# Research Papers — 2026-07 · bundle page 11 of 222 > Full-text markdown of papers #501–550 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/11 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/10.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/12.md) ### Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations Authors: Konur Tholl, François Rivest, Mariam El Mezouar, Adrian Taylor, Ranwa Al Mallah Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28826v1 Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. ACO applications commonly employ Reinforcement Learning (RL) agents to learn defensive behaviors through interaction with environments. However, RL agents typically require extensive exploration during training, often resulting in unstable behavior and poor initial decision-making before converging toward effective defense strategies. In this work, we investigate the use of a Large Language Model (LLM) to improve autonomous defensive decision-making within an ACO environment. Through prompt engineering rather than fine-tuning, we demonstrate that an 8-billion parameter LLM pretrained on cybersecurity data can outperform a baseline RL agent in a modified CybORG CAGE Challenge 2 environment. We then propose an online policy distillation framework that transfers the LLM's defensive policy into a lightweight RL agent containing only 64,910 parameters, reducing model size by several orders of magnitude while maintaining effective defensive capabilities. This provides a pathway toward operationalizing frontier cybersecurity models within lightweight, deployable agents. To evaluate transferability, we construct CybORG scenarios ranging from 4 to 12 hosts and assess the approach across varying network configurations. We also evaluate teacher-guided RL stabilization strategies and observe that none consistently surpass the optimized teacher policy, suggesting policy-alignment limitations between reward-driven RL optimization and teacher-guided defense strategies. Our results demonstrate the potential of cybersecurity-focused LLMs as sources of expertise for autonomous cyber defense, while policy distillation provides a practical path toward operationalizing frontier cybersecurity models within efficient, scalable agents. --- ### Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions Authors: Pranav Narayanan Venkit, Akshara Prabhakar, Yu Li, Daniel Lee, Chien-Sheng Wu Published: 2026-07-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28818v1 As AI companions increasingly mediate repeated social interaction, users may rely on a stable role and shared history, yet locally acceptable replies do not ensure that either persists. We study two observable long-horizon failures: 'persona collapse', the loss of a deployed role, boundaries, values, or style, and 'behavioral drift', the gradual or recurrent erosion of those properties. We introduce ANCHOR, a controlled synthetic audit that separately measures persona enactment and trajectory recall. The study contains 2,008 conversations spanning 27 personas, nine interaction schedules, three generated memory settings, and four evaluated models. The Identity Probe combines a sealed 102-item questionnaire with turn-level judgments, while the Trajectory Probe scores 110 calibrated counterfactual questions from 35 conversation banks. Our results show that no evaluated model and configuration reliably preserves either dimensions: trajectory accuracy averages only 44.4%, user-state recall remains near four-option chance, and no tested context condition or memory consistently resolves these failures. Questionnaire retention also varies by model and persona facet, disagrees with turn-level behavior, and is sensitive to evaluator choice. These results indicate that current systems do not yet reliably support long-horizon companion continuity and that audits must distinguish persona enactment, trajectory recall, evaluator provenance, and deployment context rather than collapse them into a single trust or stability score. --- ### Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing Authors: Weiying Chen, Junlong Shen, Zhexuan Tang Published: 2026-07-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.28814v1 In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that can fail in two opposite ways: capitulation (abandoning the change agenda to preserve rapport) or confrontation (arguing or directing, overriding the client's autonomy). We introduce a two-axis evaluation of counselor responses, anchored in the Motivational Interviewing Treatment Integrity (MITI) code, Goal Persistence (GP) and Relational Attunement (RA), yielding a four-quadrant framing in which rolling with resistance is high on both, and we ask whether penalizing one failure through preference optimization teaches rolling with resistance or provokes its opposite. From the expert-annotated AnnoMI corpus we build topic-disjoint Direct Preference Optimization data whose preference sets differ only in which failure is rejected, using on-policy negatives. An automatic judge, validated against AnnoMI's expert labels and rechecked by trained human coders, scores blind pairwise win-rates against each base under a firewall in which disjoint model families generate, label, and judge. Across three aligned instruction models spanning the Qwen and Llama families, penalizing confrontation reliably lowers goal persistence below parity, on every base and in every seed run, a robust cost, whereas the attunement gain is base-dependent, present on two of the three bases but absent on the third. Penalizing capitulation is inert, because these models rarely capitulate on-policy, so the trade is gated by each base's failure profile. A prompt-only control raises attunement without the goal-persistence cost, locating the cost in the optimization rather than in attunement itself. --- ### Bayesian Mediation Analysis for Individualized Treatment Rules Authors: Emmanuel M. Rockwell, Patrick J. Smith, Michael R. Kosorok, Nikki L. B. Freeman Published: 2026-07-30 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.28804v1 The value of an individualized treatment rule (ITR), defined as the expected outcome under treatment assignment according to the rule, is useful for assessing average clinical benefit but does not explain how the benefit of a rule is generated. We propose a causal mediation framework for decomposing the value contrast between a prespecified candidate ITR and a clinically meaningful reference rule into direct and indirect components. Using rule-specific nested potential outcomes, we define natural direct and indirect rule effects that quantify the extent to which the improvement in value arises through pathways operating directly on the outcome versus through a specified mediator. We give identification conditions under which these components are identified by a rule-level mediation g-formula. For estimation, we adapt Bayesian causal mediation forests to obtain posterior inference for the value contrast and its path-specific components. Our simulations demonstrate that the proposed estimator achieved near-nominal credible interval coverage with decreasing bias and root mean squared error as sample size increased in settings with varying direct and mediated contributions. We further illustrate the method using data from the TRIUMPH trial, decomposing the cognitive benefit of a lifestyle intervention rule through candidate neurovascular, cardiorespiratory, and behavioral mediators. The proposed framework complements optimal ITR learning with explanation using mediation, providing a natural approach for mechanistic evaluation of ITRs. --- ### Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures Authors: Harsh Raj, Vipul Gupta, Anas Mahmoud, Razvan-Gabriel Dumitru, Darvin Yi, Aakash Sabharwal, Yunzhong He Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28802v1 Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This creates a repair-assignment problem: the same visible failure may call for model post-training, harness engineering, environment redesign, or benchmark repair depending on its source. Because agent behavior emerges from interactions among models, harnesses, users, tools, memory, and environments, outcome-level labels are often insufficient for improvement. Most failure taxonomies do little to resolve this problem because they are benchmark-specific and lack a shared structure. We introduce an interaction-centric taxonomy that localizes failures to the interactions in which they originate and identifies the responsible component. It organizes 41 failure modes by assigning each to an edge between two components and a fault side indicating where the repair belongs. This makes the taxonomy actionable: model-side failures identify targets for post-training, harness-side failures point to scaffolding and tool-integration fixes, and environment or grader failures reveal evaluation conditions requiring redesign. The schema applies across agent architectures, from coding assistants to long-horizon personal assistants and multi-agent systems. We ground the taxonomy in worked examples from public benchmarks, model system cards, published reports, and logged agent trajectories, and evaluate its reproducibility using independent reasoning agents as judges. Across four frontier models, the strongest judge reaches Cohen's $κ=0.76$ against human category labels, suggesting that the categories capture shared structure rather than annotator-specific preferences. --- ### Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation Authors: Philipp D. Siedler, Jordan Sassoon Published: 2026-07-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.28801v1 Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples. We introduce a dataset-centric meta-evaluation framework that audits benchmark datasets at the sample level along five latent dimensions: 1. Cognitive and Knowledge Demands, 2. Language and Content Quality, 3. Task Properties, 4. Context, and 5. Ethics, Safety, and Fairness. Applying this framework, we annotate five influential benchmarks -- MMLU, ARC, WinoGrande, HellaSwag, and TruthfulQA -- revealing pronounced internal heterogeneity that is not captured by aggregate accuracy scores. We show how these annotations enable criterion-driven orchestration of composite benchmark subsets across datasets, supporting targeted evaluation of model capabilities such as Reasoning Depth or Ethical Sensitivity. This approach reframes benchmark evaluation as dataset introspection, providing a principled methodology for analyzing and re-composing existing benchmarks to better reflect diverse evaluation needs. --- ### Can Synthetic Data Overcome the Generalization Limits of AI-Based Flower and Pod Detection Across Cowpea Breeding Genotypes and Environments? Authors: Hamid Kamangir, Jonathan Berlingeri, Earl Ranario, Isaac Kazuo Uyehara, Lars Lundqvist, Heesup Yun, Christine H. Diepenbrock, Brian N. Bailey, J. Mason Earles Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28796v1 High-throughput phenotyping requires AI-enabled computer vision models that generalize across genotypes, locations, and growing seasons, yet such models often lose accuracy under new conditions. Annotating real imagery for every genotype-by-environment (G x E) combination a breeding program encounters is prohibitively expensive. We quantify how G x E shifts affect AI-based detection of cowpea flowers and pods across two California locations and two growing seasons. Flower detection mAP@50 fell from 76.3% to as low as 50.6% under unseen shifts, and pod detection was more sensitive. Feature-space and image-quality diagnostics confirmed these losses track measurable distributional shifts. Because closing this gap with real data alone is not practical, we test whether synthetic imagery, rendered from a procedural 3D cowpea model, can substitute for that annotation burden. Synthetic supervision alone improved over pretraining but remained limited by a domain gap driven by camera image formation, not scene content. A domain-gap-aware camera-realism augmentation strategy, optimized against measured real-image statistics via Wasserstein distance, narrowed this gap, and a linear HDR representation converted a smaller measured gap into a larger detection gain than an 8-bit representation. Optimized HDR synthetic data combined with as few as five real images matched or exceeded the real-data baseline for spatial generalization, and pod detection benefited most at the lowest shot counts, with more modest gains under temporal shift. These results show that synthetic data can overcome the generalization limits of AI-based flower and pod detection, but only when the domain gap is measured and optimized rather than assumed away. --- ### EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses Authors: Jiahui Li, Ruili Fang, Zishuai Liu, Yutong Guo, Nan Yang, Wenzhan Song, Jin Lu, Fei Dou Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28788v1 Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence. Existing diagnosis-prediction benchmarks are poorly suited to this setting: they restrict prediction to closed code sets, exclude free-text notes, and supervise with discharge diagnoses that incorporate the full inpatient course. We introduce EarlyDx, a large-scale benchmark for open-ended early diagnosis, built from 154,834 emergency department encounters in MIMIC-IV. Each encounter is restricted to records available at admission time $t_0$ and supervised by the diagnoses recorded during the ED encounter rather than at discharge. An LLM auditor further verifies every free-text label as supported, partially supported, or unsupported by that evidence; the primary evaluation scores only fully supported labels. Under a semantic LLM-as-judge protocol, no evaluated system --- frontier general, medical-specialized, or in-domain post-trained --- synthesizes admission-time evidence reliably. Zero-shot models score largely by extraction, recovering only 3-31% of diagnoses that must be inferred rather than read from the record; post-training raises inference-dependent recall to 56%, but a sizeable margin remains, and on time-critical conditions no system attains a clinician's balance of sensitivity and precision. We release the full construction and evaluation pipeline at here. --- ### Stratified Negation in RDF Rules: A Correct Approach (Extended Version) Authors: Nils Küchenmeister, Alex Ivliev, Dörthe Arndt, Markus Krötzsch Published: 2026-07-30 Categories: cs.LO, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2607.28778v1 Combining RDF rule languages, such as N3 or SHACL Rules, with default negation is challenging. Existing methods to stratify negation often fail for RDF rules, since individual triples do not carry enough information to meaningfully restrict potential dependencies. Blank nodes in rule heads further complicate the matter, since the order of rule applications may determine whether new values are created, which in turn can change the applicability of rules with negation. To solve these open problems, we propose chain stratification as a robust new condition that guarantees a well-behaved semantics for RDF rules with negation, and existential rules in general. Our condition combines an elaborate analysis of potential multistep derivations with a mechanism for using integrity constraints to discard impossible cases. Applying rules in any order that respects chain stratification is guaranteed to derive an RDF graph that is unique, lean, and justified under the usual negation-as-failure semantics. To show the practicality, we also provide a prototype implementation. --- ### Self-Supervised Skill Optimization Authors: Siran Peng, Cuiyu Yang, Tianyu Fu, Tianshuo Zhang, Haoyuan Zhang, Weisong Zhao, Anyang Su, Minghui Wu, Huiying Li, Xiangyu Zhu, Chenxu Zhao, Zhen Lei Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.28777v1 Agent skills provide frozen large language model (LLM) agents with reusable procedural guidance, and recent work shows that such skills can be optimized with ground-truth (GT) feedback. Many applications, however, lack GT labels, task scores, rewards, or reliable task-specific evaluators. We therefore introduce Self-Supervised Skill Optimization (SSO), a comparative framework that learns a reusable skill from unlabeled task instances alone. At each step, SSO runs the current skill on an unlabeled batch, uses a subset of the resulting executions to generate complete skill probes, and runs the probes on the same batch. An LLM judge compares the resulting answers, trajectories, artifacts, or terminal states. A separate behavior extractor identifies behavioral differences without seeing the judge's decisions. SSO uses these decisions to aggregate evidence for and against the observed behaviors across instances. It then ranks the behaviors by the resulting evidence and renders a new complete skill from the highest-ranked behaviors. The update is accepted only if the new skill outperforms the current one on an unlabeled validation set. SSO outperforms existing GT-free prompt optimizers on both closed-ended and open-ended tasks. On closed-ended benchmarks, it approaches and sometimes exceeds the strongest GT-based skill optimizer without using any GT feedback. --- ### Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation Authors: Paul Hagemann, Katharina Ueltzen, Simon Müller, Janine George, Philipp Benner Published: 2026-07-30 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2607.28776v1 Generative machine learning is increasingly used for inorganic crystal structure generation. Most models and the corresponding evaluation approaches rely on simple forms of crystal structure representation. In this paper, we showcase the power of atom-averaged features from pretrained Machine-Learning Interatomic Potentials (MLIPs), such as MACE, for such tasks. We first introduce a distance measure that assesses the output of material generative models by capturing both quality and novelty in a single distribution-based evaluation framework. In particular, we introduce the Coarse-Fine Transport Distance (CFTD) using two different featurizers, where the quality component is based on coarse MACE features. We showcase CFTD's versatility in capturing crystal-structure quality while also detecting memorization, and compare it with the recently introduced continuous SUN metrics. We further show that coarse MACE features can be used as guidance for a material generative model. --- ### Do Medical Foundation Models Generalize on the African Brain? Authors: Kaouther Mouheb, Gonzalo Esteban Mosquera Rojas, Juancito van Leeuwen, Stefan Klein, Esther E. Bron Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28771v1 Medical foundation models (FMs) are increasingly used for brain MRI analysis. However, their evaluation remains dominated by high-resource datasets, leaving generalization to African cohorts underexplored. We assess whether FMs generalize equally to African and non-African brain MRI data across two tasks: dementia classification using a Nigerian dataset and brain tumor segmentation using BraTS-Africa. We evaluate two generalist FMs (BrainIAC, 3DINO) and two segmentation-specific FMs (MedSAM2, Medical-SAM2) against a from-scratch baseline. For classification, FMs provide limited gains (highest ROC-AUC of 0.86 with BrainIAC), whereas for segmentation they consistently improve performance, reaching up to 0.86 Dice with MedSAM2. Performance differences between African and non-African cohorts are inconsistent and appear more related to dataset size than data origin. These results suggest that FMs do not exhibit an inherent bias against African cohorts, and highlight the limited availability and diversity of African neuroimaging datasets as the main barrier to robust evaluation and deployment. --- ### Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning Authors: Muhammad Umar Farooq, Kutub Uddin, Awais Khan, Khalid Malik Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28769v1 Security-critical biometric and forensic applications require accurate predictions and reliable confidence estimates, particularly under distribution shift. This challenge is especially acute for deepfake detection, where foundation-model-based detectors often exhibit overconfident predictions on out-of-distribution manipulations, which limits their suitability for operational deployment. We propose an uncertainty-aware deepfake detection framework that identifies manipulations through inconsistencies across complementary evidence sources. The framework integrates three streams: a visual stream based on an adapted CLIP encoder, a semantic stream that models consistency among facial attributes through differentiable constraints, and a structural stream that captures class-dependent dependency patterns between semantic and forensic features. To effectively combine these signals, we introduce Inter-Branch Disagreement Calibration (IBDC), a disagreement-aware uncertainty modeling mechanism that links predictive uncertainty to conflicts among evidence streams. Extensive cross-dataset experiments using FaceForensics++ as the training source demonstrate that the proposed framework achieves state-of-the-art generalization across multiple out-of-distribution benchmarks while consistently improving calibration and selective prediction performance. These results show that combining complementary evidence with disagreement-aware uncertainty provides a robust foundation for trustworthy and well-calibrated deepfake detection under distribution shift. --- ### The Morphological Core of Dungan: A Two-Dialect Finite-State Model and a Multi-Genre Evaluation Authors: Anton M. Alekseev, Sergey I. Nikolenko Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.28766v1 Dungan, a Sinitic language of Central Asia written in a Cyrillic-based script, is described in detail in the grammatical literature, yet the quantitative properties of its morphology in actual usage have, to the best of our knowledge, never been measured systematically. This paper uses a finite-state morphological analyzer as a measuring instrument. Implemented with HFST and covering both dialect groups (the Gansu variety, which is the literary standard, and the Shaanxi variety), the model offers no new grammatical description; it formalises the knowledge accumulated in Dungan studies and makes it measurable on corpora of three genres. Three results follow. Overt inflection is rare and limited: only 9.3% of recognized tokens in the encyclopaedic register have an overt marker, the system has just ten categories, and degree marking is almost absent. Ambiguity is genuine but sharply localized: 78.1% of tokens receive a single analysis, and the residue sits almost entirely on two clitics, -di (genitive/progressive) and -ni (locative/prospective). And the grammatical core proves effectively closed, the claim the instrument is really needed for: between 78% and 95% of the tokens the analyzer fails on, depending on register, are simply absent from the lexicon, and the phenomena the model deliberately declines to implement account for at most 4.5% of those failures. Held-out coverage (80 to 85%) is no lower than development coverage (73%), while a stem list with no morphology already reaches 67.4%, so the morphology is worth 5.2 points. The open frontier of Dungan is lexical. The analyzer, its sources and every evaluation script are released openly. --- ### Feature Interaction Modeling for Neural Operators Authors: Quan Gu, Xiaoduo Li, Hongxia Liu Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28762v2 Despite the many variants of DeepONet that have been proposed, query-based operator networks still struggle with shock-dominated and low-viscosity PDEs, whose sharp moving discontinuities and slowly decaying solution spectra challenge finite-dimensional separable representations. In this work, we propose \emph{Feature Interaction Modeling Operator} (FM-Operator), a point-wise query neural operator that explicitly models feature construction and interactions between sensor observations and query coordinates. Our design is motivated by a reinterpretation of the canonical DeepONet aggregation through the lens of multiplicative interactions. Specifically, the branch--trunk inner product admits the equivalent form \(\boldsymbol{b}(u)^\top \boldsymbolτ(y)=\boldsymbol{1}^\top \operatorname{diag}(\boldsymbol{b}(u))\,\boldsymbolτ(y)\), revealing that the two representations interact only along corresponding latent dimensions and therefore constitute a diagonally constrained multiplicative interaction. This observation suggests that, beyond improving the individual branch and trunk networks, the structure through which function and query representations interact is itself an important inductive bias in point-wise operator learning. FM-Operator accordingly redesigns both feature construction and feature interaction, enabling structured information exchange beyond the conventional branch--trunk coupling while retaining point-wise query evaluation. Experiments across multiple PDE benchmarks demonstrate that FM-Operator consistently outperforms vanilla DeepONet and achieves clear improvements over the strong Shift-DeepONet baseline. These results suggest that explicitly designing representation construction and interaction provides a promising direction for improving the effectiveness of DeepONet-style query-based neural operators. --- ### Feature Interaction Modeling for Physics-Informed Neural Networks and Neural Operators Authors: Quan Gu, Hongxia Liu Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28762v1 This work embeds feature interaction modules derived from factorization machines (FMs) into physics-informed neural networks (PINNs) and neural operator learning, to enhance model expressiveness for solution manifolds of parameterized partial differential equations (PDEs). Motivated by the second-order Taylor expansion of multivariate functions to characterize variable couplings, we first propose FM-PINN. It explicitly captures spatio-temporal variable interactions and improves the approximation accuracy for smooth high-order PDEs. We further group spatial coordinates, time, physical parameters, and initial and boundary conditions into independent feature sets and model their cross-group interactions. Based on this strategy, we develop FM-Operator and FM-DeepONet, which are particularly effective for nonlinear conservation laws and problems with sharp gradients or discontinuities, while offering no consistent advantage on smooth operator learning benchmarks. Numerical tests demonstrate that the proposed mechanism delivers substantial accuracy gains on challenging shock-dominated equations, indicating a promising direction for physics-consistent modeling of parameterized PDEs with strong cross-field dependencies. --- ### WaiT for the Signal: Simple Frequency-Aware Flow-Matching Authors: Krunoslav Lehman Pavasovic, Théophane Vallaeys, Stéphane Mallat, Giulio Biroli, Luke Zettlemoyer, Brian Karrer, Jakob Verbeek Published: 2026-07-30 Categories: cs.CV, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.28760v1 As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flow matching treats all spatial frequencies uniformly, ignoring the natural frequency hierarchy where high-frequency bands become indistinguishable from pure noise far earlier than coarse structures. We introduce WaiT, a Wavelet-aware image Transformer that decomposes generation into coarse and fine bands via lossless wavelets. True to its name, the high-frequency bands wait for the signal: staying pure noise until coarse structure has emerged, then joining the flow for joint refinement. Since standard FID discards fine-grained detail through aggressive downsampling, we introduce a more stringent three-axis evaluation protocol to assess quality at native resolution. On ImageNet 512x512, WaiT achieves a pixel-space FID of 1.43 and is Pareto-optimal across all three axes, reducing sampling compute by up to 50%. With our largest 2B model, we set a new state-of-the-art FID of 1.3 for pixel-space models on ImageNet 512 resolution. Our formulation outperforms even the strongest latent-space models on texture fidelity, and scales seamlessly to high-resolution OpenImages and to video generation, achieving a state-of-the-art FVD of 0.84 on Kinetics-600 with no algorithmic modifications. --- ### SCMA: Structure-Conditioned and Metal-Aware Flow Matching for CT Metal Artifact Reduction Authors: Heran Wang, Jianing Sun, Xu Jiang, Genwei Ma, Jigang Duan, Xing Zhao Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.28759v2 In X-ray CT, metallic objects cause beam hardening, photon starvation, and scattering, leading to projection inconsistency, streaks, dark bands, and structural distortions that compromise clinical diagnosis and quantitative analysis. Existing metal artifact reduction (MAR) methods remain limited: optimization-based methods may leave residual artifacts or blur structures, regression networks may generalize poorly across scenarios, and generative models without sample-specific structural guidance and physical constraints may produce anatomically inconsistent structures. Flow Matching learns a continuous-time velocity field that deterministically transports a source distribution to a target distribution, providing a flexible MAR prior. However, standard unconditional Flow Matching does not exploit sample-specific structure, spatially nonuniform metal-induced degradation, or measured projections. To address these limitations, we propose SCMA, a structure-conditioned and metal-aware Flow Matching framework. First, a linear-interpolation-corrected image is fed into the velocity network with the intermediate state as a sample-specific structural condition, guiding inference toward artifact-free CT images while preserving anatomy. Second, time-varying spatial weights from the metal mask and its distance transform are incorporated into the Flow Matching loss to emphasize severe degradation within and around metal regions. Finally, conditional Flow Matching updates alternate with projection-consistency correction during inference, allowing reliable measurements outside metal traces to constrain predictions. Experiments on simulated and real CT data demonstrate that SCMA more effectively suppresses metal artifacts, preserves local anatomical structures, and reduces hallucination-like structures inconsistent with projection measurements than representative MAR methods. --- ### TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning Authors: Brendan Kennedy, Tegan Emerson, Gregory Roek, Emilie Purvine, Henry Kvinge Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28755v1 Over the last decade, neural networks have been applied to an increasingly diverse range of applications, including data with rich geometric, topological, or symmetry-related structure. As a result, researchers have increasingly drawn inspiration from topology, algebra, and geometry. Despite this rich algorithmic development, the supporting software ecosystem remains fragmented. Many important methods exist only as research prototypes in unmaintained repositories. We address this by introducing Topology, Algebra, and Geometry Torch (TAGTorch), an open-source, PyTorch-based library that unifies tools inspired by topology, algebra, and geometry, including data-preprocessing methods, architectures, training techniques, and model analysis tools. We describe the design philosophy of TAGTorch and then discuss its current architecture and capabilities, highlighting areas where it can fill gaps in the current software ecosystem. We conclude with a discussion of our future development priorities for the library. --- ### ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding Authors: Shijie Wang, Xiangzhao Hao, Yueti Li, Guangyu Cao, Xinyu Tang, Haiyun Guo Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28751v1 Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding or add computation through explicit rationale tokens and latent autoregressive states. Although token expansion can improve complex matching, serial generation increases retrieval latency and makes the final embedding depend on generated intermediate states. This raises a different question: can useful computation be expanded along model depth while keeping the token workspace fixed? We analyze positive-negative similarity separation at every layer of independently trained UME models and observe a shared progression: early layers contextualize multimodal inputs, a contiguous middle-to-late stage forms retrieval-discriminative features, and the final layers map them into the embedding space. Based on this finding, we propose ReLoop-UME, which executes the early layers once, recurrently reuses a parameter-shared retrieval-forming block, and applies the final mapping layers after the last loop. Learnable Retrieval Registers provide persistent retrieval-specific states that accumulate and exchange evidence across loops, with the final register serving as the embedding readout. On MMEB-V2 and MRMR, ReLoop-UME consistently improves retrieval across different backbones while running 44.9x faster than UME-R1 and 1.5x faster than PLUME. --- ### DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing Authors: Sowjanya Puligadda, Mengdie Zhang, Ali Zamani, Dhruva Dixith Kurra, Eric Chen, Juan Marcano Published: 2026-07-30 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.28750v2 As mobile applications grow in complexity, traditional End-to-End (E2E) testing frameworks struggle with UI volatility, maintenance overhead, and cross-platform scalability. This paper presents DragonCrawl, an AI-driven mobile testing system for continuous regression testing that has evolved from embedding-based similarity matching to generative intent-based reasoning using large language models. Unlike prior LLM-based testing research focused on exploratory testing and crash detection, DragonCrawl validates specific user flows on every code change, blocking commits that break critical functionality. By leveraging GPT-4o's multimodal capabilities, DragonCrawl achieves 91.6% pass rate on iOS and 92.2% on Android across 1,013 automated tests running continuously in CI/CD pipelines. The system reduces test onboarding time from 96-120 hours to under 4 hours and has saved an estimated 27 developer years in test maintenance effort. We present the architectural evolution from V1 (semantic embedding matching) to V2 (generative intent-based reasoning), discuss implementation challenges including token explosion and memory constraints, and report operational experience from production deployment. The integration of multimodal vision for end-state detection and tool calling for backend state transitions enables comprehensive regression testing that bridges UI interactions with system state. Our results demonstrate that AI-driven testing can maintain stability while eliminating the brittleness of traditional automated tests, enabling continuous quality assurance at scale. --- ### Mirror Learning Authors: Yunpeng Liu, Matthew Niedoba, Oluwanifemi A. Adekanye, Jason Yoo, Yingchen He, Berend Zwartsenberg, Frank Wood Published: 2026-07-30 Categories: cs.LG, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.28737v1 We investigate imitation learning through the lens of third-person observation and propose a framework for mirror learning: acquiring actionable policies from passive observation. While behavior cloning (BC) excels under dense, well-aligned first-person data, it fundamentally fails to leverage the rich observational signals arising from third-person demonstrations that humans and animals routinely exploit. We introduce a method that composes (i) a learned perspective transformation that places learners in demonstrators' shoes using a fine-tuned video diffusion model and (ii) an inverse dynamics model that infers action trajectories in the learners' control space. This enables the synthesis of mirror data, pseudo first-person expert data generated from third-person observations of demonstrator behavior. Empirically, we show that mirror data alone can train effective policies, and that augmenting first-person BC training with mirror data further improves downstream policy performance. Our results suggest that modern generative world models implicitly encode sufficient structure to enable a scalable and safe alternative to teleoperation-heavy data collection. --- ### A user's guide to PINNs in geometric analysis: lessons from the asymptotic Plateau problem Authors: Tancredi Schettini Gherardini Published: 2026-07-30 Categories: math.DG, cs.AI, hep-th, math.AP arXiv: https://arxiv.org/abs/2607.28733v1 This proceedings contribution elaborates on the findings of arXiv:2605.26234v2: a joint work with Marco Usula, where we introduced a machine learning framework based on physics-informed neural networks (PINNs), aimed at constructing near-minimal discs in hyperbolic space asymptotic to a prescribed knot at infinity. We used this method to provide numerical evidence for a conjecture of Joel Fine relating minimal surfaces in $H^{4}$ to the coefficients of the HOMFLY polynomial. This is a methodological companion to that paper, based on a presentation given at the 2026 edition of the workshop "DANGER: Data, Numbers, and Geometry". Rather than reviewing the results, which are presented extensively in the preprint above, we discuss the two aspects of the framework which, in our experience, determined whether the method worked at all. First, the geometry of the problem must be encoded in the architecture of the model, so that the boundary condition and asymptotics at infinity hold exactly for every value of the learnable parameters - leaving us with a single-component loss function; second, the evaluation of the PDE residual must be engineered with care to ensure that complete trainings can be performed in a reasonable time. On the latter point, we describe two implementation techniques which are not spelled out in detail in the original paper: replacing nested reverse-mode automatic differentiation with the forward propagation of second-order jets, and compiling the computational graph of the residual once instead of rebuilding it at every optimisation step. Together, on identical hardware, these two changes reduce the cost of a training step by a factor of roughly forty to fifty. We hope these methodological discussions can be useful for researchers in differential geometry and geometric analysis who wish to deploy PINNs on problems of their own. --- ### MMFGU: Multimodal Federated Graph Unlearning Authors: Haodong Lu, Zekai Chen, Weiwei Ji, Shihao Li, Xunkai Li, Xun Wu, Yinlin Zhu, Rong-Hua Li Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28708v1 Multimodal federated graph learning enables clients to collaboratively train graph models over structural, textual, and visual signals without sharing private local data. However, the presence of heterogeneous multimodal content also makes unlearning requests more frequent and fine-grained: users may delete accounts or interactions, remove a particular image or text while retaining the associated entity, or revoke the learned correspondence between retained modalities or graph attributes. Existing federated graph unlearning mainly handles entity/relation or client removal and cannot directly satisfy these multimodal requests. They introduce three challenges: removing only the requested information without damaging retained content, preventing the target from being recovered through remaining modalities or graph neighborhoods, and stopping related traces on other clients from re-entering the global model after aggregation. To address them, we propose \textsc{\textbf{MMFGU}}, a multimodal federated graph unlearning framework built around target-specific representation decoupling. \textsc{MMFGU} maps heterogeneous requests into unified target carriers, decouples requested representations while anchoring retained semantics, exposes and repairs propagated residuals with lightweight probes, and selectively purges affected clients through compact prototype and response signals. Experiments show that \textsc{MMFGU} effectively removes requested information, preserves retained graph utility, and achieves a $\boldsymbol{41.5\times}$ speedup over full retraining. --- ### Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models Authors: Sara Candussio, Daniel Scalena, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.28707v3 Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness of low- and high-entropy CoT step selection methods across various models and reasoning tasks, showing that entropy offers no advantage over random pruning in any evaluated setting. Moving from sentences to tokens, we then show that retaining low-entropy tokens seems effective only on mathematical benchmarks. We find this is due to the inherently low-entropy nature of numeric tokens, which also convey semantic content in such problems. Finally, we demonstrate that patching a subset of a few CoT tokens with their original activations recovers near-perfect full-trace performance, providing causal evidence that task information is not concentrated in a small set of CoT tokens identifiable by heuristics, but rather distributed across the full reasoning chain. --- ### Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models Authors: Sara Candussio, Daniel Scalena, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.28707v1 Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness of low- and high-entropy CoT step selection methods across various models and reasoning tasks, showing that entropy offers no advantage over random pruning in any evaluated setting. Moving from sentences to tokens, we then show that retaining low-entropy tokens seems effective only on mathematical benchmarks. We find this is due to the inherently low-entropy nature of numeric tokens, which also convey semantic content in such problems. Finally, we demonstrate that patching a subset of a few CoT tokens with their original activations recovers near-perfect full-trace performance, providing causal evidence that task information is not concentrated in a small set of CoT tokens identifiable by heuristics, but rather distributed across the full reasoning chain. --- ### Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs Authors: Borna Khodabandeh, Mehdi Molkaraie Published: 2026-07-30 Categories: stat.ML, cs.IT, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2607.28706v1 We study the convergence properties of the random-sweep Gibbs sampler for Gaussian graphical models with a thin-membrane prior. We demonstrate that the convergence rate of the Gibbs sampler is significantly accelerated in the dual model, which is obtained by applying the Fourier transform to the local factors of the normal factor graph representing the original model. In both domains, we derive the exact convergence rates for homogeneous $k$-regular graphs. We prove that, for all homogeneous models whose graphical representations contain cycles, the convergence rate in the dual domain is universal and independent of the underlying graph topology. Moreover, we show that the effective convergence rate in the dual domain is governed by the algebraic connectivity of the graph, providing an additional acceleration without increasing the computational complexity per sweep. We further establish an explicit algebraic relation between the covariance structures of the primal and dual models, enabling marginal statistics of the primal model to be recovered directly from those of the dual model. Finally, numerical experiments on several graph families confirm our theoretical results and demonstrate substantial improvements in the convergence rates in various settings. --- ### Simulative Anomaly Detection using 2D Tomography Authors: Moti Ben-Harush, Nimrod Teneh, Gregory Lukovsky Published: 2026-07-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.28701v1 We present a novel technique for predicting the imaging quality of anomalies such as cancer cells located inside organic tissues. This technique is useful for evaluating and designing RF tomography sensors. --- ### WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization Authors: Fanzhe Wei, Li Liu, Ziyang Wang, Chenyu Wang Published: 2026-07-30 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2607.28699v3 KV-cache quantization is validated today by offline benchmark averages; a deployed system cannot tell whether compression is damaging the request it is serving right now. We give it a provably sound runtime meter -- a "DTrace for KV quantization": a per-(layer, head, step) upper bound on the total variation between exact and compressed attention. The meter has two tiers: a deterministic band-norm-witness bound, sound for any cache-preserving black-box quantizer and for any query (adaptive-safe, worst-case Cauchy--Schwarz plus RoPE band-unitarity), and a tighter probabilistic certificate for a controlled subtractively-dithered INT8 quantizer under an explicit request-level failure budget (stated for non-adaptive queries; core theorems machine-checked in Lean 4). Three results. Observability: the meter enters SGLang through an env-guarded patch, and any scheme registered as one tensor function is measured in live serving. Repair: meter-driven gating -- risk-ranked where the witness is saturated, certified where it is informative -- empirically restores the quality floor at benchmark scale, e.g. raw-cast fp8 from 22.8 back to 79.7 on hard RULER tasks with the difference from uncompressed bounded at $(+0.0,+0.8)$ by a paired test. Analysis: aggressive schemes survive on cross-layer error cancellation, not per-step fidelity -- in a 28-layer sweep, no single layer's pollution alone loses anything (0/28) -- and the certified int8 cache serves $1.88\times$ more KV tokens at the same memory in SGLang. All artifacts, guards, and the Lean development are released at https://github.com/metask-ai/witcert-kv-certificates; every number regenerates from the shipped artifacts by one command. --- ### WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization Authors: Fanzhe Wei, Li Liu, Ziyang Wang, Chenyu Wang Published: 2026-07-30 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2607.28699v2 KV-cache quantization is validated today by offline benchmark averages; a deployed system cannot tell whether compression is damaging the request it is serving right now. We give it a provably sound runtime meter -- a "DTrace for KV quantization": a per-(layer, head, step) upper bound on the total variation between exact and compressed attention. The meter has two tiers: a deterministic band-norm-witness bound, sound for any cache-preserving black-box quantizer and for any query (adaptive-safe, worst-case Cauchy--Schwarz plus RoPE band-unitarity), and a tighter probabilistic certificate for a controlled subtractively-dithered INT8 quantizer under an explicit request-level failure budget (stated for non-adaptive queries; core theorems machine-checked in Lean 4). Three results. Observability: the meter enters SGLang through an env-guarded patch, and any scheme registered as one tensor function is measured in live serving. Repair: meter-driven gating -- risk-ranked where the witness is saturated, certified where it is informative -- empirically restores the quality floor at benchmark scale, e.g. raw-cast fp8 from 22.8 back to 79.7 on hard RULER tasks with the difference from uncompressed bounded at $(+0.0,+0.8)$ by a paired test. Analysis: aggressive schemes survive on cross-layer error cancellation, not per-step fidelity -- in a 28-layer sweep, no single layer's pollution alone loses anything (0/28) -- and the certified int8 cache serves $1.88\times$ more KV tokens at the same memory in SGLang. All artifacts, guards, and the Lean development are released at https://github.com/metask-ai/witcert-kv-certificates; every number regenerates from the shipped artifacts by one command. --- ### Flow Matching with Missing Data Authors: Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28698v1 Flow matching assumes fully observed training data, which many real-world applications rarely provide. We propose Missing-Data Flow Matching, which treats the missing coordinates of training samples as latent variables and averages the flow matching loss over the values they could take. We first prove the correction is exact rather than approximate. Under missing completely at random with true completions, the incomplete-data objective equals the complete-data objective, so missingness changes nothing about what flow matching learns and the entire difficulty relocates to the completion model. Our finite-sample analysis then answers design questions that the algorithm leaves open, and the answers are not the ones intuition suggests. Missingness transfers estimator variance rather than adding it, one completion per example already matches complete-data variance exactly, and under a fixed evaluation budget one completion is optimal. A learned completion model contributes a single irreducible bias, which we bound by its expected conditional Wasserstein distance to the true completion law. Experiments numerically validate the theoretical predictions, show that deterministic rather than frozen imputation is what collapses the generated distribution, and place our method alongside strong classical and deep imputation baselines on real tabular data. --- ### Mitigating Class-Tail Undercoverage in Medical Vision-Language Models under Clinical Shift Authors: Mushir Akhtar, M. Tanveer Published: 2026-07-30 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.28696v1 Medical vision-language models (VLMs) can retain high observed marginal coverage after clinical shift while substantially under-covering an individual disease class. The affected class varies with acquisition protocol and backbone geometry, so source prevalence does not reliably reveal the failure. Existing localized and tail-aware conformal methods respectively adapt to test neighborhoods and source-frequency tails, leaving held-out class-wise coverage failure unmodeled. We introduce Class-Tail Adaptive Localized Conformal Deferral (CALCoDe), a post-hoc reliability layer for frozen medical VLMs. Cross-fitted validation predictions identify classes at risk of undercoverage, and a disjoint calibration split estimates their class-conditional tail thresholds. CALCoDe combines each protected threshold with a localized conformal threshold using a one-sided maximum. The resulting set contains every label admitted by the localized rule, with additional protection confined to validation-identified classes. An independently calibrated support audit defers cases with insufficient inlier support. Under exchangeability among accepted examples within each protected class, CALCoDe provides finite-sample coverage at the prespecified guard level and contains the corresponding localized conformal sets; coverage on shifted external cohorts is evaluated empirically. Among standard conformal baselines and recent VLM-specific conformal methods evaluated across two dermatology shifts (HAM10000 to ISIC 2019 and HAM10000 to PAD-UFES-20) and four frozen VLM backbones (BiomedCLIP, OpenAI CLIP ViT-B/32, PubMedCLIP ViT-B/32, and MedSigLIP-448), CALCoDe is the only approach whose observed marginal and worst-class accepted coverage both reach 0.95 in all eight settings. On HAM10000 to ISIC 2019, its average worst-class accepted coverage is 0.970, compared with 0.926 for sTACP and 0.864 for LCP-VLM. --- ### Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning Authors: Aryuemaan Kumar Chowdhury Published: 2026-07-30 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.28695v1 Here is the plain text version optimized for arXiv's submission form. Custom macros (like \CV and \SI) have been converted to standard text/math so they render correctly on the webpage: Evaluating the fatigue life of structural steels conventionally requires mechanical testing lasting tens to hundreds of hours, making it impractical for rapid quality control. We present CV, a computer vision framework that estimates the fatigue life ($\log N_f$) of lightweight alloy steels directly from optical micrographs without physical testing.The pipeline features a seven-stage OpenCV preprocessing routine to remove artifacts, a 28-dimensional physics-informed feature extractor (quantifying crack morphology, grain structure, porosity, and texture), and a CNN regression model trained with a Gaussian negative log-likelihood (GNLL) loss to jointly predict $\log N_f$ and sample-specific uncertainty $\hatσ$.Evaluating three architectures (SE-CNN, ResNet-50, VGG-16) on a synthetic micrograph benchmark, ResNet-50 achieves $R^2 = 0.93$, RMSE = 0.18 log-cycles, and macro-F1 = 0.91. The GNLL objective reduces Expected Calibration Error by 76% compared to a mean-squared-error baseline (ECE: $0.089 \rightarrow 0.021$). Grad-CAM maps confirm the network attends to metallurgically meaningful microstructural features.Running in under 65 ms per image, the pipeline and synthetic dataset generator are open-sourced. Because validation relies entirely on synthetic micrographs, these results demonstrate methodological soundness under simulated conditions; a domain-transfer study on real field samples is the immediate next step. --- ### SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM Authors: Hatem Haddad, Feres Jerbi, Issam Smaali Published: 2026-07-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.28693v1 Industrial NILM remains challenging because measurement noise and widespread concurrent machine operation reduce the generalization of models tuned on residential data. This work adopts a one-to-many, multi-task disaggregation setting, in which a single network estimates multiple industrial machine loads from aggregate power. Under a unified evaluation protocol on IMDELD, we benchmark Seq2Seq, Seq2SubSeq, Seq2Point, GRU, and WaveNet using energy-estimation metrics and the accuracy-delay criterion. While Seq2Point offers a stronger accuracy-delay balance than Seq2Seq/Seq2SubSeq, GRU and WaveNet achieve higher accuracy at markedly higher computational cost. To close this gap, we propose SEDR-Seq2P, a lightweight Seq2Point extension with dilated residual blocks and squeeze-and-excitation attention. Relative to the Seq2Point baseline, SEDR-Seq2P reduces MAE by approximately 7%, improves the coefficient of determination by approximately 1%, and increases the match rate by approximately 0.8%. In addition, compared to WaveNet, SEDR-Seq2P reduces inference latency by approximately 58%, yielding a favorable accuracy-delay trade-off for scalable industrial deployment. --- ### SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition Authors: Yuqi Tang, Chenyi Zhou, Libin Wang, Keyan Ding, Qiang Zhang, Huajun Chen Published: 2026-07-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28692v1 Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools. However, their reliance on predefined tool spaces with static semantics limits their applicability to open-world scientific workflows, where tool requirements, capabilities, and boundaries evolve dynamically. To this end, we propose SciToolAgent-Evo, an ontology-aware self-evolving agent for open-world scientific tool acquisition. Driven by an evolving memory of skills, experiences, and an ontologized tool graph, it distills generalizable knowledge from contrastive trajectories during accumulation, whereas during inference, it formulates active requests and utilizes a LinUCB-based bandit gate to dynamically balance exploration and exploitation. Once a novel tool is acquired, its scientific ontology is completed online for seamless integration into the known graph. Moreover, we introduce OpenSciToolBench, a benchmark containing 900 realistic tasks across four difficulty levels. Extensive evaluations show that SciToolAgent-Evo achieves state-of-the-art performance, validating its robustness and generalization. --- ### Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descent Authors: Roy Zhao, Zhenyu Zhao Published: 2026-07-30 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.28691v1 Personalized AI agents are often configurable without giving users control over the artifacts that determine their future behavior. We present OurArk, an architecture for persistent personal agents centered on an agent-owned software body: an identity-bearing, inspectable, and versioned artifact under human custody. The body contains behavior-defining code, prompts, tools, skills, policies, tests, and evolution mechanisms. Memories and credentials remain private instance state, while model inference is treated as a replaceable external service. OurArk defines governed self-evolution and recursive descent over the same body. Self-evolution produces isolated candidate changes that are validated, reviewed, and merged under human control, enabling human-agent co-development of the agent's software body. Descent creates an independently versioned descendant with a distinct identity, mission, history, and fresh private-state boundary; compatible descendants can themselves source further descent. After divergence, direct-parent changes and peer skills can be inspected for selective local adaptation. We implement the architecture in the open-source Genesis creation engine and Enoch reference agent. A four-agent, three-descent linear lineage and executable regression tests demonstrate recursive creation, inherited validation contracts, isolated body changes, human-controlled review, and failed-update recovery. OurArk provides a concrete substrate for personal agents that people can possess, govern, specialize, and evolve over time. --- ### Reflected UAS: Corrected Deterministic Stability and Direct CTMC Drift Calculation Authors: Krishna Subedi Published: 2026-07-30 Categories: cs.PF, cs.AI, math.PR arXiv: https://arxiv.org/abs/2607.28688v1 We analyze Reflected UAS routing for heterogeneous multi-server queues at fixed parameters under subcritical load. The deterministic surrogate is a reflected ODE on the nonnegative orthant, not the unconstrained drift equation. This reflected ODE has a unique boundary equilibrium characterized by a scalar consistency equation and a convex-potential representation; all trajectories converge to it. The older argument lifting deterministic Lyapunov descent to CTMC stability fails: the exact generator applied to the deterministic potential produces a boundary term absent from the reflected-ODE descent identity. We give a direct Foster-Lyapunov drift inequality for the CTMC using a weighted-quadratic function, bypassing the failed lift. At the benchmark parameter point, the boundary equilibrium matches the numerical attractor to machine precision, and the default Reflected UAS policy has lower mean queue length than UAS and JSSQ across independent seed blocks. --- ### Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions Authors: Mohammad Asif, Azizuddin Khan, Mohd Azam, Anurag Rajkumar Bombarde Published: 2026-07-30 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2607.28687v2 As populations age, cognitive decline from mild cognitive impairment (MCI) to dementia is a defining health challenge of the coming decades, yet routine assessment often misses its earliest signs. This article critically synthesizes recent technological advances for detecting and managing cognitive impairment in older adults, spanning neurophysiological signals (chiefly electroencephalography, EEG), structural and molecular neuroimaging (MRI and amyloid/tau PET), blood-based biomarkers, and digital markers, integrated through artificial intelligence (AI), machine learning (ML), and deep learning (DL). Beyond summarizing, it contributes a cross-disciplinary taxonomy, a methodological-rigor lens foregrounding subject- and site-independent validation, an integrative early-detection framework linking tiered screening to intervention, and comparison tables of detection methods, interventions, and risk and protective factors. EEG markers (alpha/theta changes, P300 latency) and deep models (CNNs, LSTM/BiLSTM, transformers, self-supervised EEG foundation models) report strong accuracy, yet many rest on small, single-site datasets unlikely to survive rigorous external validation. Elsewhere, gains are tangible: plasma p-tau217 has reached clinical utility, with the first blood test cleared to aid Alzheimer's diagnosis in 2025; anti-amyloid therapies (lecanemab, donanemab) are approved despite modest, contested benefits; and multidomain lifestyle prevention has matured. Wearable, remote, speech, and virtual-reality tools enable continuous, ecologically valid monitoring, and multimodal fusion improves sensitivity and specificity. Barriers remain: standardization, explainability, data privacy, and equitable, externally validated deployment. The field's near-term promise lies in trustworthy, multimodal, longitudinally validated systems linking early detection to actionable, personalized care. --- ### Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions Authors: Mohammad Asif, Azizuddin Khan, Mohd Azam, Anurag Rajkumar Bombarde Published: 2026-07-30 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2607.28687v1 As populations age, cognitive decline from mild cognitive impairment (MCI) to dementia is a defining health challenge of the coming decades, yet routine assessment often misses its earliest signs. This article critically synthesizes recent technological advances for detecting and managing cognitive impairment in older adults, spanning neurophysiological signals (chiefly electroencephalography, EEG), structural and molecular neuroimaging (MRI and amyloid/tau PET), blood-based biomarkers, and digital markers, integrated through artificial intelligence (AI), machine learning (ML), and deep learning (DL). Beyond summarizing, it contributes a cross-disciplinary taxonomy, a methodological-rigor lens foregrounding subject- and site-independent validation, an integrative early-detection framework linking tiered screening to intervention, and comparison tables of detection methods, interventions, and risk and protective factors. EEG markers (alpha/theta changes, P300 latency) and deep models (CNNs, LSTM/BiLSTM, transformers, self-supervised EEG foundation models) report strong accuracy, yet many rest on small, single-site datasets unlikely to survive rigorous external validation. Elsewhere, gains are tangible: plasma p-tau217 has reached clinical utility, with the first blood test cleared to aid Alzheimer's diagnosis in 2025; anti-amyloid therapies (lecanemab, donanemab) are approved despite modest, contested benefits; and multidomain lifestyle prevention has matured. Wearable, remote, speech, and virtual-reality tools enable continuous, ecologically valid monitoring, and multimodal fusion improves sensitivity and specificity. Barriers remain: standardization, explainability, data privacy, and equitable, externally validated deployment. The field's near-term promise lies in trustworthy, multimodal, longitudinally validated systems linking early detection to actionable, personalized care. --- ### Optical Flow Sensor: A Direction-Selective Bionic Retina Design Authors: Juchen Zhou, Bonan Yan, Yuchao Yang Published: 2026-07-30 Categories: cs.AR, cs.CV, cs.ET, eess.IV arXiv: https://arxiv.org/abs/2607.28686v1 Optical flow characterizes motion in the visual field and is fundamental to motion perception and tracking in biological and artificial vision systems. Biological retinas extract motion efficiently through local ON/OFF pathways and parallel processing, while conventional frame-based optical flow relies on dense sampling and global computation, resulting in high latency and power consumption. To overcome these limitations, we present a pixel-level Optical Flow Sensor (OFS) integrated circuit. The design combines Dynamic Vision Sensor (DVS) ON/OFF event comparison with time-difference measurement to enable fully parallel optical flow computation on-chip. An optical-flow-specific Address-Event Representation (OF-AER) interface supports low-power, high-throughput readout. \rev{Based on the CMOS-based OFS, we further propose optical memristor-based OFS to reduce sensor power consumption and area overhead.} Experimental results show that the proposed OFS achieves a 303$\times$ reduction in power consumption compared with FPGA-accelerated DVS systems while maintaining microsecond-level latency. Moreover, by directly outputting optical flow vectors, the OFS reduces output data size by approximately 3.3$\times$, demonstrating strong potential for ultra-high-speed, low-power vision sensing applications. --- ### Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks Authors: Youting Wang, Xiao Han, Dingyan Shang, Yuan Tang, Bowen Liu Published: 2026-07-30 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.28685v1 Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by $F_1$, an ``always positive'' policy attains $F_1 = 2π/(1+π)$; on R-Judge that is $0.690$, above five of the 21 models that actually discriminate. The three broad-coverage benchmarks then rank the same 18 models differently, and the trade-off behind that disagreement is a small-panel artifact: R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n{=}7$ and $+0.02$ at $n{=}18$, and a quarter of random size-7 subsets reach $|ρ| \geq 0.5$ around that near-zero value. Held-out validity turns on which outcome you pick. Capability predicts task success ($ρ{=}{+}0.60$) but correlates negatively with misalignment safety ($ρ{=}{-}0.44$, $n{=}21$). On their paired $n{=}20$ panel, the corresponding contrast is $Δ{=}{-}1.00$ (95% CI $(-1.48, -0.49)$, $p<0.001$), and it survives leave-one-organization-out and organization-clustered bootstrap analyses. On an expanded 41-model panel, the misalignment correlation weakens to $-0.16$ (95% CI $(-0.54, +0.22)$) and jailbreak strengthens to $+0.34$, though neither change is significant. \mbox{AgentHarm} shows the strongest held-out association, $ρ{=}{+}0.72$ with three-template jailbreak safety after controlling capability. But both instruments score harmful compliance, so this is evidence of convergent validity rather than general safety. Naming the benchmark, metric, target behavior, and model panel is the minimum a safety claim needs. --- ### Library Reachability in LSR-Synth: How Anti-Memorization Design Changes the Measurement of Symbolic Discovery Authors: Zhan'ao Yao, Liang Yin, Zhihao Gao, Boxuan Zhang, Xiaoyu Wu, Linjing Li, Rongyan Wang, Tingwei Chen, Youwei Wang, Xiaolin Zhao, Jiahui Shi, Jianjun Liu Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28684v1 Existing benchmarks for scientific equation discovery are largely composed of well-known equations available in the public domain, making it difficult to determine whether a model is discovering laws from data or merely recalling answers from its training corpus. LSR-Synth mitigates this problem by introducing novel synthetic terms into established scientific mechanisms and filtering the resulting tasks for novelty, solvability, and scientific plausibility. This paper examines a narrower measurement question: can these tasks further distinguish scientific priors supplied by language models from conventional operator search that does not access task semantics? We construct a semantics-free baseline using a fixed vocabulary with publicly documented provenance, and assess the role of candidate coverage through semantic blinding, library weakening, and matched operator-family knockouts. Under the current task snapshot, search budget, and scoring protocol, the fixed vocabulary already covers most tasks, while language-model-generated candidates rarely expand the set of solvable instances. Their marginal contribution becomes substantial only when vocabulary coverage is selectively disrupted. Strict out-of-distribution evaluation lowers the absolute success rates of all methods but does not alter this relationship. These findings neither invalidate LSR-Synth's controls against memorization of complete formulas nor imply that language-model priors are generally unhelpful. Rather, they support a more limited conclusion: most current tasks remain suitable for evaluating the fitting and recombination of previously unseen expressions, but are insufficient on their own to identify contributions from priors beyond a fixed search space. --- ### Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation Authors: Zhibo Hu, Chen Wang, Yanfeng Shu, Hye-young Paik, Liming Dong, Liming Zhu Published: 2026-07-30 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.28683v1 Large language models benefit from elements in natural language, such as metaphors and analogies in training data and inference input to achieve generalisability across different domains. However, these language elements may also lead to unwanted behaviors when metaphorical expressions implicitly transfer inappropriate procedural patterns into new tasks. In this paper, we show that metaphorical instructions can induce analogical transfer of procedural mechanisms, thus steering code-generation models towards less efficient algorithms. We refer to this metaphor-induced effect as metaphorical algorithmic steering: a skill that is benign and plausible within its source domain transfers an abstract procedural schema into a programming task, causing the model to favor exhaustive search, full scans, or repeated reconstruction without explicitly mentioning the target algorithm. More broadly, this suggests that code-generation models can carry procedures that are appropriate in a task's background domain into the task's programming problem, where they can lead to unwanted outcomes. To study this phenomenon, we develop MASC (Metaphorical Algorithmic Steering for Code Generation), a framework that iteratively metaphorizes and refines benign skills to elicit low-efficiency code while remaining benign and task-relevant. Beyond behavioral evaluation, we study whether this phenomenon is detectable and mechanistically reflected in model representations. Our method achieves high detection rates for metaphorical skills and less-efficient implementations. We also find that metaphorical skills induce a hidden-state shift towards lower-efficiency procedural behavior prototypes. These results suggest that metaphorical algorithmic steering operates through the transfer of procedural patterns associated with metaphorical source scenarios rather than surface level metaphorical language alone. --- ### Learning to Trace Seiberg Dualities Authors: Jonathan J. Heckman, Shani Meynet, Alessandro Mininno, Gary Shiu Published: 2026-07-30 Categories: hep-th, cs.AI, cs.LG, hep-ph arXiv: https://arxiv.org/abs/2607.28628v2 Dualities play an important role in establishing both microscopic and emergent phenomena in a wide range of physical systems. In practice, though, it can often be computationally challenging to establish when two systems are dual, even when all of the "rules of the game" are well-known. Said differently, when confronted with two systems, how can one efficiently establish that they are in fact dual? In this paper we use machine learning methods to address this question for Seiberg dualities of supersymmetric quiver gauge theories. Mathematically, this involves establishing mutations of quivers, which is in turn a variation on the theme of "learning to unknot". On the one hand, this leads us to a practical tool for establishing the computational complexity of different dualities. On the other hand, it also allows us to study how different network architectures learn how to trace Seiberg dualities. We find that for quivers with a modest number of quiver nodes (of order $10$), different network architectures consisting of transformers and multi-layer perceptrons tend to outperform deterministic algorithms. Supplementing the network by well-established pathfinder algorithms (essentially "Google Maps for quivers") leads to an additional improvement in the efficiency and accuracy of the search strategy. We anticipate that this class of questions can serve as a useful benchmark for frontier AI models applied to theoretical physics. --- ### Learning to Trace Seiberg Dualities Authors: Jonathan J. Heckman, Shani Meynet, Alessandro Mininno, Gary Shiu Published: 2026-07-30 Categories: hep-th, cs.AI, cs.LG, hep-ph arXiv: https://arxiv.org/abs/2607.28628v1 Dualities play an important role in establishing both microscopic and emergent phenomena in a wide range of physical systems. In practice, though, it can often be computationally challenging to establish when two systems are dual, even when all of the "rules of the game" are well-known. Said differently, when confronted with two systems, how can one efficiently establish that they are in fact dual? In this paper we use machine learning methods to address this question for Seiberg dualities of supersymmetric quiver gauge theories. Mathematically, this involves establishing mutations of quivers, which is in turn a variation on the theme of "learning to unknot". On the one hand, this leads us to a practical tool for establishing the computational complexity of different dualities. On the other hand, it also allows us to study how different network architectures learn how to trace Seiberg dualities. We find that for quivers with a modest number of quiver nodes (of order $10$), different network architectures consisting of transformers and multi-layer perceptrons tend to outperform deterministic algorithms. Supplementing the network by well-established pathfinder algorithms (essentially "Google Maps for quivers") leads to an additional improvement in the efficiency and accuracy of the search strategy. We anticipate that this class of questions can serve as a useful benchmark for frontier AI models applied to theoretical physics. --- ### ReToken: One Token to Improve Vision-Language Models for Visual Retrieval Authors: Yao Xiao, Reuben Tan, Zhen Zhu, Yuqun Wu, Jianfeng Gao, Derek Hoiem Published: 2026-07-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.28627v1 Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We present ReToken, a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache. Trained on only a small image-QA dataset, ReToken yields consistent gains across image and video benchmarks: on Visual Haystacks it improves Qwen3VL-8B by 13.4 points and InternVL3.5 by 12.4 points (>20% relative), and on LVBench it transfers zero-shot to long video for an 8.0-point gain with Qwen3VL-8B. Thanks to its lightweight design, both training and long-video inference fit on a single H100. Code is available at: https://github.com/avaxiao/ReToken --- ### ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine Authors: Yukang Cao, Haozhe Xie, Beichen Wen, Runmao Yao, Yinghao Liu, Yue Huang, Zhichao Liao, Yunxiang Wang, Haiheng Liu, Xingshun Tian, Dawei Su, Long Zhuo et al. Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28625v1 Embodied intelligence faces a fundamental data bottleneck. Models must capture how first-person perception, whole-body motion, dexterous manipulation, object state, sound, and touch evolve together as humans pursue goals over time. Existing datasets fragment this experience across viewpoints, modalities, or spatial scales, leaving the full perception-action loop only partially observed. We introduce the Ambient Capture Engine (ACE), a human-centric data engine that transforms real home environments into spatially calibrated, temporally synchronized recording studios. ACE operates at two complementary scales: a table-scale configuration resolves hand-object manipulation, while a room-scale configuration captures whole-body motion, locomotion, and interactions across a furnished home. ACE records egocentric and multi-view exocentric video, full-body and articulated hand motion, object geometry and 6-DoF trajectories, audio, and tactile signals as a unified multisensory stream. Using ACE, we build ACE-Data-0, comprising 150 hours and 17M video frames across 200 task categories, performed by 50 participants in 2 environments, for a total of 75,000 interaction episodes. The dataset spans atomic manipulation, long-horizon chains of household activities, and human-scene interaction, while preserving natural behavioral variation through goal-level rather than step-by-step instructions. We further introduce a hierarchical benchmark that progresses from signals to scene components and then to interactions. Evaluations of state-of-the-art methods expose substantial gaps under contact, occlusion, egomotion, and long temporal horizons. ACE-Data-0 provides synchronized human demonstrations with aligned perceptual, kinematic, and contact supervision, offering a scalable foundation for imitation learning, world models, vision-language-action systems, and embodied AI. --- ### PhiZero: A World Model Built Around Physical Language Authors: Shuyao Shang, Yuqi Wang, Ruopeng Gao, Xu Chen, Tieniu Tan, Lue Fan, Zhaoxiang Zhang Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28624v1 We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors. Motivated by humans' ability to abstract predictive structure from visual experience and organize it in natural language for explicit reasoning, we learn physical language from in-the-wild videos through self-supervision and use it to explicitly reason about how the physical world evolves. Accordingly, PhiZero adopts a reason-then-render paradigm: it first infers future world evolution as a physical-language sequence and then renders the inferred transitions into videos. Extensive experiments across generation and understanding benchmarks validate the ability of PhiZero to model physically coherent world evolution. We further show its potential for realistic and interactive world modeling, fine-grained action-conditioned simulation, and zero-shot motion transfer. --- ### PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball Authors: Lizhi Yang, Junheng Li, Aaron D. Ames Published: 2026-07-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.28623v2 We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance represents clearance to every body link, and an adversarial motion prior regularizes the resulting evasive reflexes. We evaluate on a controlled any-link contact benchmark with seeded throws in two regimes: single throws and a deployment loop in which the robot walks back to its station and recovers between throws. On this benchmark, the policy comes within a few points of a privileged state oracle: a fixed onboard camera alone is adequate for evasion. We find that usable barrier structure depends on perceptual observability: Joint-CBF gives the best performance with accurate ball states, degrades under fixed-camera observations when used only as training guidance, and recovers with a ball-tracking gimbal or privileged runtime filter. We therefore deploy a lightweight Link-CBF policy zero-shot on the Unitree G1 in the real world, where it tolerates imperfect perception, succeeds on 95% of throws, and uses semantic segmentation to dodge different balls. --- ### PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball Authors: Lizhi Yang, Junheng Li, Aaron D. Ames Published: 2026-07-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.28623v1 We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance represents clearance to every body link, and an adversarial motion prior regularizes the resulting evasive reflexes. We evaluate on a controlled any-link contact benchmark with seeded throws in two regimes: single throws and a deployment loop in which the robot walks back to its station and recovers between throws. On this benchmark, the policy comes within a few points of a privileged state oracle: a fixed onboard camera alone is adequate for evasion. We find that usable barrier structure depends on perceptual observability: Joint-CBF gives the best performance with accurate ball states, degrades under fixed-camera observations when used only as training guidance, and recovers with a ball-tracking gimbal or privileged runtime filter. We therefore deploy a lightweight Link-CBF policy zero-shot on the Unitree G1 in the real world, where it tolerates imperfect perception, succeeds on 95% of throws, and uses semantic segmentation to dodge different balls. ---