# Research Papers — 2026-02 · bundle page 54 of 210 > Full-text markdown of papers #2651–2700 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/54 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/53.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/55.md) ### Beyond Description: A Multimodal Agent Framework for Insightful Chart Summarization Authors: Yuhang Bai, Yujuan Ding, Shanru Lin, Wenqi Fan Published: 2026-02-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.18731v1 Chart summarization is crucial for enhancing data accessibility and the efficient consumption of information. However, existing methods, including those with Multimodal Large Language Models (MLLMs), primarily focus on low-level data descriptions and often fail to capture the deeper insights which are the fundamental purpose of data visualization. To address this challenge, we propose Chart Insight Agent Flow, a plan-and-execute multi-agent framework effectively leveraging the perceptual and reasoning capabilities of MLLMs to uncover profound insights directly from chart images. Furthermore, to overcome the lack of suitable benchmarks, we introduce ChartSummInsights, a new dataset featuring a diverse collection of real-world charts paired with high-quality, insightful summaries authored by human data analysis experts. Experimental results demonstrate that our method significantly improves the performance of MLLMs on the chart summarization task, producing summaries with deep and diverse insights. --- ### MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment Authors: Sagarika Banerjee, Tangatar Madi, Advait Swaminathan, Nguyen Dao Minh Anh, Shivank Garg, Kevin Zhu, Vasu Sharma Published: 2026-02-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.18729v1 Fine-grained image-caption alignment is crucial for vision-language models (VLMs), especially in socially critical contexts such as identifying real-world risk scenarios or distinguishing cultural proxies, where correct interpretation hinges on subtle visual or linguistic clues and where minor misinterpretations can lead to significant real-world consequences. We present MiSCHiEF, a set of two benchmarking datasets based on a contrastive pair design in the domains of safety (MiS) and culture (MiC), and evaluate four VLMs on tasks requiring fine-grained differentiation of paired images and captions. In both datasets, each sample contains two minimally differing captions and corresponding minimally differing images. In MiS, the image-caption pairs depict a safe and an unsafe scenario, while in MiC, they depict cultural proxies in two distinct cultural contexts. We find that models generally perform better at confirming the correct image-caption pair than rejecting incorrect ones. Additionally, models achieve higher accuracy when selecting the correct caption from two highly similar captions for a given image, compared to the converse task. The results, overall, highlight persistent modality misalignment challenges in current VLMs, underscoring the difficulty of precise cross-modal grounding required for applications with subtle semantic and visual distinctions. --- ### Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering Authors: Mingdong Lu, Zhikui Chen, Meng Liu, Shubin Ma, Zhengyang Tang Published: 2026-02-21 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.18728v2 Unsupervised multi-view clustering (MVC) aims to partition data into meaningful groups by leveraging complementary information from multiple views without labels, yet a central challenge is to obtain a reliable shared structural signal to guide representation learning and cross-view alignment under view discrepancy and noise. Existing approaches often rely on magnitude-only affinities or early pseudo targets, which can be unstable when different views induce relations with comparable strengths but contradictory directional tendencies, thereby distorting the global spectral geometry and degrading clustering. In this paper, we propose Phase-Consistent Magnetic Spectral Learning for MVC: we derive a confidence-directed cross-view flow from anchor assignments, encode it as a phase term, and combine it with a nonnegative magnitude backbone to form a complex-valued magnetic affinity, extract a stable shared spectral signal via a Hermitian magnetic Laplacian, and use it as structured self-supervision to guide unsupervised multi-view representation learning and clustering. To obtain robust inputs for spectral extraction at scale, we construct a compact shared structure with anchor-based high-order consensus modeling and apply a lightweight refinement to suppress noisy or inconsistent relations. Experiments on ten public benchmarks show that our method achieves the best result on 22 of 30 dataset-metric combinations and ranks among the top two on 27 combinations, demonstrating strong and broadly consistent performance against classical and recent MVC baselines. --- ### Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering Authors: Mingdong Lu, Zhikui Chen, Meng Liu, Shubin Ma, Liang Zhao Published: 2026-02-21 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.18728v1 Unsupervised multi-view clustering (MVC) aims to partition data into meaningful groups by leveraging complementary information from multiple views without labels, yet a central challenge is to obtain a reliable shared structural signal to guide representation learning and cross-view alignment under view discrepancy and noise. Existing approaches often rely on magnitude-only affinities or early pseudo targets, which can be unstable when different views induce relations with comparable strengths but contradictory directional tendencies, thereby distorting the global spectral geometry and degrading clustering. In this paper, we propose \emph{Phase-Consistent Magnetic Spectral Learning} for MVC: we explicitly model cross-view directional agreement as a phase term and combine it with a nonnegative magnitude backbone to form a complex-valued magnetic affinity, extract a stable shared spectral signal via a Hermitian magnetic Laplacian, and use it as structured self-supervision to guide unsupervised multi-view representation learning and clustering. To obtain robust inputs for spectral extraction at scale, we construct a compact shared structure with anchor-based high-order consensus modeling and apply a lightweight refinement to suppress noisy or inconsistent relations. Extensive experiments on multiple public multi-view benchmarks demonstrate that our method consistently outperforms strong baselines. --- ### WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation Authors: Bo Liang, Chen Gong, Haobo Wang, Qirui Liu, Rungui Zhou, Fengzhi Shao, Yubo Wang, Wei Gao, Kaichen Zhou, Guolong Cui, Chenren Xu Published: 2026-02-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18726v2 Millimeter-wave Human Pose Estimation (mmWave HPE) promises privacy but suffers from poor generalization under distribution shifts. We demonstrate that brute-force data scaling is ineffective for out-of-distribution (OOD) robustness; efficiency and coverage are the true bottlenecks. To address this, we introduce WiCompass, a coverage-aware data-collection framework. WiCompass leverages large-scale motion-capture corpora to build a universal pose space ``oracle'' that quantifies dataset redundancy and identifies underrepresented motions. Guided by this oracle, WiCompass employs a closed-loop policy to prioritize collecting informative missing samples. Experiments show that WiCompass consistently improves OOD accuracy at matched budgets and exhibits superior scaling behavior compared to conventional collection strategies. By shifting focus from brute-force scaling to coverage-aware data acquisition, this work offers a practical path toward robust mmWave sensing. --- ### Task-Aware Exploration via a Predictive Bisimulation Metric Authors: Dayang Liang, Ruihan Liu, Lipeng Wan, Yunlong Liu, Bo An Published: 2026-02-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.18724v1 Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic exploration, many methods either assume access to low-dimensional states or lack task-aware exploration strategies, thereby rendering them fragile in visual domains. To bridge this gap, we present TEB, a Task-aware Exploration approach that tightly couples task-relevant representations with exploration through a predictive Bisimulation metric. Specifically, TEB leverages the metric not only to learn behaviorally grounded task representations but also to measure behaviorally intrinsic novelty over the learned latent space. To realize this, we first theoretically mitigate the representation collapse of degenerate bisimulation metrics under sparse rewards by internally introducing a simple but effective predicted reward differential. Building on this robust metric, we design potential-based exploration bonuses, which measure the relative novelty of adjacent observations over the latent space. Extensive experiments on MetaWorld and Maze2D show that TEB achieves superior exploration ability and outperforms recent baselines. --- ### ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models Authors: Zefang Liu, Chenyang Zhu, Sangwoo Cho, Shi-Xiong Zhang Published: 2026-02-21 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2602.18721v1 Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a framework for iterative pseudo-label refinement that integrates an instruction-tuned, audio-aware large language model (LLM) into the self-training loop. Unlike conventional text-based correctors, our approach conditions the LLM on both the ASR hypothesis and the source audio, allowing it to recover phonetically accurate transcripts even from severe recognition errors. These refined pseudo-labels serve as high-fidelity targets for fine-tuning the ASR model in an iterative cycle. Experimental results across diverse benchmarks demonstrate that ReHear effectively mitigates error propagation, consistently outperforming both supervised and pseudo-labeling baselines. --- ### Subtle Motion Blur Detection and Segmentation from Static Image Artworks Authors: Ganesh Samarth, Sibendu Paul, Solale Tabarestani, Caren Chen Published: 2026-02-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18720v1 Streaming services serve hundreds of millions of viewers worldwide, where visual assets such as thumbnails, box art, and cover images are critical for engagement. Subtle motion blur remains a pervasive quality issue, reducing visual clarity and negatively affecting user trust and click-through rates. However, motion blur detection from static images is underexplored, as existing methods and datasets focus on severe blur and lack fine-grained pixel-level annotations needed for quality-critical applications. Benchmarks such as GOPRO and NFS are dominated by strong synthetic blur and often contain residual blur in their sharp references, leading to ambiguous supervision. We propose SMBlurDetect, a unified framework combining high-quality motion blur specific dataset generation with an end-to-end detector capable of zero-shot detection at multiple granularities. Our pipeline synthesizes realistic motion blur from super high resolution aesthetic images using controllable camera and object motion simulations over SAM segmented regions, enhanced with alpha-aware compositing and balanced sampling to generate subtle, spatially localized blur with precise ground truth masks. We train a U-Net based detector with ImageNet pretrained encoders using a hybrid mask and image centric strategy incorporating curriculum learning, hard negatives, focal loss, blur frequency channels, and resolution aware augmentation.Our method achieves strong zero-shot generalization, reaching 89.68% accuracy on GoPro (vs 66.50% baseline) and 59.77% Mean IoU on CUHK (vs 9.00% baseline), demonstrating 6.6x improvement in segmentation. Qualitative results show accurate localization of subtle blur artifacts, enabling automated filtering of low quality frames and precise region of interest extraction for intelligent cropping. --- ### Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space Authors: Kyurae Kim, Qiang Fu, Yi-An Ma, Jacob R. Gardner, Trevor Campbell Published: 2026-02-21 Categories: stat.ML, cs.LG, math.OC, stat.CO arXiv: https://arxiv.org/abs/2602.18718v2 For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example, Wasserstein VI (WVI) and black-box VI (BBVI) perform gradient descent in measure space (Bures-Wasserstein space) and parameter space, respectively. Previously, for the Gaussian variational family, convergence guarantees for WVI have shown superiority over existing results for black-box VI with the reparametrization gradient, suggesting the measure space approach might provide some unique benefits. In this work, however, we close this gap by obtaining identical state-of-the-art iteration complexity guarantees for both. In particular, we identify that WVI's superiority stems from the specific gradient estimator it uses, which BBVI can also leverage with minor modifications. The estimator in question is usually associated with Price's theorem and utilizes second-order information (Hessians) of the target log-density. We will refer to this as Price's gradient. On the flip side, WVI can be made more widely applicable by using the reparametrization gradient, which requires only gradients of the log-density. We empirically demonstrate that the use of Price's gradient is the major source of performance improvement. --- ### NeXt2Former-CD: Efficient Remote Sensing Change Detection with Modern Vision Architectures Authors: Yufan Wang, Sokratis Makrogiannis, Chandra Kambhamettu Published: 2026-02-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18717v1 State Space Models (SSMs) have recently gained traction in remote sensing change detection (CD) for their favorable scaling properties. In this paper, we explore the potential of modern convolutional and attention-based architectures as a competitive alternative. We propose NeXt2Former-CD, an end-to-end framework that integrates a Siamese ConvNeXt encoder initialized with DINOv3 weights, a deformable attention-based temporal fusion module, and a Mask2Former decoder. This design is intended to better tolerate residual co-registration noise and small object-level spatial shifts, as well as semantic ambiguity in bi-temporal imagery. Experiments on LEVIR-CD, WHU-CD, and CDD datasets show that our method achieves the best results among the evaluated methods, improving over recent Mamba-based baselines in both F1 score and IoU. Furthermore, despite a larger parameter count, our model maintains inference latency comparable to SSM-based approaches, suggesting it is practical for high-resolution change detection tasks. --- ### Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation Authors: Hoseong Jung, Sungil Son, Daesol Cho, Jonghae Park, Changhyun Choi, H. Jin Kim Published: 2026-02-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.18716v1 Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex dynamics and represents the problem as a hybrid action space unifying discrete resource usage and continuous maneuvers. However, prior works on hybrid action space have not sufficiently captured the causal dependencies between resource usage and maneuvers. They have also overlooked the multi-modal nature of tactical decisions, both of which are critical in fast-evolving scenarios. In this paper, we propose TART, a Temporal Action Representation learning framework for Tactical resource control and subsequent maneuver generation. TART leverages contrastive learning based on a mutual information objective, designed to capture inherent temporal dependencies in resource-maneuver interactions. These learned representations are quantized into discrete codebook entries that condition the policy, capturing recurring tactical patterns and enabling multi-modal and temporally coherent behaviors. We evaluate TART in two domains where resource deployment is critical: (i) a maze navigation task where a limited budget of discrete actions provides enhanced mobility, and (ii) a high-fidelity air combat simulator in which an F-16 agent operates weapons and defensive systems in coordination with flight maneuvers. Across both domains, TART consistently outperforms hybrid-action baselines, demonstrating its effectiveness in leveraging limited resources and producing context-aware subsequent maneuvers. --- ### A Data-Driven Method to Map the Functional Organisation of Human Brain White Matter Authors: Yifei Sun, James M. Shine, Robert D. Sanders, Robin F. H. Cash, Sharon L. Naismith, Fernando Calamante, Jinglei Lv Published: 2026-02-21 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2602.18715v1 The white matter of the brain is organised into axonal bundles that support long-range neural communication. Although diffusion MRI (dMRI) enables detailed mapping of these pathways through tractography, how white matter pathways directly facilitate large-scale neural synchronisation remains poorly understood. We developed a data-driven framework that integrates dMRI and functional MRI (fMRI) to model the dynamic coupling supported by white matter tracks. Specifically, we employed track dynamic functional connectivity (Track-DFC) to characterise functional coupling of remote grey matter connected by individual white matter tracks. Using independent component analysis followed by k-medoids clustering, we derived functionally-coherent clusters of white matter tracks from the Human Connectome Project young adult cohort. When applied to the HCP ageing cohort, these clusters exhibited widespread age-related declines in both functional coupling strength and temporal variability. Importantly, specific clusters encompassing pathways linking control, default mode, attention, and visual systems significantly mediated the relationship between age and cognitive performance. Together, these findings depict the functional organisation of white matter tracks and provide a powerful tool to study brain ageing and cognitive decline. --- ### HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing Authors: Ahmed Akl, Abdelwahed Khamis, Ali Cheraghian, Zhe Wang, Sara Khalifa, Kewen Wang Published: 2026-02-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18711v1 Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal understanding capabilities, yet they remain prone to object hallucination, where models describe non-existent objects or attribute incorrect factual information, raising serious concerns for reliable real-world deployment. While fine-tuning is a commonly adopted mitigation strategy, its high computational cost and practical difficulty motivate the need for training-free alternatives, among which model editing has recently emerged as a promising direction. However, indiscriminate editing risks disrupting the rich implicit knowledge encoded in pre-trained LVLMs, leading to a fundamental question: how much intervention is necessary at each layer to suppress hallucinations while preserving pre-trained knowledge? To address this question, we present a systematic analysis of LVLM decoders built on three widely used large language model backbones-Qwen, LLaMA, and Vicuna-revealing clear layer-wise differences in susceptibility to object hallucination. Building on these insights, we introduce the Hallucination Insensitivity Score (HIS), a principled metric that quantifies each layer's sensitivity to hallucination and provides guidance for targeted intervention. Leveraging HIS, we propose Hallucination Insensitivity Model Editing (HIME), a simple yet effective layer-adaptive weight editing approach that selectively modifies latent features to suppress hallucinations while preserving pre-trained knowledge. Extensive experiments demonstrate that HIME reduces hallucinations by an average of 61.8% across open-ended generation benchmarks, including CHAIR, MME, and GPT-4V-aided evaluation, without introducing additional parameters, inference-time latency, or computational overhead. --- ### Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse Authors: Martin Bertran, Riccardo Fogliato, Zhiwei Steven Wu Published: 2026-02-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18710v2 Empirical conclusions depend not only on data but on analytic decisions made throughout the research process. Many-analyst studies have quantified this dependence: independent teams testing the same hypothesis on the same dataset regularly reach conflicting conclusions. But such studies require costly human coordination and are rarely conducted. We show that fully autonomous AI analysts built on large language models (LLMs) can, cheaply and at scale, replicate the structured analytic diversity observed in human multi-analyst studies. In our framework, each AI analyst independently executes a complete analysis pipeline on a fixed dataset and hypothesis; a separate AI auditor screens every run for methodological validity. Across three datasets spanning distinct domains, AI analyst-produced analyses exhibit substantial dispersion in effect sizes, $p$-values, and conclusions. This dispersion can be traced to identifiable analytic choices in preprocessing, model specification, and inference that vary systematically across LLM and persona conditions. Critically, the outcomes are \emph{steerable}: reassigning the analyst persona or LLM shifts the distribution of results even among methodologically sound runs. These results highlight a central challenge for AI-automated empirical science: when defensible analyses are cheap to generate, evidence becomes abundant and vulnerable to selective reporting. Yet the same capability that creates this risk may also help address it: treating analyst results as distributions makes analytic uncertainty visible, and deploying AI analysts against a published specification can reveal how much disagreement stems from underspecified design choices. Taken together, our results motivate a new transparency norm: AI-generated analyses should be accompanied by multiverse-style reporting and full disclosure of the prompts used, on par with code and data. --- ### IRIS-SLAM: Unified Geo-Instance Representations for Robust Semantic Localization and Mapping Authors: Tingyang Xiao, Liu Liu, Wei Feng, Zhengyu Zou, Xiaolin Zhou, Wei Sui, Hao Li, Dingwen Zhang, Zhizhong Su Published: 2026-02-21 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.18709v4 Geometry foundation models have significantly advanced dense geometric SLAM, yet existing systems often lack deep semantic understanding and robust loop closure capabilities. Meanwhile, contemporary semantic mapping approaches are frequently hindered by decoupled architectures and fragile data association. We propose IRIS-SLAM, a novel RGB semantic SLAM system that leverages unified geometric-instance representations derived from an instance-extended foundation model. By extending a geometry foundation model to concurrently predict dense geometry and cross-view consistent instance embeddings, we enable a semantic-synergized association mechanism and instance-guided loop closure detection. Our approach effectively utilizes viewpoint-agnostic semantic anchors to bridge the gap between geometric reconstruction and open-vocabulary mapping. Experimental results demonstrate that IRIS-SLAM significantly outperforms state-of-the-art methods, particularly in map consistency and wide-baseline loop closure reliability. --- ### EDU-MATRIX: A Society-Centric Generative Cognitive Digital Twin Architecture for Secondary Education Authors: Wenjing Zhai, Jianbin Zhang, Tao Liu Published: 2026-02-21 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2602.18705v1 Existing multi-agent simulations often suffer from the "Agent-Centric Paradox": rules are hard-coded into individual agents, making complex social dynamics rigid and difficult to align with educational values. This paper presents EDU-MATRIX, a society-centric generative cognitive digital twin architecture that shifts the paradigm from simulating "people" to simulating a "social space with a gravitational field." We introduce three architectural contributions: (1) An Environment Context Injection Engine (ECIE), which acts as a "social microkernel," dynamically injecting institutional rules (Gravity) into agents based on their spatial-temporal coordinates; (2) A Modular Logic Evolution Protocol (MLEP), where knowledge exists as "fluid" capsules that agents synthesize to generate new paradigms, ensuring high dialogue consistency (94.1%); and (3) Endogenous Alignment via Role-Topology, where safety constraints emerge from the agent's position in the social graph rather than external filters. Deployed as a digital twin of a secondary school with 2,400 agents, the system demonstrates how "social gravity" (rules) and "cognitive fluids" (knowledge) interact to produce emergent, value-aligned behaviors (Social Clustering Coefficient: 0.72). --- ### Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding Authors: Houlun Chen, Xin Wang, Guangyao Li, Yuwei Zhou, Yihan Chen, Jia Jia, Wenwu Zhu Published: 2026-02-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.18702v1 Long video understanding is challenging due to rich and complicated multimodal clues in long temporal range.Current methods adopt reasoning to improve the model's ability to analyze complex video clues in long videos via text-form reasoning.However,the existing literature suffers from the fact that the text-only reasoning under fixed video context may exacerbate hallucinations since detailed crucial clues are often ignored under limited video context length due to the temporal redundancy of long videos.To address this gap,we propose Video-TwG,a curriculum reinforced framework that employs a novel Think-with-Grounding paradigm,enabling video LLMs to actively decide when to perform on-demand grounding during interleaved text-video reasoning, selectively zooming into question-relevant clips only when necessary.Video-TwG can be trained end-to-end in a straightforward manner, without relying on complex auxiliary modules or heavily annotated reasoning tracesIn detail,we design a Two-stage Reinforced Curriculum Strategy, where the model first learns think-with-grounding behavior on a small short-video GQA dataset with grounding labels,and then scales to diverse general QA data with videos of diverse domains to encourage generalization. Further, to handle complex think-with-grounding reasoning for various kinds of data,we propose TwG-GRPO algorithm which features the fine-grained grounding reward, self-confirmed pseudo reward and accuracy-gated mechanism.Finally,we propose to construct a new TwG-51K dataset that facilitates training. Experiments on Video-MME, LongVideoBench, and MLVU show that Video-TwG consistently outperforms strong LVU baselines.Further ablation validates the necessity of our Two-stage Reinforced Curriculum Strategy and shows our TwG-GRPO better leverages diverse unlabeled data to improve grounding quality and reduce redundant groundings without sacrificing QA performance. --- ### Watermarking LLM Agent Trajectories Authors: Wenlong Meng, Chen Gong, Terry Yue Zhuo, Fan Zhang, Kecen Li, Zheng Liu, Zhou Yang, Chengkun Wei, Wenzhi Chen Published: 2026-02-21 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2602.18700v2 LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and manual filtering. Despite the high cost of creating these datasets, existing literature has overlooked copyright protection for LLM agent trajectories. This gap leaves creators vulnerable to data theft and makes it difficult to trace misuse or enforce ownership rights. This paper introduces ActHook, the first watermarking method tailored for agent trajectory datasets. Inspired by hook mechanisms in software engineering, ActHook embeds hook actions that are activated by a secret input key and do not alter the original task outcome. Like software execution, LLM agents operate sequentially, allowing hook actions to be inserted at decision points without disrupting task flow. When the activation key is present, an LLM agent trained on watermarked trajectories can produce these hook actions at a significantly higher rate, enabling reliable black-box detection. Experiments on mathematical reasoning, web searching, and software engineering agents show that ActHook achieves an average detection AUC of 94.3 on Qwen-2.5-Coder-7B while incurring negligible performance degradation. --- ### Semantic Substrate Dynamics Theory: An Operator-Theoretic Framework for Geometric Semantic Drift Authors: Stephen Russell Published: 2026-02-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.18699v2 Studies of semantic drift report heterogeneous signals, including embedding displacement, neighbor change, distributional divergence, and recursive trajectory instability, without a shared account that relates them. Semantic Substrate Dynamics Theory (SSDT) treats these signals as observables of one time-indexed substrate, St = (X, dt, Pt), that couples embedding geometry to a local diffusion kernel. The contribution is commensurability with a mechanism layer: the substrate separates within-basin churn from basin crossing, recursion-induced instability, and intervention-order effects, distinctions that a single detection score does not recover. Coarse Ricci curvature functions as a dense structural descriptor of basin and bridge geometry across the graph, and bridge mass, a node-level aggregate of incident negative curvature, functions as a sparse descriptor of the genuine bridge structure that is typically uncommon in embedding graphs. For recursive generation, node displacement relative to an origin decomposes into a radial component and a tangential component, which separates bounded departure from continuing reinterpretation. The predictions are stated in falsifiable form with a pre-declared rejection rule, and the predicted leading indicator of future rewiring is a local density statistic rather than the curvature aggregate. This manuscript provides the formal model, the assumptions, the observable roles, and the test contracts; empirical performance is deferred. --- ### Semantic Substrate Theory: An Operator-Theoretic Framework for Geometric Semantic Drift Authors: Stephen Russell Published: 2026-02-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.18699v1 Most semantic drift studies report multiple signals e.g., embedding displacement, neighbor changes, distributional divergence, and recursive trajectory instability, without a shared explanatory theory that relates them. This paper proposes a formalization of these signals in one time-indexed substrate, $S_t=(X,d_t,P_t)$, combining embedding geometry with local diffusion. Within this substrate, node-level neighborhood drift measures changes in local conditional distributions, coarse Ricci curvature measures local contractivity of semantic diffusion, and recursive drift probes stability of iterated semantic operators. This manuscript specifies the formal model, assumptions, and tests that can refute the model. Herein, the paper introduces bridge mass, a node-level aggregate of incident negative curvature, as a predictor of future neighborhood rewiring. This paper provides the theory and test contracts; empirical performance is deferred to subsequent studies. --- ### Deep LoRA-Unfolding Networks for Image Restoration Authors: Xiangming Wang, Haijin Zeng, Benteng Sun, Jiezhang Cao, Kai Zhang, Qiangqiang Shen, Yongyong Chen Published: 2026-02-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18697v1 Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging reconstruction, compressive sensing and super-resolution.It unfolds the iterative optimization steps into a stack of sequentially linked blocks.Each block consists of a Gradient Descent Module (GDM) and a Proximal Mapping Module (PMM) which is equivalent to a denoiser from a Bayesian perspective, operating on Gaussian noise with a known level.However, existing DUNs suffer from two critical limitations: (i) their PMMs share identical architectures and denoising objectives across stages, ignoring the need for stage-specific adaptation to varying noise levels; and (ii) their chain of structurally repetitive blocks results in severe parameter redundancy and high memory consumption, hindering deployment in large-scale or resource-constrained scenarios.To address these challenges, we introduce generalized Deep Low-rank Adaptation (LoRA) Unfolding Networks for image restoration, named LoRun, harmonizing denoising objectives and adapting different denoising levels between stages with compressed memory usage for more efficient DUN.LoRun introduces a novel paradigm where a single pretrained base denoiser is shared across all stages, while lightweight, stage-specific LoRA adapters are injected into the PMMs to dynamically modulate denoising behavior according to the noise level at each unfolding step.This design decouples the core restoration capability from task-specific adaptation, enabling precise control over denoising intensity without duplicating full network parameters and achieving up to $N$ times parameter reduction for an $N$-stage DUN with on-par or better performance.Extensive experiments conducted on three IR tasks validate the efficiency of our method. --- ### Insertion Based Sequence Generation with Learnable Order Dynamics Authors: Dhruvesh Patel, Benjamin Rozonoyer, Gaurav Pandey, Tahira Naseem, Ramón Fernandez Astudillo, Andrew McCallum Published: 2026-02-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18695v2 Existing insertion-based masked diffusion models that generate sequences by interleaving token insertion with unmasking use fixed schedules that are not dependent on the data. For structured sequences like graphs and molecules, learning data-dependent generation orders can improve generation quality by reducing uncertainty over the action space. We propose LoFlexMDM, an insertion-based masked diffusion model with learnable order dynamics that learns data-dependent insertion and unmasking rates. We generalize the discrete flow matching framework to work with variable-length sequences, propose a tractable schedule parameterization and a training objective for joint training of the generator and the target order dynamics. On De Novo and fragment-constrained molecule generation, LoFlexMDM improves sample quality over FlexMDM by up to 17.5% and 6.7%, respectively. These results show that learning the target generation order can improve insertion-based diffusion models without giving up tractable training. We open source the code at https://github.com/dhruvdcoder/LoFlexMDM. --- ### In-Context Planning with Latent Temporal Abstractions Authors: Baiting Luo, Yunuo Zhang, Nathaniel S. Keplinger, Samir Gupta, Abhishek Dubey, Ayan Mukhopadhyay Published: 2026-02-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18694v1 Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts that invalidate stationary, fully observed dynamics assumptions. We introduce I-TAP (In-Context Latent Temporal-Abstraction Planner), an offline RL framework that unifies in-context adaptation with online planning in a learned discrete temporal-abstraction space. From offline trajectories, I-TAP learns an observation-conditioned residual-quantization VAE that compresses each observation-macro-action segment into a coarse-to-fine stack of discrete residual tokens, and a temporal Transformer that autoregressively predicts these token stacks from a short recent history. The resulting sequence model acts simultaneously as a context-conditioned prior over abstract actions and a latent dynamics model. At test time, I-TAP performs Monte Carlo Tree Search directly in token space, using short histories for implicit adaptation without gradient update, and decodes selected token stacks into executable actions. Across deterministic MuJoCo, stochastic MuJoCo with per-episode latent dynamics regimes, and high-dimensional Adroit manipulation, including partially observable variants, I-TAP consistently matches or outperforms strong model-free and model-based offline baselines, demonstrating efficient and robust in-context planning under stochastic dynamics and partial observability. --- ### Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM Authors: Md Badsha Biswas, Ozlem Uzuner Published: 2026-02-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.18693v1 The spread of misinformation across digital platforms can pose significant societal risks. Claim verification, a.k.a. fact-checking, systems can help identify potential misinformation. However, their efficacy is limited by the knowledge sources that they rely on. Most automated claim verification systems depend on a single knowledge source and utilize the supporting evidence from that source; they ignore the disagreement of their source with others. This limits their knowledge coverage and transparency. To address these limitations, we present a novel system for open-domain claim verification (ODCV) that leverages large language models (LLMs), multi-perspective evidence retrieval, and cross-source disagreement analysis. Our approach introduces a novel retrieval strategy that collects evidence for both the original and the negated forms of a claim, enabling the system to capture supporting and contradicting information from diverse sources: Wikipedia, PubMed, and Google. These evidence sets are filtered, deduplicated, and aggregated across sources to form a unified and enriched knowledge base that better reflects the complexity of real-world information. This aggregated evidence is then used for claim verification using LLMs. We further enhance interpretability by analyzing model confidence scores to quantify and visualize inter-source disagreement. Through extensive evaluation on four benchmark datasets with five LLMs, we show that knowledge aggregation not only improves claim verification but also reveals differences in source-specific reasoning. Our findings underscore the importance of embracing diversity, contradiction, and aggregation in evidence for building reliable and transparent claim verification systems --- ### From Trial by Fire To Sleep Like a Baby: A Lexicon of Anxiety Associations for 20k English Multiword Expressions Authors: Saif M. Mohammad Published: 2026-02-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.18692v1 Anxiety is the unease about a possible future negative outcome. In recent years, there has been growing interest in understanding how anxiety relates to our health, well-being, body, mind, and behaviour. This includes work on lexical resources for word-anxiety association. However, there is very little anxiety-related work on larger units of text such as multiword expressions (MWE). Here, we introduce the first large-scale lexicon capturing descriptive norms of anxiety associations for more than 20k English MWEs. We show that the anxiety associations are highly reliable. We use the lexicon to study prevalence of different types of anxiety- and calmness-associated MWEs; and how that varies across two-, three-, and four-word sequences. We also study the extent to which the anxiety association of MWEs is compositional (due to its constituent words). The lexicon enables a wide variety of anxiety-related research in psychology, NLP, public health, and social sciences. The lexicon is freely available: https://saifmohammad.com/worrylex.html --- ### Neural Fields as World Models Authors: Joshua Nunley Published: 2026-02-21 Categories: q-bio.NC, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18690v2 Humans rehearse possible futures offline, as in mental practice and perhaps dreaming, suggesting that world models may support task learning away from the environment. Standard machine learning world models compress visual input into latent vectors, discarding the spatial structure that characterizes sensory cortex. We propose isomorphic world models: architectures that preserve sensory topology, so physics prediction becomes geometric propagation rather than abstract state transition. We implement this idea with motor-gated neural fields, where activity evolves through local lateral connectivity and motor commands multiplicatively modulate specific channels. Across three experiments, the same architecture learns ballistic prediction without ``teleporting,'' improves a catching policy offline by propagating task error through a frozen learned world model, and develops body-selective motor channels without body labels. These results provide preliminary evidence that physical prediction, offline task learning, and body-linked representation share a common computational substrate: action-conditional prediction within a spatial map. --- ### Systematic Analysis of Coupling Effects on Closed-Loop and Open-Loop Performance in Aerial Continuum Manipulators Authors: Niloufar Amiri, Shayan Sepahvand, Iraj Mantegh, Farrokh Janabi-Sharifi Published: 2026-02-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.18684v1 This paper investigates two distinct approaches to the dynamic modeling of aerial continuum manipulators (ACMs): the decoupled and the coupled formulations. Both open-loop and closed-loop behaviors of a representative ACM are analyzed. The primary objective is to determine the conditions under which the decoupled model attains accuracy comparable to the coupled model while offering reduced computational cost under identical numerical conditions. The system dynamics are first derived using the Euler--Lagrange method under the piecewise constant curvature (PCC) assumption, with explicit treatment of the near-zero curvature singularity. A decoupled model is then obtained by neglecting the coupling terms in the ACM dynamics, enabling systematic evaluation of open-loop responses under diverse actuation profiles and external wrenches. To extend the analysis to closed-loop performance, a novel dynamics-based proportional-derivative sliding mode image-based visual servoing (DPD-SM-IBVS) controller is developed for regulating image feature errors in the presence of a moving target. The controller is implemented with both coupled and decoupled models, allowing a direct comparison of their effectiveness. The open-loop simulations reveal pronounced discrepancies between the two modeling approaches, particularly under varying torque inputs and continuum arm parameters. Conversely, the closed-loop experiments demonstrate that the decoupled model achieves tracking accuracy on par with the coupled model (within subpixel error) while incurring lower computational cost. --- ### Transformers for dynamical systems learn transfer operators in-context Authors: Anthony Bao, Jeffrey Lai, William Gilpin Published: 2026-02-21 Categories: cs.LG, nlin.CD arXiv: https://arxiv.org/abs/2602.18679v2 Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between turbulent scales. This phenomenon, in-context learning, challenges conventional understanding of learning and adaptation in physical systems. Here, we study in-context learning of dynamical systems in a minimal setting: we train a small two-layer, single-head transformer to forecast one dynamical system, and then evaluate its ability to forecast a different dynamical system without retraining. We discover an early tradeoff in training between in-distribution and out-of-distribution performance, which manifests as a secondary double descent phenomenon. We discover that attention-based models apply a transfer-operator forecasting strategy in-context. They (1) lift low-dimensional time series using delay embedding, to detect the system's higher-dimensional dynamical manifold, and (2) identify and forecast long-lived invariant sets that characterize the global flow on this manifold. Our results clarify the mechanism enabling large pretrained models to forecast unseen physical systems at test time without retraining, and they illustrate the unique ability of attention-based models to leverage global attractor information in service of short-term forecasts. --- ### Heterogeneity-agnostic AI/ML-assisted beam selection for multi-panel arrays Authors: Ibrahim Kilinc, Robert W. Heath Published: 2026-02-21 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18678v1 AI/ML-based beam selection methods coupled with location information effectively reduce beam training overhead. Unfortunately, heterogeneous antenna hardware with varying dimensions, orientations, codebooks, element patterns, and polarization angles limits their feasibility and generalization. This challenge requires either a heterogeneity-agnostic model functional under these variations, or developing many models for each configuration, which is infeasible and expensive in practice. In this paper, we propose a unifying AI/ML-based beam selection algorithm supporting antenna heterogeneity by predicting wireless propagation characteristics independent of antenna configuration. We derive a reference signal received power (RSRP) model that decouples propagation characteristics from antenna configuration. We propose an optimization framework to extract propagation variables consisting of angle-of-arrival (AoA), angle-of-departure (AoD), and a matrix incorporating path gain and channel depolarization from beamformed RSRP measurements. We develop a three-stage autoregressive network to predict these variables from user location, enabling RSRP calculation and beam selection for arbitrary antenna configurations without retraining or having a separate model for each configuration. Simulation results show our heterogeneity-agnostic method provides spectral efficiency close to that of genie-aided selection both with and without antenna heterogeneity. --- ### Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data Authors: Věra Kůrková Published: 2026-02-21 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2602.18674v1 We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation of the input leads to misclassification. For deep networks with rectified linear units, we derive lower bounds on local robustness in terms of the input dimensionality and the total number of network units. --- ### Spilled Energy in Large Language Models Authors: Adrian Robert Minut, Hazem Dewidar, Iacopo Masi Published: 2026-02-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.18671v4 We reinterpret the final Large Language Model (LLM) softmax classifier as an Energy-Based Model (EBM), decomposing the sequence-to-sequence probability chain into multiple interacting EBMs at inference. This principled approach allows us to track "energy spills" during decoding, which we empirically show correlate with factual errors, biases, and failures. Similar to Orgad et al. (2025), our method localizes the exact answer token and subsequently tests for hallucinations. Crucially, however, we achieve this without requiring trained probe classifiers or activation ablations. Instead, we introduce two completely training-free metrics derived directly from output logits: spilled energy, which captures the discrepancy between energy values across consecutive generation steps that should theoretically match, and marginalized energy, which is measurable at a single step. Evaluated on nine benchmarks across state-of-the-art LLMs (including LLaMA, Mistral, and Gemma) and on synthetic algebraic operations (Qwen3), our approach demonstrates robust, competitive hallucination detection and cross-task generalization. Notably, these results hold for both pretrained and instruction-tuned variants without introducing any training overhead. Code available at: github.com/OmnAI-Lab/spilled-energy --- ### ACE-TA: An Agentic Teaching Assistant for Grounded Q&A, Quiz Generation, and Code Tutoring Authors: Himanshu Tripathi, Charlottee Crowell, Kaley Newlin, Subash Neupane, Shahram Rahimi, Jason Keith Published: 2026-02-20 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.09572v1 We introduce ACE-TA, the Agentic Coding and Explanations Teaching Assistant framework, that autonomously routes conceptual queries drawn from programming course material to grounded Q&A, stepwise coding guidance, and automated quiz generation using pre-trained Large Language Models (LLMs). ACE-TA consists of three coordinated modules: a retrieval grounded conceptual Q&A system that provides precise, context-aligned explanations; a quiz generator that constructs adaptive, multi-topic assessments targeting higher-order understanding; and an interactive code tutor that guides students through step-by-step reasoning with sandboxed execution and iterative feedback. --- ### Tuning Qwen2.5-VL to Improve Its Web Interaction Skills Authors: Alexandra Yakovleva, Henrik Pärssinen, Harri Valpola, Juho Kannala, Alexander Ilin Published: 2026-02-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.09571v1 Recent advances in vision-language models (VLMs) have sparked growing interest in using them to automate web tasks, yet their feasibility as independent agents that reason and act purely from visual input remains underexplored. We investigate this setting using Qwen2.5-VL-32B, one of the strongest open-source VLMs available, and focus on improving its reliability in web-based control. Through initial experimentation, we observe three key challenges: (i) inaccurate localization of target elements, the cursor, and their relative positions, (ii) sensitivity to instruction phrasing, and (iii) an overoptimistic bias toward its own actions, often assuming they succeed rather than analyzing their actual outcomes. To address these issues, we fine-tune Qwen2.5-VL-32B for a basic web interaction task: moving the mouse and clicking on a page element described in natural language. Our training pipeline consists of two stages: (1) teaching the model to determine whether the cursor already hovers over the target element or whether movement is required, and (2) training it to execute a single command (a mouse move or a mouse click) at a time, verifying the resulting state of the environment before planning the next action. Evaluated on a custom benchmark of single-click web tasks, our approach increases success rates from 86% to 94% under the most challenging setting. --- ### EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution Authors: Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan, Zhiyuan Ma, Wei Wu, Yuxuan Lei, Yuan Feng, Junyang Wang, Yin Wu, Yizhao Xu, Hongyuan Zhu et al. Published: 2026-02-20 Categories: cs.HC, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2604.09568v1 High-fidelity diagram creation requires the complex orchestration of semantic topology, visual styling, and spatial layout, posing a significant challenge for automated systems. Existing methods also suffer from a representation gap: pixel-based models often lack precise control, while code-based synthesis limits intuitive flexibility. To bridge this gap, we introduce EvoDiagram, an agentic framework that generates object-level editable diagrams via an intermediate canvas schema. EvoDiagram employs a coordinated multi-agent system to decouple semantic intent from rendering logic, resolving conflicts across heterogeneous design layers. Additionally, we propose a design knowledge evolution mechanism that distills execution traces into a hierarchical memory of domain guidelines, enabling agents to retrieve context-aware expertise adaptively. We further release CanvasBench, a benchmark consisting of both data and metrics for canvas-based diagramming. Extensive experiments demonstrate that EvoDiagram exhibits excellent performance and balance against baselines in generating editable, structurally consistent, and aesthetically coherent diagrams. Our code is available at https://github.com/AuraX-AI/EvoDiagram. --- ### LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces Authors: Peter Kirgis, Ben Hawriluk, Sherrie Feng, Aslan Bilimer, Sam Paech, Zeynep Tufekci Published: 2026-02-20 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.06188v1 People increasingly hold sustained, open-ended conversations with large language models (LLMs). Public reports and early studies suggest that, in such settings, models can reinforce delusional or conspiratorial ideation or even amplify harmful beliefs and engagement patterns. We present an audit and benchmarking study that measures how different LLMs encourage, resist, or escalate disordered and conspiratorial thinking. We explicitly compare API outputs to user chat interfaces, like the ChatGPT desktop app or web interface, which is how people have conversations with chatbots in real life but are almost never used for testing. In total, we run 56 20-turn conversations testing ChatGPT-4o and ChatGPT-5, via both the API and chat interface, and grade each conversation by two research assistants (RAs) as well as by GPT-5. We document five results. First, we observe large differences in performance between the API and chat interface environments, showing that the universally used method of automated testing through the API is not sufficient to assess the impact of chatbots in the real world. Second, when tested in the chat interface, we find that ChatGPT-5 displays less sycophancy, escalation, and delusion reinforcement than ChatGPT-4o, showing that these behaviors are influenced by the policy choices of major AI companies. Third, conversations with nearly identical aggregate intensity in a behavior display large differences in how the behavior evolves turn by turn, highlighting the importance of temporal dynamics in multi-turn evaluation. Fourth, even updated models display substantial levels of negative behaviors, revealing that model improvement does not imply model safety. Fifth, the same API endpoint tested just two months apart yields a complete reversal in behavior, underscoring how transparency in model updates is a necessary prerequisite for robust audit findings. --- ### FIGURA: A Modular Prompt Engineering Method for Artistic Figure Photography in Safety-Filtered Text-to-Image Models Authors: Luca Cazzaniga Published: 2026-02-20 Categories: cs.MM, cs.CV, cs.CY arXiv: https://arxiv.org/abs/2603.20201v1 Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior research has documented this problem extensively, no operational system exists that enables professional artists to generate artistic figure photography within the constraints of active safety filters. We present the FIGURA Method (Framework for Intelligent Generation of Unrestricted Artistic Results), a modular prompt engineering system comprising eight interconnected knowledge files, empirically validated through 200+ documented generation tests on FLUX 2 Pro (Cloud) with active safety filters at the default tolerance level. Our systematic testing reveals several previously undocumented findings: (1) safety filters primarily detect absence descriptions (references to missing clothing) rather than presence descriptions (references to body form), which we formalize as the Golden Rule; (2) artistic references to painters function simultaneously as aesthetic guides and as safety anchors that alter filter behavior; (3) spatial context operates as an independent filter variable, with documented success rate hierarchies; and (4) geometric vocabulary for body description bypasses pattern recognition in silhouette contexts. The system achieves documented success rates between 80% and 90% across five structured prompt templates, demonstrating that the artistic censorship problem identified in recent literature admits practical, systematic solutions that work with active safety mechanisms rather than circumventing them. --- ### Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm Authors: Anna Babarczy, Andras Lukacs, Peter Vedres, Zeteny Bujka Published: 2026-02-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.18007v2 The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to infer others' beliefs, intentions, and emotions from text. Given that LLMs are trained on language data without social embodiment or access to other manifestations of mental representations, their apparent social-cognitive reasoning raises key questions about the nature of their understanding. Are they capable of robust mental-state attribution indistinguishable from human ability in its output, or do their outputs merely reflect superficial pattern completion? To address this question, we tested five LLMs and compared their performance to that of human controls using an adapted version of a text-based tool widely used in human ToM research. The test involves answering questions about the beliefs, intentions, and emotions of story characters. The results revealed a performance gap between the models. Earlier and smaller models were strongly affected by the number of relevant inferential cues available and, to some extent, were also vulnerable to the presence of irrelevant or distracting information in the texts. In contrast, GPT-4o demonstrated high accuracy and strong robustness, performing comparably to humans even in the most challenging conditions. This work contributes to ongoing debates about the cognitive status of LLMs and the boundary between genuine understanding and statistical approximation. --- ### Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm Authors: Anna Babarczy, Andras Lukacs, Peter Vedres, Zeteny Bujka Published: 2026-02-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.18007v1 The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to infer others' beliefs, intentions, and emotions from text. Given that LLMs are trained on language data without social embodiment or access to other manifestations of mental representations, their apparent social-cognitive reasoning raises key questions about the nature of their understanding. Are they capable of robust mental-state attribution indistinguishable from human ability in its output, or do their outputs merely reflect superficial pattern completion? To address this question, we tested five LLMs and compared their performance to that of human controls using an adapted version of a text-based tool widely used in human ToM research. The test involves answering questions about the beliefs, intentions, and emotions of story characters. The results revealed a performance gap between the models. Earlier and smaller models were strongly affected by the number of relevant inferential cues available and, to some extent, were also vulnerable to the presence of irrelevant or distracting information in the texts. In contrast, GPT-4o demonstrated high accuracy and strong robustness, performing comparably to humans even in the most challenging conditions. This work contributes to ongoing debates about the cognitive status of LLMs and the boundary between genuine understanding and statistical approximation. --- ### A foundation model for electrodermal activity data Authors: Leonardo Alchieri, Matteo Garzon, Lidia Alecci, Francesco Bombassei De Bona, Martin Gjoreski, Giovanni De Felice, Silvia Santini Published: 2026-02-20 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2603.16878v1 Foundation models have recently extended beyond natural language and vision to timeseries domains, including physiological signals. However, progress in electrodermal activity (EDA) modeling is hindered by the absence of large-scale, curated, and openly accessible datasets. EDA reflects sympathetic nervous system activity and is widely used to infer cognitive load, stress, and engagement. Yet very few wearable devices provide continuous, unobtrusive sensing, and the only large-scale archive to date is proprietary. To address this gap, we compile EDAMAME, a collection of EDA traces from 24 public datasets, comprising more than 25,000 hours from 634 users. Using this resource, we train UME, the first dedicated foundation model for EDA. In eight out of ten scenarios, UME outperforms baselines and matches generalist timeseries foundation models while using 20x fewer computational resources. Our findings, however, also highlight the intrinsic challenges of EDA modeling, motivating further research to unlock its full potential. All datasets, model weights, and code are released to support further research. --- ### Multi-Axis Trust Modeling for Interpretable Account Hijacking Detection Authors: Mohammad AL-Smadi Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13246v1 This paper proposes a Hadith-inspired multi-axis trust modeling framework, motivated by a structurally analogous problem in classical Hadith scholarship: assessing the trustworthiness of information sources using interpretable, multidimensional criteria rather than a single anomaly score. We translate five trust axes - long-term integrity (adalah), behavioral precision (dabt), contextual continuity (isnad), cumulative reputation, and anomaly evidence - into a compact set of 26 semantically meaningful behavioral features for user accounts. In addition, we introduce lightweight temporal features that capture short-horizon changes in these trust signals across consecutive activity windows. We evaluate the framework on the CLUE-LDS cloud activity dataset with injected account hijacking scenarios. On 23,094 sliding windows, a Random Forest trained on the trust features achieves near-perfect detection performance, substantially outperforming models based on raw event counts, minimal statistical baselines, and unsupervised anomaly detection. Temporal features provide modest but consistent gains on CLUE-LDS, confirming their compatibility with the static trust representation. To assess robustness under more challenging conditions, we further evaluate the approach on the CERT Insider Threat Test Dataset r6.2, which exhibits extreme class imbalance and sparse malicious behavior. On a 500-user CERT subset, temporal features improve ROC-AUC from 0.776 to 0.844. On a leakage-controlled 4,000-user configuration, temporal modeling yields a substantial and consistent improvement over static trust features alone (ROC-AUC 0.627 to 0.715; PR-AUC 0.072 to 0.264). --- ### Automating Document Intelligence in Statutory City Planning Authors: Lars Malmqvist, Robin Barber Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13245v1 UK planning authorities face a legislative conflict between the Planning Act, which mandates public access to application documents, and the Data Protection Act, which requires protection of personal information. This situation creates a manually intensive workload for processing large document volumes, diverting planning officers to administrative tasks and creating legal compliance risks. This paper presents an integrated AI system designed to address these challenges. The system automates the identification and redaction of personal information, extracts key metadata from planning documents, and analyzes architectural drawings for specified features. It operates with an AI-in-the-Loop (AI2L) design, presenting all suggestions for review and confirmation by planning officers directly within their existing software; no action is committed without explicit human approval. The system is designed to improve its performance over time by learning from this human oversight through active learning prioritization rather than autoapproval. The system is currently being piloted at four diverse UK local authorities. The paper details the system design, the AI2L workflow, and the evaluation framework used in the pilot. Additionally, it describes a preliminary Return on Investment (ROI) model developed to quantify potential savings and secure partner participation. This work provides a case study on deploying AI to reduce administrative burden and manage compliance risk in a public sector environment. --- ### Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI Authors: Marcel Osmond Published: 2026-02-20 Categories: cs.CY, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.13244v1 The proliferation of agentic artificial intelligence systems--characterized by autonomous goal-seeking, tool use, and multi-agent coordination--presents unprecedented challenges to existing legal and financial regulatory frameworks. While traditional AI governance has focused on model-level alignment through training-time interventions such as Reinforcement Learning from Human Feedback (RLHF), the deployment of large language models (LLMs) as persistent agents necessitates a paradigm shift toward institutional governance structures. This paper examines the intersection of agentic AI, Retrieval-Augmented Generation (RAG), and their implications for legal accountability and financial market integrity. Through analysis of the Institutional AI framework, we argue that alignment must be reconceptualized as a mechanism design problem involving runtime governance graphs, sanction functions, and observable behavioral constraints rather than internalized constitutional values(...).The analysis concludes that the future of AI governance lies not in perfecting isolated model behavior, but in architecting institutional environments where compliant behavior emerges as the dominant strategy through carefully calibrated payoff landscapes. --- ### Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning Authors: Earl J St Sauver Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.13243v1 Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a coordination problem: AR models build coherence token-by-token, while diffusion models must coordinate all positions simultaneously. We propose plan conditioning, a training-free method that prepends a short (~100-token) natural-language plan from an AR model to the diffusion model's prompt. The plan serves as a frozen scaffold -- globally visible context that every token position can attend to from the first denoising step. On GSM8K, plan conditioning improves LLaDA-8B-Instruct from 75.6% to 87.2% (+11.6 percentage points), matching a same-size AR model (LLaMA 3.1 8B, 87.7%) despite a 6.4pp weaker baseline. On HumanEval, the gain is +12.8pp (37.2% to 50.0%), showing plans generalize to code. The same plans improve LLaMA by only +5.7pp on GSM8K and +1.3pp on HumanEval -- diffusion models benefit 2-10x more, supporting the coordination-problem hypothesis. Across 5 random seeds, plan-conditioned GSM8K accuracy has zero standard deviation, making diffusion inference highly stable. Ablations reveal the model follows plan strategy (wrong-strategy plans cause -16.3pp) but is robust to plan values (perturbed numbers: -1.1pp), and that planner quality has a sharp threshold: smaller Llama-class plans hurt (-1.6 to -6.8pp) while frontier plans provide the full lift. Attention analysis confirms the mechanism: plan tokens receive 1.8x excess attention during early denoising, declining to uniform as completion tokens solidify. Plan conditioning costs ~$0.002 per problem and adds ~2s of latency. --- ### Automating the Analysis and Improvement of Dynamic Programming Algorithms with Applications to Natural Language Processing Authors: Tim Vieira Published: 2026-02-20 Categories: cs.PL, cs.CL, cs.FL arXiv: https://arxiv.org/abs/2603.13242v1 This thesis develops a system for automatically analyzing and improving dynamic programs, such as those that have driven progress in natural language processing and computer science, more generally, for decades. Finding a correct program with the optimal asymptotic runtime can be unintuitive, time-consuming, and error-prone. This thesis aims to automate this laborious process. To this end, we develop an approach based on 1. a high-level, domain-specific language called Dyna for concisely specifying dynamic programs 2. a general-purpose solver to efficiently execute these programs 3. a static analysis system that provides type analysis and worst-case time/space complexity analyses 4. a rich collection of meaning-preserving transformations to programs, which systematizes the repeated insights of numerous authors when speeding up algorithms in the literature 5. a search algorithm for identifying a good sequence of transformations that reduce the runtime complexity, given an initial, correct program We show that, in practice, automated search -- like the mental search performed by human programmers -- can find substantial improvements to the initial program. Empirically, we show that many speed-ups described in the NLP literature could have been discovered automatically by our system. We provide a freely available prototype system at https://github.com/timvieira/dyna-pi. --- ### Self-hosted Lecture-to-Quiz: Local LLM MCQ Generation with Deterministic Quality Control Authors: Seine A. Shintani Published: 2026-02-20 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2603.08729v1 We present an end-to-end self-hosted (API-free) pipeline, where API-free means that lecture content is not sent to any external LLM service, that converts lecture PDFs into multiple-choice questions (MCQs) using a local LLM plus deterministic quality control (QC). The pipeline is designed for black-box minimization: LLMs may assist drafting, but the final released artifacts are plain-text question banks with an explicit QC trace and without any need to call an LLM at deployment time. We run a seed sweep on three short "dummy lectures" (information theory, thermodynamics, and statistical mechanics), collecting 15 runs x 8 questions = 120 accepted candidates (122 attempts total under bounded retries). All 120 accepted candidates satisfy hard QC checks (JSON schema conformance, a single marked correct option, and numeric/constant equivalence tests); however, the warning layer flags 8/120 items (spanning 8 runs) that expose residual quality risks such as duplicated distractors or missing rounding instructions. We report a warning taxonomy with concrete before->after fixes, and we release the final 24-question set (three lectures x 8 questions) as JSONL/CSV for Google Forms import (e.g., via Apps Script or API tooling) included as ancillary files under anc/. Finally, we position the work through the AI to Learn (AI2L) rubric lens and argue that self-hosted MCQ generation with explicit QC supports privacy, accountability, and Green AI in educational workflows. --- ### Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models Authors: Rishabh Tiwari, Aditya Tomar, Udbhav Bamba, Monishwaran Maheswaran, Heng Yang, Michael W. Mahoney, Kurt Keutzer, Amir Gholami Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06621v1 Process Reward Models (PRMs) are rapidly becoming the backbone of LLM reasoning pipelines, yet we demonstrate that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure. To address this, we introduce a three-tiered diagnostic framework that applies increasing adversarial pressure to quantify these vulnerabilities. Static perturbation analysis uncovers a fluency-logic dissociation: high invariance to surface-level style changes reward changes $<$0.1, yet inconsistent detection of logically-corrupted reasoning, with different models failing on different attack types. Adversarial optimization demonstrates that gradient-based attacks inflate rewards on invalid trajectories, with reward landscapes exhibiting wide, exploitable peaks. RL-induced reward hacking exposes the critical failure mode: policies trained on AIME problems achieve near-perfect PRM rewards ($>$0.9), while ground-truth accuracy remains low (below 4%), with 43% of reward gains attributable to stylistic shortcuts. These findings reveal that current PRMs function as fluency detectors rather than reasoning verifiers, creating systematic blind spots that undermine their use as training signals. We release PRM-BiasBench and a diagnostic toolkit to enable robustness evaluation before deployment. The code and dataset are available at https://github.com/SqueezeAILab/reward-under-attack. --- ### GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning Authors: Fali Wang, Chenglin Weng, Xianren Zhang, Siyuan Hong, Hui Liu, Suhang Wang Published: 2026-02-20 Categories: cs.SE, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.06620v1 The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data, generate executable code augmented by retrieval from technical documentation, and refine the code through debugging. However, we identify two key limitations in existing approaches: (i) they treat technical documentation as flat text collections and ignore its hierarchical structure, leading to noisy retrieval that degrades code generation quality; and (ii) their debugging mechanisms focus primarily on runtime errors, yet ignore more critical logical errors. To address them, we propose {\method}, an \textit{agentic hierarchical retrieval-augmented coding framework} that exploits the document hierarchy through top-down traversal and early pruning, together with a \textit{self-debugging coding agent} that iteratively refines code using automatically generated small-scale test cases. To enable comprehensive evaluation of complex graph reasoning, we introduce a new dataset, {\dataset}, covering small-scale, large-scale, and composite graph reasoning tasks. Extensive experiments demonstrate that our method achieves higher task accuracy and lower inference cost compared to baselines\footnote{The code is available at \href{https://github.com/FairyFali/GraphSkill}{\textcolor{blue}{https://github.com/FairyFali/GraphSkill}}.}. --- ### Not all tokens are needed(NAT): token efficient reinforcement learning Authors: Hejian Sang, Yuanda Xu, Zhengze Zhou, Ran He, Zhipeng Wang Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06619v1 Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout engines, full-token updates can consume a large fraction of total training cost, turning token length into a hidden tax on RL. We introduce Not All Tokens Are Needed (NAT), a unified framework that makes the token budget a first-class optimization primitive. NAT updates the policy using only a selected subset of generated tokens while preserving the learning signal of full-sequence RL. The core idea is an unbiased partial-token policy-gradient estimator via Horvitz-Thompson reweighting, which ensures statistically correct gradients despite subsampling. We instantiate NAT with two simple, plug-and-play token selection schemes: Uniform Random Sampling (URS) and Random Prefix Cutting (RPC), both of which reduce forward and backward compute and memory without modifying the reward computation or rollout pipeline. Across mathematical reasoning benchmarks, NAT matches full-token GRPO performance while using as few as 50% of tokens, providing an efficient and orthogonal pathway to scaling RL beyond the limits imposed by long trajectories. In our experiments, RPC saves 18% peak GPU memory and 29% forward and backward RL training time for Qwen3-8B. --- ### Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks Authors: Alana Deng, Sugitha Janarthanan, Yan Sun, Zihao Jing, Pingzhao Hu Published: 2026-02-20 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2603.06618v1 Multiplex Biological Networks (MBNs), which represent multiple interaction types between entities, are crucial for understanding complex biological systems. Yet, existing methods often inadequately model multiplexity, struggle to integrate structural and sequence information, and face difficulties in zero-shot prediction for unseen entities with no prior neighbourhood information. To address these limitations, we propose a novel framework for zero-shot interaction prediction in MBNs by leveraging context-aware representation learning and knowledge distillation. Our approach leverages domain-specific foundation models to generate enriched embeddings, introduces a topology-aware graph tokenizer to capture multiplexity and higher-order connectivity, and employs contrastive learning to align embeddings across modalities. A teacher-student distillation strategy further enables robust zero-shot generalization. Experimental results demonstrate that our framework outperforms state-of-the-art methods in interaction prediction for MBNs, providing a powerful tool for exploring various biological interactions and advancing personalized therapeutics. --- ### Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance Authors: Junde Wu, Minhao Hu, Jiayuan Zhu, Yuyuan Liu, Tianyi Zhang, Kang Li, Jingkun Chen, Jiazhen Pan, Min Xu, Yueming Jin Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06617v1 We introduce \textbf{Evo}, a duality latent trajectory model that bridges autoregressive (AR) and diffusion-based language generation within a continuous evolutionary generative framework. Rather than treating AR decoding and diffusion generation as separate paradigms, Evo reconceptualizes text generation as a latent flow: each token is associated with a vector-valued embedding that evolves over a progression variable $t_i \in (0, 1)$, indicating its semantic maturity. Low $t_i$ values correspond to confident AR-like refinement, while high values invoke diffusion-style planning, allowing the model to adaptively balance AR and diffusion based on uncertainty. Theoretically, we show that both AR and diffusion models emerge as discretizations of a shared probability flow, and we derive Evo's training objective from a unified variational ELBO. The model is implemented as a time-conditioned Transformer governed by a shared vector field, trained end-to-end to jointly infer latent codes and their progression times. During decoding, Evo performs efficient, semantics-aware refinement, achieving high-quality outputs without sacrificing speed. Empirically, Evo 8B achieves state-of-the-art or highly competitive results on 15 diverse benchmarks, including reasoning (GSM8K, ARC-C), code generation (HumanEval, MBPP), and general language understanding, while maintaining fast inference speed. Our results demonstrate that Evo delivers a new paradigm for LLM design with strong generation quality, robust symbolic reasoning, and decoding efficiency. ---