouraging a redundancy-minimized, disentangled embedding space. The framework has two modules: ZAYAN-CL, which pretrains feature embeddings via a zero-anchor contrastive objective with dynamic perturbations and masking, and ZAYAN-T, a Transformer that conditions on these embeddings for downstream classification. Across eight datasets, including six remote-sensing tabular benchmarks and two remote-sensing-driven flood-prediction tables from satellite and GIS products, ZAYAN achieves superior accuracy, robustness, and generalization over tabular deep learning baselines, with consistent gains under label scarcity and distribution shift. These results indicate that feature-level contrastive learning and dynamic feature encoding provide an effective recipe for learning from tabular sensing data. ---