# Research Papers — 2026-09 · bundle page 112 of 266 > Full-text markdown of papers #5551–5600 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/112 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/111.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/113.md) ### PICPIs: Prediction-Interval-Conditional Prediction Intervals Authors: Xuelin Yang, Baihe Huang, Yilong Hou, Guido Imbens, Michael I. Jordan Published: 2026-09-21 Categories: stat.ML, cs.AI, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2609.25388v1 A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal prediction in nonparametric uncertainty quantification, standard marginal validity offers limited resolution at the prediction values on which decisions are based, and fully conditional guarantees with respect to the covariates are provably unattainable. We address this gap by introducing a prediction-based conditioning framework that we refer to as Prediction-Interval-Conditional Prediction Intervals (PICPIs). Formally, a PICPI is an interval $I$ satisfying a self-consistency condition: $$\mathbb{E} (Y \mid p(X) \in I) \in I,$$ for predictive model $p$, contextual covariate $X$, and outcome $Y$. Thus, an interval simultaneously defines a stratum of prediction values and certifies that the mean outcome in that stratum lies in the same interval. This self-consistency condition yields data-adaptive strata without altering the original prediction. Such intervals can be constructed using practical algorithms. Under regularity of the prediction distribution, the constructed intervals cover all but an arbitrarily small fraction of prediction values and have widths that decrease at rate $n^{-1/3}$, up to logarithmic factors and the prediction error. Moreover, identifying these locally calibrated intervals can, in turn, inform downstream decision-making. We derive inference procedures for PICPIs in probabilistic prediction and multi-class classification, accompanied by theoretical guarantees. Empirical results are provided that compare PICPIs with existing interval-based baselines. --- ### Sex Estimation from Footwear Outsole Impressions Using CNN Transfer Learning and Interpretable Image Statistics Authors: Jinyi Niu, Ziyi Song, Weining Shen Published: 2026-09-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.25386v2 Footwear outsole impressions are a common form of forensic pattern evidence, yet quantitative methods for estimating wearer attributes from these images remain relatively underdeveloped. We investigate binary sex estimation from footwear outsole impressions by comparing convolutional neural network (CNN) transfer learning with traditional feature-based classification. Using a publicly available outsole-impression dataset, we adopt a shoe-level training and test partition that keeps replicate scans of the same physical shoe together to reduce data leakage. We evaluate pretrained CNNs through end-to-end fine-tuning, frozen feature extraction followed by support vector machine classification, and hybrid feature fusion incorporating handcrafted, geometric, and metadata-derived descriptors. Fine-tuned CNNs achieve the strongest overall predictive performance and substantially outperform traditional classifiers trained on the manually specified descriptors alone, while frozen-feature approaches offer a less computationally demanding alternative. Exploratory analysis of low-dimensional CNN representations reveals associations with frequency threshold ratio, image contrast, and wavelet-based summaries, providing a connection between learned representations and measurable properties of outsole impressions. These findings suggest that CNN transfer learning captures discriminative information beyond the descriptors considered and offers a promising approach to footwear-based forensic screening. Further validation on independently collected and casework-like impressions is needed before operational use. --- ### Penalized Nonreversible Langevin for Constrained Sampling Authors: Pervez Ali, Weihao Dong, Xiaoyu Wang Published: 2026-09-21 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2609.25381v1 We propose penalized nonreversible Langevin algorithms for sampling from $π(x)\propto e^{-f(x)}\mathbf 1_{\mathcal C}(x)$, where $\mathcal C\subset\mathbb R^d$ is a compact convex set. The algorithms combine a squared distance penalty with constant or compatible state dependent skew symmetric perturbations that preserve the penalized Gibbs distribution. For smooth, possibly nonconvex $f$, we derive nonasymptotic total variation bounds for the full gradient algorithm under a log Sobolev inequality. When unbiased stochastic gradients are available, we establish $2$-Wasserstein bounds under global contraction and Lipschitz conditions on the full drift in an adapted quadratic metric. For a fixed penalty parameter, the error relative to the penalized Gibbs distribution decays exponentially to an $\mathcal{O}(\sqrtη)$ neighborhood, where $η$ is the stepsize. We also bound the discrepancy between the penalized Gibbs distribution and the constrained target. In a two dimensional quadratic model, we establish nonreversible acceleration by tuning the skew perturbation to the curvature imbalance induced by penalization. With the target accuracy and smaller curvature fixed and initial Wasserstein distances uniformly bounded, tuning the skew perturbation improves the sufficient Euler iteration bound from linear to logarithmic in the curvature ratio. Numerical experiments evaluate the algorithms on constrained Bayesian regression, classification, neural networks, and truncated sampling, and examine the acceleration mechanism in a stochastic quadratic model. --- ### VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models Authors: Jiuyi Xu, Qing Jin, Meida Chen, Song Wang, Yang Sui, Yangming Shi Published: 2026-09-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.25376v1 Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, numerical format, and calibration. We introduce \textbf{VLAQuantBench}, a controlled evaluation with 409 runs and 94,574 simulation episodes: four models on LIBERO, with X-VLA additionally evaluated on three simulation benchmark families. Under uncalibrated W4A4 round-to-nearest quantization, expanding a $π_{0.5}$ action-head subset from 126 to 167 layers raises success from 7.0\% to 70.5\%. Fixed-observation replay confirms a corresponding numerical recovery. Two-episode calibration removes the severe joint failures in the tested subsets, whereas the same smoothing-and-clipping recipe lowers $π_0$ success and does not recover OpenVLA-OFT end-to-end. For OpenVLA-OFT, protecting one 28,672-parameter output projection instead restores near-baseline success: the remaining 441 eligible linear layers retain W3 on LIBERO-Long or eight-bit activations across all four suites. Task-clustered intervals support the large failure and recovery contrasts. These results establish recipe-dependent interactions and identify concrete precision assignments, rather than universal layer-sensitivity rules. Real-kernel and physical-robot measurements complement the accuracy analysis. Code, configurations, and episode records are publicly available at https://github.com/jiuyixu25/VLAQuantBench. --- ### PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration Authors: Abolfazl Babanazari, Carson Cramer, Tyler Summers, Carlos Nieto, Kaveh Fathian Published: 2026-09-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.25375v2 Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by outliers. Planar regions are particularly difficult for conventional point descriptors and are therefore often suppressed or discarded before matching. We present PARTE (Plane-Assisted Robust Transformation Estimation), a global registration method that instead treats planar structure as complementary registration evidence. PARTE extracts planar patches and represents them using our novel Plane Context Histogram (PCH), a descriptor that encodes the geometry surrounding each patch, while a two-level matching procedure identifies reliable plane correspondences. Candidate point and plane correspondences are combined in a confidence-weighted compatibility graph for joint outlier rejection, followed by rigid transformation estimation. When no usable plane correspondences are available, PARTE naturally reduces to point-only registration. We evaluate PARTE on 8,097 registration pairs across six indoor and outdoor benchmarks spanning dense RGB-D and sparse LiDAR measurements. Evaluations show PARTE achieves the highest overall success rate against 13 standard and state-of-the-art methods while maintaining low runtime. An open-source C++ implementation with Python bindings is provided at https://ariarobotics.github.io/parte/. --- ### Extending FunctionGemma for Practical On-Device Mobile Function Calling Authors: Ali Rezagholizadeh, Soheila Samiee Published: 2026-09-21 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.25373v1 On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or narrow mobile-action catalogs. We extend FunctionGemma 270M-it to practical Android workflows by introducing MOBILEACTIONSEXTENDED, a synthetic, schema-validated dataset of ~9,500 conversations covering fifteen device-control categories, including messaging, phone calls, camera/screenshot, brightness control, device-status queries, flashlight control, and application management. We fine-tune the 270M model with TRL supervised fine-tuning under completion-only loss, producing an extended specialist and a combined model trained jointly with Google's MOBILEACTIONSGOOGLE. On MOBILEACTIONSEXTENDED, end-to-end accuracy improves from 29.3% for the base model and 17.2% for Google's Mobile-Actions variant to 76.5%. The combined model retains 76.5% on MOBILEACTIONSEXTENDED and reaches 82.3% on MOBILEACTIONSGOOGLE, down from the 90.3% of Google's Mobile-Actions specialist, representing an 8.0-percentage-point trade-off in return for doubling category coverage. We release the dataset, fine-tuned models, reproducible training/evaluation pipeline, and an Android demo, highlighting compact local function calling as a practical path towards low-latency and privacy-preserving mobile assistants. --- ### From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought Authors: Renee Jia, Di Mu Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25366v1 Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch intervention that perturbs one reasoning step, truncates the chain, and forces the model to continue from the corrupted prefix. It measures how load-bearing a CoT is for the final answer, a behavioral notion distinct from mechanistic faithfulness. Across Gemma-2-9B-IT, Llama-3.1-8B-Instruct, and DeepSeek-R1-Distill-Qwen-7B on GSM8K, MMLU, and BIG-Bench Hard, CoT load-bearingness tracks model-relative task difficulty: on easy tasks models silently bypass their own reasoning; on hard tasks they follow corrupted steps and propagate errors. A matched 2x2 analysis shows task difficulty dominates perturbation type: error propagation rises 16x from GSM8K to BBH multistep arithmetic, and a variance partition over 28,584 continuations attributes 98.8% of explained deviance to task difficulty versus 0.8% to perturbation type. Reasoning-specific RL suppresses error propagation and compresses the gradient. A four-variant judge-sensitivity analysis and blind two-annotator study (n=500) show the error-propagation vs. non-propagation label is invariant to judge prompt, with perfect inter-annotator agreement (Cohen's kappa = 1.00). This gradient creates a structural problem for CoT-based oversight and AI safety monitoring: where the trace is easy to read it carries little signal, and where it matters errors propagate before a monitor can intervene. Linear probes on hidden states separate silent bypass, self-correction, and error propagation, but additive activation steering provides limited causal control, flipping only about 25% of error-propagation cases at best. Behavioral mode is readable but not reliably controllable. --- ### TelecomGPT-R1: Unified Post-Training for Reasoning Across Heterogeneous Telecom Tasks Authors: Bohao Wang, Chenwei Wu, Hang Zou, Yu Tian, Lina Bariah, Li Wei, Chongwen Huang, Yongliang Shen, Zhaoyang Zhang, Merouane Debbah Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.25356v1 Large language models (LLMs) offer great potential to automate a broad range of telecom engineering tasks by reasoning over standards, network configurations, mathematical models, source code, and operational logs. However, existing telecom LLMs struggle to reliably reason across these diverse tasks and data types. General-purpose LLMs often lack reliable grounding in telecom-specific knowledge, while telecom-specialized models are typically developed for narrower task families and exhibit limited multi-task performance. To fill this gap, we introduce TelecomGPT-R1, a family of open source unified telecom reasoning models structured around four complementary axes: protocol, knowledge, modeling, and fault. We first develop an axis-aware data generation framework that refines coarse public telecom artifacts into verified question-answer pairs and high quality chain-of-thought (CoT) reasoning trajectories, yielding a training corpus containing 104,880 examples. Building on this corpus, supervised fine-tuning (SFT) instills telecom knowledge and evidence-grounded reasoning patterns to overcome the cold start barrier for reinforcement learning (RL). We then apply dynamic sampling policy optimization (DAPO) with task-routed rubric rewards to keep RL updates informative and stable across heterogeneous telecom reasoning tasks. These rewards decompose axis-specific CoT traces into verifiable reasoning units and combine grounded dense process credit with outcome correctness, allowing RL to learn generalizable problem solving behaviors from verifiable telecom evidence. We release the TelecomGPT-R1 models and a reproducible training recipe to support further community development. Evaluations on seven benchmarks of the GSMA Open Telco Leaderboard show that the open-source TelecomGPT-R1-27B achieves an 89.64% mean score, outperforming leading proprietary models, including GPT-5, Claude, and Gemini. --- ### SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy Evaluation Authors: Fatih Deniz, Yazan Boshmaf, Issa Khalil Published: 2026-09-21 Categories: cs.CR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.25352v2 Evaluation of large language models (LLMs) for safety, security, and privacy (SSP) relies heavily on static benchmarks, which suffer from score saturation, data contamination, and aggregation artifacts, and fail to capture sensitivity to linguistic variation. As a result, models that perform well on fixed test sets often fail under semantically equivalent rephrasings. We introduce SSP-Bench, a dynamic benchmarking framework that generates evaluation instances on demand while preserving domain consistency. The framework ensures label validity through externally grounded sources, enforces scope via service-specific validation, and calibrates difficulty using a multi-model steering panel. Benchmark construction is formulated as a multi-objective optimization problem over difficulty, separability, novelty, and diversity. Across 24 models and four SSP services, SSP-Bench reveals systematic failures of static evaluation, including near-zero correlation in safety rankings due to construct mixing, strong safety--over-refusal coupling, and hidden within-family regressions. These results show that static benchmarks can misrepresent model behavior, motivating dynamic, deployment-relevant evaluation. --- ### Learning from Humans for Proactive Assistance in Human-Robot Collaborative Transport Authors: Elvin Yang, Christoforos Mavrogiannis Published: 2026-09-21 Categories: cs.RO, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2609.25351v1 We focus on human-robot collaborative transport, a challenging task of broad relevance spanning logistics, manufacturing, and the home, in which a user and a robot work together to relocate a large or heavy object. To act as an effective partner, the robot should reduce the user's effort by contributing to efficient relocation of the object while remaining physically responsive to them. Prior work often addresses these capabilities separately, producing robots that may move the object efficiently but resist user input, or accommodate the user but depend on continuous guidance. Our key insight is that obstacle-constrained collaborative transport requires integrating predictions of human collaborative behavior with compliant robot control. To this end, we introduce PROACT, a framework for human-robot collaborative transport that incorporates anticipation into compliant whole-body control through a learned model of human collaborative behavior. Trained on a large-scale, real-world dataset of dyadic human transport demonstrations, our transformer architecture distills collaborative behavior into predictions of future object motion. Across 108 real-world trials with a 9-DoF mobile manipulator, PROACT reduces mean interaction work by 59.2\% and 20.4\%, and mean completion time by 12.9\% and 6.9\%, relative to compliance-only and MPC baselines, respectively. Footage from our experiments can be found at https://youtu.be/qAGvQfVPjbk. --- ### Concept Drift from a Causal Perspective Authors: Eduardo V. L. Barboza, Jean Paul Barddal, Robert Sabourin, Rafael M. O. Cruz Published: 2026-09-21 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.25340v1 Concept drift is a common phenomenon in real-world data streams, in which changes in the data-generating distribution can degrade predictive model performance. Most existing definitions characterize drift as changes in the joint distribution $P(\mathbf{x}, y)$, without distinguishing which component of the data-generating process has changed. In this work, we introduce a causal perspective on concept drift based on Structural Causal Models (SCMs). We propose a taxonomy that categorizes drift events by their causal origin, including changes in exogenous variables, endogenous mechanisms, confounders, and target-generating processes. Building on this framework, we develop an SCM-based data stream generator that simulates controlled mechanism-level drift events. Our experiments empirically characterize the distributional effects of each drift type and show that drifts with different causal origins induce distinct patterns of distribution shift and predictive behavior. Furthermore, by integrating causal discovery methods, we use our framework to construct data streams grounded in real-world dependency structures, enabling more realistic and informative evaluation scenarios. We also demonstrate that leveraging the generated data can improve downstream performance. These results highlight the importance of accounting for causal structure when studying and evaluating adaptive learning methods, and establish a foundation for causally-aware evaluation in non-stationary environments. --- ### GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry Authors: Chankyo Kim, Minghan Zhu, Tzu-Yuan Lin, Avantika Rattan, Maani Ghaffari Published: 2026-09-21 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.25338v2 Neural inertial odometry increasingly uses networks as learned measurements inside filtering pipelines. Such measurements should transform consistently under arbitrary IMU mounting conventions: their mean must transform as a vector, and their covariance must transform congruently as a second-order tensor. We present GINIO, a geometric SO(3)-equivariant interface for neural inertial odometry under arbitrary rotations of the IMU measurement frame. Given calibrated IMU windows, our framework predicts a motion measurement and uncertainty obeying these tensorial laws. To support efficient sensor-frame learning, we introduce Last-Frame Alignment (LFA), a deterministic preprocessing step that is provably equivalent to world-frame training for SO(3)-equivariant predictors. The connected estimator tracks sensor-local states such as IMU bias, separating nuisance estimation from the geometric law enforced by the learned measurement. We instantiate the same interface in filter-connected NIO, AirIO-style recurrent aerial prediction, EqNIO-style full-SO(3) canonicalization, and ResNet-style temporal backbones. On TLIO, GINIO achieves 2.018 m ID/SO(3) ATE while EqNIO degrades to 76.389 m, using 11.6x fewer FLOPs. On NanoBench, our AirIO-style instantiation improves ATE from 5.579 m to 1.430 m without external attitude input, and our ResNet-style instantiation reaches 0.581 m ATE versus 0.645 m for ResNet1D. On Fetch, GINIO empirically reduces unseen physical-remount ATE from 8.15 m to 0.50 m without retraining, demonstrating robustness beyond the exact coordinate-frame guarantee. For uncertainty, spectral covariance reduces covariance-equivariance error by over three orders of magnitude compared with a diagonal head. --- ### Clarification Is Not Correction: LLMs Fail to Let Go Authors: Jianzhe Lin, Xiaolin Li, Fei Wang, Robert Douglas, Rajeshkumar Golani, Jubin Chheda Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25337v1 Dialogue failures in language models are usually framed as memory failures: context too long, summaries lossy, a constraint forgotten. We argue this misses a deeper problem: in many conversations the model does not forget, it commits too early. An ambiguous early turn collapses into a single hidden interpretation, and later clarification is filtered through that commitment. We call this early posterior collapse: unresolved user intent collapsing into a committed task state before ambiguity is resolved. We study it with controlled dialogue tasks in writing, planning, and coding using Gemini-2.5-Pro and Gemini-2.5-Flash. Across thousands of trials, the same information in different orders yields different outcomes, even when the final dialogue contains equivalent task-relevant information. This order effect suggests later clarification is treated as extra context rather than a corrective signal: it refines a stale task state without invalidating it. Coding tasks are especially vulnerable, suggesting early assumptions get embedded in structured artifacts such as interfaces and control flow. Standard prompting and memory strategies do not reliably help: summaries can collapse ambiguity, and chain-of-thought can reduce explicit wrong commitment in reasoning traces without improving final task success. These findings motivate uncertainty-preserving state management. If assistants cannot let go of early interpretations, robustness cannot rely on post hoc correction alone; it must keep ambiguous early turns from hardening into one task state. Assistants should hold tentative hypotheses while ambiguity remains, ask before executing when high-impact ambiguity persists, and rebuild from a revised state when later evidence invalidates an earlier reading. Rather than one prompting fix, we aim to redirect research for interactive LLMs from retaining more context toward preserving uncertainty. --- ### MT-ProtBERT: Multi-task Learning ProtBERT for Intrinsically Disordered Proteins Classification with Scarce Data Authors: Jian Sun, Kingshuk Ghosh, Lilianna Houston, Mohammad H. Mahoor Published: 2026-09-21 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.25334v1 Intrinsically disordered proteins (IDPs) differ from folded proteins in that they are dynamic, lack a stable three-dimensional conformation, and have low sequence similarity between similar proteins. The conformational heterogeneity of IDPs - while beneficial for their diverse functions - limits the use of traditional experimental tools to determine their conformation. The experimental difficulty, along with low sequence similarity, results in data scarcity, and makes it difficult to classify/detect IDPs that are similar or dissimilar, a task relevant to understand biology and evolution. We address this challenge using Multi-task ProtBERT (MT-ProtBERT), a multi-task extension of ProtBERT tailored for low-data regimes. MT-ProtBERT integrates Dynamic Window Masking, a Multi-Scale 1D Convolutional classifier (MS-Conv1D), and auxiliary objectives that jointly optimize masked language modeling and biochemistry-informed tasks. We evaluate this framework on two tasks under limited data: (i) phosphorylation site prediction (S/T/Y) in short sequences and small datasets, and (ii) protein compaction prediction on two small datasets (684 and 530 sequences), including sequences comparable in length to typical disordered regions. MT-ProtBERT consistently outperforms PARROT, an RNN-based IDP-specific model, across all tasks. These results demonstrate that combining self-supervised and biochemistry-informed tasks, and multi-scale learning enables robust modeling of unstructured proteins under data scarcity. --- ### MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration Authors: Farida Mohsen, Tala Zaim, Nurul Izni Rusli, Ali Al-Zawqari, Ali Safa, Samir Brahim Belhaouari Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25331v1 Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surveillance, au- tonomous navigation, remote sensing, and inspection in poorly lit industrial environments. Most LLIE methods rely on output- level reconstruction losses that supervise only the final restored image, leaving the intermediate feature recovery process weakly constrained. This paper proposes MirrorDistill, an illumination- aware latent distillation framework that links the low-light and clean domains through feature mirroring. During training, a shared encoder and an exponential-moving-average teacher decoder process the clean reference image to generate clean- domain latent targets. These targets supervise the low-light student at two levels: raw encoder features and standardized multi-scale decoder projections. The alignment is applied layer by layer, while a proposed illumination-aware weighting scheme gives greater emphasis to underexposed regions. The teacher and reference branches are used only during training, so inference requires only the lightweight student encoder-decoder and in- troduces no teacher-side computational cost. Under evaluation on the standard LOL benchmarks, MirrorDistill outperforms the state-of-the-art methods on the real-captured LOL-v2-Real set, while having the lowest compute complexity (GMACs) and while remaining competitive on the LOL-v1 and LOL-v2-Synthetic datasets. Ablation studies further show the contributions of the encoder mirror, decoder mirror, and illumination-aware weighting. Finally, we release our code as open-source for the benefit of future research. --- ### Spatiotemporal Kronecker Covariance Neural Networks Authors: Andrea Cavallo, Athanasios Georgoutsos, Elvin Isufi Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.25326v1 Multivariate time series contain complex patterns that span across both space and time. While covariance-based statistical tools like spatiotemporal Principal Component Analysis (ST-PCA) help identify these patterns, they are limited to linear operations and prone to estimation errors with limited data. Recent covariance-based spatiotemporal neural networks offer more stable, non-linear alternatives, but they ignore correlations across different time steps. To solve this, we introduce the Kronecker coVariance Neural Network (KVNN), a temporal graph neural network that represents the spatiotemporal covariance matrix via a sum of Kronecker products where spatial and temporal dependencies are decoupled. By implementing filtering operations on spatial and temporal components, KVNNs achieve expressive processing capabilities, admit a rigorous spectral analysis, and are provably stable to finite-sample estimation errors, ultimately addressing all of ST-PCA's limitations. We show on five real-world datasets that KVNNs achieve strong forecasting performance, often requiring significantly fewer trainable parameters than competitive methods, and are consistent under estimation noise. --- ### Online Automated Algorithm Design with Large Language Models Authors: Zhiyao Zhang, Yichen Li, Xingyu Wu, Liang Feng, Kay Chen Tan Published: 2026-09-21 Categories: cs.NE arXiv: https://arxiv.org/abs/2609.25325v1 Large language models (LLMs) enable automated algorithm design (AAD) through reasoning and code synthesis. However, most existing LLM-based AAD methods separate algorithm design from target optimization, deploying a fixed design even as the optimization state evolves. Conventional adaptive optimizers can respond to such changes, but their adjustments remain confined to predefined parameters, operators, or strategies. To address these limitations, we introduce online LLM-based AAD, a novel optimization paradigm that treats the algorithm itself as a state-dependent decision variable. At each stage, LLM agents synthesize an algorithm with new behavior logic from the current optimization state. Executing the generated algorithm advances the search and provides feedback for subsequent designs, coupling algorithm design with target optimization without requiring a separate offline algorithm pretraining stage. To implement this paradigm, we propose OnDesign, a multi-agent framework that reconciles competing design perspectives to synthesize executable algorithms and uses execution feedback to refine how runtime evidence is interpreted for subsequent designs. We evaluate OnDesign across two mainstream black-box optimization paradigms on three scenarios: Bayesian optimization, evolutionary continuous optimization, and evolutionary mixed-variable optimization. Extensive experiments on six benchmark suites and one engineering problem across multiple problem dimensions demonstrate superior overall performance over conventional optimizers and offline LLM-based AAD methods. --- ### Uncertainty-Aware 3D Residual Wavelet Diffusion for Ultra Low-Field MRI Super-Resolution Authors: Rui W. Yeow, Millie Beament, Fred Dick, Raha Razin, Martina Bocchetta, David L. Thomas, Henry F. J. Tregidgo, Daniel C. Alexander, James H. Cole Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25319v1 Ultra low-field MRI expands global access to neuroimaging but produces scans with low signal-to-noise ratio, reduced contrast, and thick slices. While regression-based super-resolution can recover anatomical detail for segmentation, it returns a single deterministic estimate that gives no indication of regions where the low-field input leaves anatomy underdetermined. Generative diffusion models offer an alternative by sampling the posterior distribution of plausible high-field images, quantifying this anatomical ambiguity. However, applying them to 3D whole-brain MRI is restricted by memory bottlenecks, slow sampling, and scanner domain shifts. We propose a 3D residual wavelet diffusion model that combines three ideas to overcome these hurdles. A lossless wavelet reparameterisation shrinks the spatial grid to fit a whole brain on a single GPU, residual shifting accelerates sampling by starting from the low-field input, and domain randomisation promotes scanner generalisation without paired training data. As the high-field reference is not a voxel-aligned ground truth, we evaluate downstream volumetric agreement. On a healthy cohort (n=19) imaged at 0.064T and 3T, our method matches a leading general-purpose regression approach in volumetric accuracy while additionally generating per-voxel uncertainty maps highlighting underdetermined regions. Furthermore, on a pilot dataset (n=11) of participants with cognitive impairment, disease-relevant atrophy is preserved rather than normalised towards a healthy prior. Our framework brings whole-brain posterior sampling to low-field super-resolution without sacrificing volumetric accuracy. --- ### Topological Signal Processing With Unoriented Operators Authors: Andrea Cavallo, Varun Sarathchandran, Geert Leus, Elvin Isufi Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.25310v1 Topological signal processing (TSP) processes signals on simplicial complexes with oriented boundary operators, which is the natural choice for flow signals or when the topological invariants play a role for the task at hand. However, many higher-order signals carry no orientation, and applying oriented operators to them is not well-defined since it introduces an arbitrary choice of simplex orientation. We study an unoriented TSP (UTSP) framework that replaces oriented boundaries with unoriented incidence matrices. First, we show that unoriented incidence and Laplacian matrices between arbitrary simplicial levels admit graph-like spectral properties. Second, since dropping orientation removes the Hodge decomposition, we introduce an unoriented counterpart, termed interaction-order decomposition, which quantifies how much of a higher-order signal is explained by aggregating lower-order signals. Third, we use this decomposition to derive regularizers for signal reconstruction that penalize each interaction order separately. Experiments on real-world data show that the order-aware regularizers outperform oriented baselines, with the largest gains when the signal energy is unevenly distributed across orders. --- ### Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing Authors: Brian Wright Published: 2026-09-21 Categories: cs.AI, stat.CO arXiv: https://arxiv.org/abs/2609.25303v1 Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We present a controlled head-to-head comparison of two knowledge representations over an identical classroom corpus: (A) vector RAG, replicating the best-performing configuration from our prior study, and (B) an LLM-compiled wiki (Karpathy framework), in which the corpus is synthesized at ingest into linked concept pages with explicit cross-references and citations back to source materials. We evaluate 59 questions spanning single-fact recall, cross-unit concept linking, synthesis and explanation, and currency after a syllabus revision, scored by an LLM judge against a human-authored rubric. Both representations answered single-fact questions about equally well (9.33 vs. 9.96 of 10), but diverged sharply on questions requiring links across course units. The compiled wiki remained accurate and grounded (9.93; 100% grounded in cited sources), while retrieval scored lower and was markedly less grounded (8.14; 64%). The wiki's citations let students and instructors trace any claim back to the lecture that introduced it, adding a layer of dynamic retrieval that machine learning courses require. While further testing is needed, instructors using AI to support learning in ML courses should consider wiki-based structure for its potential to support foundational elements of best practice. --- ### Making Agents More Consistent: Skills Should Form Habits for Repeat Tasks Authors: Travis Weber, Rohit Taneja Published: 2026-09-21 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.25299v1 On repeated work, agents are inconsistent. We ran 42 tasks three times each and found that, depending on the model, 38% to 74% returned answers that did not agree. Consistency is what a buyer, an auditor, or a regulator requires, and agents do not have it. They are wasteful too: 95.3% to 97.2% of what an agent generates goes to re-deriving a plan the system already knows. We propose skill habit formation. An agent mines its own execution history for candidate skills, deterministic variants that compete against the incumbent rather than replacing it. A candidate declares the region of input space it claims, so the common case runs as a script and the rest falls through to reasoning. Four gates of ascending cost admit candidates; the central one tests a candidate's execution trace against a retained reference, within a tolerance measured from that reference's own run-to-run variability. On text-to-SQL, three of four reasoning arms reproduced their own output on 11 to 13 of 42 repeated questions and the fourth on 26 of 42, while a habit-formed variant reproduced on all 456 dispatches we repeated and was non-inferior to every arm it replaced (p<0.0001). It also used 14% to 56% fewer tokens, turning net positive after 7 to 53 reuses. We measured what this costs in accuracy. The guard admitted work it should have deferred on 2.6% of natural paraphrases and 26% of inputs near its boundary, and 11 of 13 such failures were invisible to the trace-conformance gate at any threshold. Deterministic errors repeat exactly: a bad habit is as reliable as a good one, and that is the price of the property that makes the system auditable. Separating routing from parameter extraction raised end-to-end accuracy from 0.888 to 0.952 at 43% of the cost. --- ### FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing Authors: Yusser Al Ghussin, Eva Gavaller, Cristina España-Bonet, Josef van Genabith, Simon Ostermann Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.25298v1 Cultural evaluation coverage and robustness in language models are difficult to diagnose because pretraining corpora and cultural benchmarks are rarely indexed with comparable metadata. Benchmarks increasingly target culturally situated phenomena at the level of languages, regions, and locale-specific practices, while web-scale corpora are usually organized only by language. A shared culture-language-region layer makes these resources comparable, enabling audits of whether a target cultural phenomenon is represented in pretraining data, evaluated by benchmarks or both. To this end, we introduce FineWeb-CLaR, a large-scale annotated dataset derived from FineWeb and FineWeb-2 that places web documents on a shared culture-language-region axis for corpus auditing and benchmark alignment. FineWeb-CLaR annotates the full 30.9B-document collection from FineWeb and FineWeb-2 with URL-derived region labels and cultural-topic provenance. Our region resolver assigns a non-empty region to 25.61% of documents (7.92B). For cultural-topic analysis, we induce locale-specific topics and project them onto the 14 leaves of the Cultural Taxonomy of Liu et al. (2025), producing Locale Topic Distributions (LTDs) for corpus-side comparison. We also annotate 277 cultural NLP benchmarks with the same taxonomy, language coverage, and region coverage. Together, these resources enable direct comparison between corpus-side pretraining evidence and benchmark-side evaluation coverage. --- ### Correcting Within-Group Self-Selection Bias in Prioritized Replay Authors: Oscar Miró López-Feliu, Herke van Hoof Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.25297v1 Prioritized experience replay (PER) improves sample efficiency by replaying high-priority transitions, usually according to absolute temporal-difference error. In stochastic environments, PER can distort the distribution of realized outcomes replayed from transitions with the same state-action pair. We call this within-group self-selection. We quantify the resulting changes in within-group outcome frequencies and mean Bellman targets. We decompose PER into between-group allocation and conditional sibling selection, and derive fixed-buffer corrections that preserve current group-level priority mass: SAMPLE selects a group through PER and trains on a uniformly sampled sibling; AVG averages sibling Bellman targets; and MODEL samples from an empirical full-outcome model. In exact state-action environments with rare high-magnitude outcomes, sibling-aware replay improves learning efficiency over PER, although matched parameter sweeps show that tuning can narrow some gaps. In MinAtar, approximate VQ-VAE groups with SAMPLE mitigate degradation under mean-preserving reward tails in four of five games. Sibling-aware replay thus retains the focus on high-priority state-action regions while recovering their empirical outcome frequencies. --- ### Learned Enterprise Data Comprehension: Compression and Routing for Data Agents Authors: Ethan Torres, Eric Mills Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25286v1 Structured-data agents in enterprise settings must reason over complex data environments whose relevant evidence is distributed across schemas, relationships, policies, and recurring business roles. Modern agentic systems often address this burden through reusable markdown-style memory or skill files that preserve previously discovered information for later queries, reducing the need to rediscover the same structure repeatedly. This is useful, but it obscures a natural division of labor: agents are well suited to semantic reasoning, while learned systems are well suited to predicting and organizing recurring structure. We introduce latent equivalence learning to bridge this gap. The framework separates persistent task-relevant identities from their dataset-relative realizations. In our realization, supporting and opposing evidence shape support-realized Gaussian prototypes that learn how those identities are expressed in a particular data environment, while soft-membership profiles retain distinctions lost under a hard assignment. A separate learned query-prototype system represents recurring evidential requirements and maps them through a learned compatibility function into the same persistent identity structure. This identity-factorized, query-conditioned routing materializes the relevant dataset-specific evidence for downstream reasoning, allowing the agent to operate over an already organized evidential state rather than reconstructing cross-schema structure at every query. On the Data Agent Benchmark, spanning 54 queries across 12 heterogeneous datasets, our full implementation achieves 94.67% dataset-macro stratified Pass@1 over five complete trials and 258/270 successful raw query attempts, compared with 55.51% for the benchmark's Claude Opus 4.6 reference agent, ranking first among 40 leaderboard entries at submission. --- ### Attention as a Routing Graph: Live Circuit Extraction from a Single Forward Pass Authors: Ash Manvi, Samreena Tajreen Published: 2026-09-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.25285v1 Finding circuits in language models usually means running many careful interventions. We try something simpler: treat attention as a routing map from one forward pass, keep a small set of routes that point toward the answer, and ask whether those routes actually matter. They often do. On induction and IOI (tasks where the "right" circuit is already known), ablating our extracted edges hurts the model much more than ablating a random set of the same size. We evaluate n=100 prompts per cell on GPT-2 Small, GPT-2 Medium, and Pythia-410M, with paired gap tests and bootstrap confidence intervals. The extract step costs one forward; a head-by-head patch sweep costs about two orders of magnitude more. We are not claiming a complete circuit atlas. We are claiming a cheap sketch that carries real causal signal on known tasks, with clear failure modes when it does not. Code and evaluation artifacts are at https://github.com/Aquinf03/live-circuit-routing. --- ### When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning Authors: Jianzhe Lin, Xiaolin Li, Yunda Liu, Fei Wang, Jubin Chheda Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25284v1 A social agent's most basic decisions (should I react to this post? who should I reach out to?) are not purely content problems. The right action often hinges on the latent relationship between people -- tie strength, reciprocity, mutual connections -- rather than on which content is most salient. Standard LLM agent loops do not explicitly represent how new relational evidence should revise the agent's current social hypothesis, leaving them prone to surface-obvious choices when relational and content cues diverge. We formalize this failure mode with a relationship-reasoning benchmark: 500 synthetic social worlds with friendships, follows, reaction histories, and feeds, yielding 1,000 queries over two tasks, reaction selection and warm introduction (finding the best bridge to a target person). By construction, the surface-obvious candidate differs from the relationship-grounded oracle in about 53% of queries, forming an overturn subset where the agent must use relational evidence to revise an initially plausible choice. We propose ReAdapt (Relationship-Adaptive Agent with Policy-driven sTate), which augments the ReAct loop with an explicit structured social state z = (G, B, R, N, D) capturing goal, belief, relationship, norm, and disclosure. After each tool observation, ReAdapt runs a typed Adapt step that updates this state and emits a policy operation (continue, switch, abandon, or clarify) before choosing the next action. With Gemini-3-Flash on a stratified subset of n = 150 queries per task, ReAdapt improves warm-introduction accuracy from 37% to 51% (+14 points) and reaction-selection accuracy from 69% to 77% (+8 points). Oracle regret drops from 0.260 to 0.152 and from 0.095 to 0.053, respectively. Holding the model, tools, and environments fixed, these results suggest that explicit relational-state adaptation helps LLM agents turn retrieved social evidence into revised decisions. --- ### MedGate-Fusion: Integrating First-Encounter Semantic Narratives and Physiological Biomarkers for Prospective Stroke Risk Stratification Authors: Hemn Khdr, Mohammad Noaeen, Karim Keshavjee, Aziz Guergachi, Zahra Shakeri Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25272v1 Prospective stroke risk stratification in primary care is challenging because early risk signals are distributed across routine biomarkers and unstructured clinical narratives. We propose MedGate-Fusion, a multi-modal gated architecture that integrates transformer-based embeddings of first-encounter narratives with ten routinely recorded risk markers. We used electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Starting from 808,921 encounter-level observations, we constructed a first-encounter cohort and retained 102,736 unique patient records with non-empty narratives and sufficient data to evaluate a five-year stroke outcome. To reduce explicit target leakage from diagnostic mentions in notes, we applied dictionary-based redaction of stroke-related terms prior to semantic encoding. --- ### Beyond the Flat Seafloor: A Closed-Form Two-View Constraint to Aid Sidescan Sonar Reconstruction Authors: Kalin Norman, Joshua G. Mangelson Published: 2026-09-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.25271v1 Sidescan sonar is a common sensor for both manned and autonomous marine exploration and mapping, yet very few methods build upon or exploit the geometric projection model of the sensor. As sidescan sonar is limited to a 1D range measurement, many approximations are frequently used, including the long-standing assumption of a flat seafloor. Rather than make similar approximations, this paper focuses on a multi-view geometry based approach and formalizes a two-view geometric constraint and proves that a shared feature is constrained to a locus within the intersection of a sphere and a plane. In addition, we characterize what governs the size of the ambiguity locus through Monte Carlo simulation that is grounded in real aperture and mounting geometry for both a surface vessel and an underwater vehicle. We translate additional simulations of relative trajectories for both vehicle platforms into concrete survey-planning guidance. Our results show that locus length is strongly governed by elevation misalignment, and peaks at a moderate oblique crossing angle of approximately 20 degrees, with minimal locus lengths obtained at near parallel and anti-parallel passes. --- ### RULER: Instance-aware Rubric Rewards for SVG Generation Authors: Hangyu Ran, Yuhao Zheng, Yingying Zhang, Kevin Qinghong Lin, Han Peng Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25270v1 Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute visual ground truth, leaving both evaluation and policy optimization without a faithful signal. Scalar metrics (CLIP, Aesthetic) calibrated on natural images transfer poorly to stylized vector content, and reusing them as RL rewards triggers reward hacking. We address both limitations with rubric-based scoring. We first establish empirically that prompting a vision-language judge with a multi-axis rubric correlates with human judgments far better than scalar metrics, both across samples and within instructions. Building on this finding, we introduce RULER (Instance-aware Rubric Rewards for Reinforcement Learning), which converts each instruction into an instance-aware rubric of six items spanning semantic, visual, and stylistic axes; a judge VLM scores rendered rollouts item-by-item, and the weighted satisfactions form a fine-grained reward optimized via Group Relative Policy Optimization. Because the rubric is derived from text alone, RULER requires neither paired SVG ground truth nor human preference labels. On MMSVG-Illustration and MMSVG-Icon, RULER lifts the rubric score from 0.432/0.395 to 0.693/0.683, surpassing dedicated SVG specialists and matching the substantially larger DeepSeek-V3, with ablations identifying rubric design as the active lever for RL on open-ended SVG generation. The project page is available at https://hangyuran.github.io/RULER/. --- ### ImIR: Image-Instruction Tuning for All-in-One Image Restoration Authors: Süleyman Aslan, Görkay Aydemir, Mısra Yavuz, Yunus Bilge Kurt, Nasrin Rahimi, Ahmet Rasim Emirdağı, Burak Can Biner, M. Akın Yılmaz Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25267v1 Degradations vary widely across images, so a practical restoration system has to handle many degradation types with one model. A recent and effective recipe adapts a large pretrained image-editing model to restoration using a small low-rank adapter with a text prompt. We replace that prompt with an instruction derived from the degraded image itself. The image reaches the editor through two paths: its structure comes from the model's VAE, and its semantic instruction comes from a lightweight token mapper that shifts the degraded image's vision-language embedding toward the embedding a clean image would produce. Because the instruction is a continuous vector, scaling it yields a family of valid restorations for tasks whose target is not unique, such as low-light enhancement. We adapt one Qwen-Image-Edit model to six tasks with a single adapter trained in about three hours on one GPU. The image instruction outperforms text conditioning under a matched comparison, and it supports task agnostic restoration without a degradation label, which the text variant does not. --- ### The AI Neuroscientist: An Interactive Agentic Interface for Neuroimaging Analysis Authors: Aakash Patel, Panos Ketonis, Shreya Saxena, Smita Krishnaswamy, David van Dijk Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25254v1 Analyzing neuroimaging data requires specialized coding and statistical expertise, which limits accessibility for researchers without computational backgrounds. We present the AI Neuroscientist, a language agent for interactive data exploration. The system integrates a large language model (LLM) with a neuroimaging toolset to perform quality control, modeling, and visualization. This allows researchers to query data quality and specify analysis parameters directly in natural language, providing a transparent and interactive alternative to conventional scripted pipelines for small-scale data exploration. We demonstrate these capabilities using functional near-infrared spectroscopy (fNIRS) data, and evaluate the agent on a custom fNIRS benchmarking suite against general-purpose LLM agents with code sandboxes. Future extensions will generalize the architecture to additional modalities, including functional magnetic resonance imaging (fMRI) data, and expand the benchmarking suite to additional fNIRS tasks. --- ### Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes Authors: Hanyang Kong, Xingyi Yang Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.25247v2 Understanding interaction in a 3D scene requires recovering movable parts, their motion, and where they can be operated. These quantities are related, and their predictions can inform one another. A closed cabinet door, for instance, reveals a movable surface but may leave the hinge side ambiguous; its handle helps resolve this ambiguity, while the part provides context for localizing and interpreting the small handle. Building on this observation, we present SEGMENT-SNAP, which combines geometric and semantic evidence through part-handle coupling. Three independently trained predictors recover movable parts, dense handles, and part-associated handle proposals. We couple their outputs in two directions. For part motion, a training-free geometric decoder fits predicted part surfaces under explicit physical priors and uses detected handles to select candidate hinge lines. For handle prediction, a part-conditioned branch proposes additional handles, while standalone part classes refine their rotation/translation labels, with dense-handle labels as a fallback. Each transfer is applied once, without iterative feedback. On the Articulate3D validation set, handle guidance raises motion-gated AP from 13.74 to 40.98 under fixed masks and axes. Additional handle proposals raise handle AP from 24.63 to 29.65, and full contextual class correction raises it to 30.99 in the reference configuration. Fixed-input controls, retraining ablations, learned-decoder comparisons, and paired visualizations together characterize the benefits and limits of this coupling. Our system also achieved first place in the Articulate3D Challenge. --- ### How Children Design and Reason about Trustworthy AI Chatbots Authors: Deniz Ozturk, Jiayu Li, Daksh Pratap Singh, Yasitha Rajapaksha, Fasika Melese, Bahare Riahi, Shiyan Jiang, Qiao Jin, Joey Huang, Veronica Cateté, Tiffany Barnes, Xiaoyi Tian Published: 2026-09-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.25244v2 Children increasingly interact with AI chatbots, making trust calibration essential to AI literacy. Prior research has examined children's trust in AI mainly as users evaluating systems built by others, rather than as designers of their own chatbots. We developed a chatbot-building environment with adjustable trust-relevant traits (e.g., confidence, transparency, formality, assertiveness), rules, and persona. We conducted mixed-methods study with 115 learners (ages 8-18) who made 119 chatbots. We examined how children configured their chatbots, reasoned about trustworthiness, and how closely chatbot behavior aligned with their designs. Younger students (age 10-13) set significantly higher confidence than older students (age 14-18), and some deliberately built chatbots that gave wrong answers on purpose, yet still called them trustworthy, arguing that a chatbot does what it was built to do. Younger students equated trust with purpose-fulfillment, while older students linked it to transparent, calibrated design. Students also calibrated academic chatbots to be more transparent and formal than hobby chatbots. We identify seven design dimensions describing what children believe makes a chatbot trustworthy, and discuss implications for AI literacy tools. --- ### Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers Authors: Weihang Ding, Junfei Zhan Published: 2026-09-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.25237v1 Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a human-approval gate, and reproducibility requirements. Seating an LLM agent in the FDE seat raises a question existing benchmarks cannot answer: not whether an agent can raise a metric, but whether it can be trusted to deliver. We answer it on a governed delivery plane, where an agent drives ten stages and an oracle scores each stage from platform-recorded facts. The central silent failure is the run that trains but does not learn (TBDL): loss falls, every signal stays green, and the delivered model is no better than the base. An operator-run acceptance gate catches every such run before payment, and a detector calibrated on known-corrupted runs flags severe corruption mid-run. We ran four frontier agents (Claude Opus 5, GPT-5.6-luna, Gemini 3.7 Flash, DeepSeek V4-Pro) end to end on metered L40S, A100, and H200 GPUs across 8B to 70B open bases, certifying every scenario before scoring. We also ran a human FDE arm under the same oracle and compare every agent against it. --- ### Lean Pool: An AI-Maintained Archive of Formalized Mathematics Authors: Vasily Ilin Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25199v1 Lean Pool is a repository of formalized mathematics. It is grown, maintained and optimized by AI agents. --- ### Indirect tipping: a social attack surface in AI agent populations Authors: Ariel Flint, Luca Maria Aiello, Sara M. Constantino, Romualdo Pastor-Satorras, Andrea Baronchelli Published: 2026-09-21 Categories: cs.MA, cs.AI, cs.CY, eess.SY, physics.soc-ph arXiv: https://arxiv.org/abs/2609.25194v1 As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on collective equilibria that determine how agent populations process information, prioritize actions, and respond to uncertainty. Yet the same equilibria that enable agents to coordinate also create a social attack surface. The standard framework to assess this vulnerability is critical mass dynamics: the minimum fraction of adversarial agents required to overturn an equilibrium through direct competition. Here, we show that this approach risks underestimating system vulnerability by reducing the problem to the identification of singular tipping points, and ignoring indirect but potentially more efficient routes through which collective behavior can be redirected. Through experiments with populations of LLM agents and an analytic framework that captures their collective dynamics at scale, we map critical-mass thresholds that define a directed, weighted topology over the space of coordination equilibria, and treat this topology as a navigable landscape. We show that indirect tipping through intermediate stepping-stone equilibria can reduce the committed minority required to reach an alternative state, bypass majority requirements, and make possible transitions inaccessible through direct challenges. The diversity of available alternatives and timing of the attack further reshape this landscape, creating opportunities for control as well as risks of unintended destabilization. These results show that an equilibrium's resistance to committed intervention is not an intrinsic property but a structural feature of its competitive relations with alternative states. Securing populations of interacting AI agents therefore requires mapping this social landscape alongside individual agent capabilities and the technical channels through which they interact. --- ### FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability Authors: Wenqing Wang, Haitao Xiang, Xinyi Zhao, Mingming Yin, Ying Zhong, Zhaoxin Huan, Qiheng Zhou, Jin Zhu, Xiaolu Zhang, Shi Chang, Jun Zhou Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.25192v1 Financial search is a highly demanding task for LLM agents, requiring not only a correct final answer but also temporally valid information retrieval, authoritative source selection, entity and period alignment, unit and definition consistency, and verifiable evidence for all conclusions. Existing benchmarks predominantly evaluate only the final answer, making it difficult to localize errors or assess whether an answer is well-founded. To address this gap, we introduce FinFIRST (Financial Information Retrieval, Sourcing and Traceability), the first financial benchmark to jointly evaluate answers and supporting evidence through atomic rubrics. FinFIRST comprises 123 expert-authored tasks spanning a graduated difficulty spectrum, constructed from aggregate patterns of real-world financial scenarios through an 18-field taxonomy, a six-axis coverage blueprint, a registry of 138 financial sources, contributions from over 50 finance experts, and a six-stage quality-control pipeline. Each task is accompanied by an evidence-grounded reference package decomposed into atomic criteria across three dimensions: raw-information acquisition, source verification, and computation and answer formation. We evaluate 15 model configurations under a unified tool setting. Claude-Opus-5 achieves the highest atomic score of 87.59%, while GPT-5.6-Sol attains the highest strict pass rate of 71.54%. Computation and answer formation consistently lag behind raw-information acquisition across systems. FinFIRST retains final-answer correctness as the primary objective while making the supporting research process measurable, verifiable, and diagnosable. --- ### GroundedGEO: Auditing the Evidence Gap in Generative Search Rankings Authors: Yihan Xia, Huiling Fan, Kangrong Zhong, Taotao Wang Published: 2026-09-21 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2609.25189v1 Generative search systems rank products and services for consequential decisions, and publishers can cheaply make candidate text look relevant. Yet evidence status is not a text property but a claim-evidence relation: text-only rankers and defenses cannot separate honest detailed content from fabricated detail, creating an identifiability gap. We audit this gap with an evidence-paired benchmark (50 e-commerce queries, 1,950 cases) and a claim-level reranker, GroundedGEO, that penalizes query-relevant claims lacking support in a supplied packet. Matched rich variants control format and volume; packet twins add attestations at fixed text, while thinned packets withdraw them. On the frozen listwise ranker Qwen2.5-7B, unsupported-rich variants show significant normalized rank gain over clean candidates (+0.065 to +0.092 across claim profiles, Holm-corrected), while supported and neutral controls do not; the effect is model-dependent (marginal on MiMo-v2.5, absent on GLM-5.3-Flash). On a frozen pointwise scorer, oracle evidence labels cut the unsupported-rich top-3 rate from 0.65 to 0.43 (laundering from 0.61 to 0.39) at lambda=40 with zero false suppression; packet twins restore the original rates without changing text. Against a 370-claim human gold, all tested automatic judges fail the preregistered reliability gate, although the best local judge retains 79-100% of oracle suppression with zero measured false suppression on protected arms. Separately, stripping attestation coverage increases false suppression by 0.307. These diagnostic effects identify two limits on the evidence channel: label quality and packet coverage. They do not validate an automatic defense, and interpretation of the adverse human-gold arm remains pending adjudication. --- ### X-Planner: Event-Structured Task Planning for Embodied Intelligence Authors: Howard Lu, Shalfun Li, Porter Pan, Cris, Lumen, Cyril, Eric Hu, Lily Li, Maeve Zhang, Robert Wang, KZ Zheng, Viggo Chen et al. Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25187v1 Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this intermediate structure implicit. Existing chain-of-thought (CoT) planners also tend to rely on coarse task-level annotations or serialize long reasoning traces token by token. We present X-Planner, a planning front-end that addresses both the supervision and representation of embodied reasoning. Our planning data combine Ego, UMI, and teleoperation under a hierarchy granularity with source-dependent annotation depth. Takeover-time annotations and human-designed failures supervise ongoing error recognition. On the model side, a shared VLM backbone exposes two event-structured plan forms: a discrete interface that emits interpretable event states and a latent interface that relays continuous CoT states across staggered Transformer depths through Staircase Decoding. A frozen latent-to-text reconstruction objective provides a semantic anchor for the latent representation. Offline two-step planning evaluation places X-Planner second among four evaluated models on both BERTScore-F1 and a judge-based Overall score. In real-robot experiments, respectively, outperforming the evaluated baselines. These results characterize planning-text quality and downstream execution. --- ### From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health Authors: He Hu, Yucheng Zhou, Qianning Wang, Yingjian Zou, Chiyuan Ma, Juzheng Si, Jianzhuang Liu, Zitong Yu, Laizhong Cui, Fei Ma, Qi Tian Published: 2026-09-21 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.25186v1 The rising global prevalence of mental health conditions, together with longstanding barriers in traditional healthcare, such as limited resources, high cost, stigma, and privacy concerns, has created an urgent need for accessible and scalable support. Large Language Models (LLMs) have emerged as a transformative technology with strong potential to democratize mental health support through advanced natural language understanding and generation. However, the rapidly expanding, fragmented body of work in this area lacks a coherent evolutionary narrative, making it difficult to contextualize current progress and identify future directions. This survey addresses this gap by organizing and analyzing the literature around a central thesis: the role of LLMs in mental health is evolving through three distinct, increasingly sophisticated phases. We trace this trajectory from Phase I, in which LLMs act primarily as passive Information Tools and Pattern Recognizers for assessment; through Phase II, where they function as Empathetic Conversationalists for in-the-moment, stateless interactions; to the current frontier, Phase III, which seeks Longitudinal, Personalized Companions implemented as stateful cognitive agents. To support this framework, we systematically review core technologies, agent architectures (Profile, Memory, Reasoning, and Planning), and the critical infrastructure of datasets and benchmarks, highlighting how their evolution underpins this developmental path. Viewing the field through this developmental lens, we provide a comprehensive synthesis of existing work, an insightful narrative of its trajectory, and a clear roadmap for future innovation in responsible, effective, and human-centered AI for mental healthcare. A curated collection of the resources reviewed in this survey is available at our project repository: https://github.com/Emo-gml/Awesome-Mental-Health-LLMs. --- ### Multi-Term Fourier Graph Neural Network with Sample Relationship Learning for Enhanced Remaining Useful Life Prediction Authors: Ya Song, Laurens Bliek, Yaoxin Wu, Yingqian Zhang Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.25179v1 Predicting the remaining useful life (RUL) is essential for effective predictive maintenance. Spatio-Temporal Graph Neural Networks (ST-GNNs), which can model both temporal and spatial relationships by representing time series data as a sequence of graphs, have shown exceptional performance in RUL prediction. However, current ST-GNNs face several drawbacks. First, they require domain expertise or significant computational power to establish graph structures prior to deploying GNNs. Second, the models are restricted to capture temporal dependencies within a predefined fixed-size lookback window. This restriction ignores the common issue of varying time series lengths, leading the prediction model to miss short-term or long-term dependencies. Finally, conventional models often fail to capture the inherent relationships between samples generated from adjacent time windows, which are crucial for improving both the accuracy and robustness of predictions. To address the aforementioned issues, we introduce a novel framework called Multi-Term Fourier Graph Neural Network with Sample Relationship Learning (MTFGN-SRL). Rather than treating the sample as a sequence of graphs, we consider it as a single complete graph and utilize a Fourier Graph Neural Network (FGN) to capture the spatio-temporal information in the frequency domain. We propose a multi-term learning module that utilizes multiple lookback windows to generate samples with varying terms, which are then fed into the FGN to enhance the extraction of useful information from the data. Finally, we develop a sample relationship learning module by training a heterogeneous GNN to identify inter-sample relationships, resulting in enhanced accuracy and robustness in predictions. Evaluations on the CMAPSS dataset demonstrate MTFGN-SRL's superior performance over state-of-the-art methods in RUL prediction. --- ### Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction Authors: Lujia Bao, Qian Chen, Luyao Cheng, Chong Deng, Yuxiang Kong, Xiangang Li, Xu Li, Jiaqing Liu, Chao-Hong Tan, Haoyu Wang, Wen Wang, Xilou Wang et al. Published: 2026-09-21 Categories: eess.AS, cs.AI, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.25176v2 Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate. Think combines Core-Cocktail supervised fine-tuning with Multimodality and Multi-Teacher On-Policy Distillation (M$^{2}$-OPD) to transfer language capabilities and develop native audio skills. Act uses self-evolving executable environments and multi-granularity rollouts for Group Relative Policy Optimization (GRPO), teaching the model to use tools, interpret feedback, and complete tasks. Speak and Coordinate aligns whether, when, and how the assistant speaks or acts. We evaluate audio reasoning, multilingual understanding, tool use, conversational behavior, full-duplex interaction, and safety. Compared with Qwen-Audio-3.0-Realtime, 3.1 raises overall task success from 78.4% to 82.0% on our half-duplex speech-to-text adaptation of $τ$-Voice. On speech-to-speech Full-Duplex-Bench v1.5, the response rate to background speech falls from 73.0% to 13.0%. We also present a separate Voice Harness prototype, using Qwen-Audio-3.0-Realtime as its foreground, that extends spoken interaction to persistent tasks through foreground--background coordination and memory. --- ### Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning Authors: Donghyun Kim, Taehyuk Lee, Jinyeong Kim, Youngmin Oh, Dohyeong Kim, Jaehyuk Ryu, Sangwoo Hong Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.25166v1 Diffusion data-point unlearning is typically evaluated immediately after each deletion, even though subsequent requests may repeatedly update the same model. We identify sequential reappearance, a failure mode in which an instance that is initially judged to be forgotten later returns to the memorized regime without reuse of the deleted data or adversarial fine-tuning. To capture this behavior, we introduce a target-level evaluation protocol that tracks whether each target is forgotten immediately, remains forgotten at the end of the sequence, or reappears during subsequent deletions. We further find that targets that later reappear exhibit sharper local denoising-loss geometry after deletion than targets that remain forgotten. --- ### Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings Authors: Ovis-Embedding Team Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25165v1 In this report, we introduce \textbf{Ovis-Embedding}, a state-of-the-art omni-modal embedding family built on native integration of text, image, video, and audio. Instead of assembling separate modality towers, Ovis-Embedding uses a shared multimodal backbone to encode different modalities in a common representation space. Specifically, we make \textbf{three key advances}: (1) \textbf{native omni-modal initialization}: we adopt a pretrained Qwen-omni model as the embedding backbone and adapt it through contrastive training with low-rank initialization; (2) \textbf{data-centric omni-modal training}: we construct a broad, high-quality corpus spanning text, images, video, audio, and interleaved multimodal data. To improve data efficiency, we introduce homogeneous-source sampling to form task-consistent batches with informative in-batch negatives; and (3) \textbf{embedding-specific training and inference optimization}: we use focal loss to emphasize hard examples and similarity-based Embedding Distillation to transfer fine-grained similarity structure from complementary experts. At inference time, low-rank feature decomposition enables compact embeddings with flexible dimensionality and minimal performance loss. Empirical evaluations show that the \textbf{Ovis-Embedding} family achieves state-of-the-art performance on \textbf{MMEB-v3}, \textbf{MMEB-v2}, \textbf{MVEB}, \textbf{MAEB}, and \textbf{RTEB}, demonstrating its effectiveness across text, image, video, and audio modalities. These results highlight the potential of unified omni-modal training to overcome modality fragmentation and advance universal embedding models for any-to-any retrieval. --- ### Learning Neural Feedback Linearization for Data-driven Systems via Augmented Lagrangian Authors: Lakshmi Priya P. K., Andreas Schwung Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.25163v1 The paper proposes a novel data-driven framework for designing and training a feedback linearizing controller by explicitly incorporating relative degree based conditions into the learning process. This enables the conventional feedback controller components to be replaced by neural Lie derivatives, thereby facilitating a fully data-driven feedback linearization framework. Furthermore, practical closed-loop stability is established by deriving sufficient conditions under which bounded identification errors lead to bounded tracking errors. The derived theoretical results are validated through their application to an armature controlled DC motor. --- ### Empirical Auditing of Edge-Private Graph Generators Authors: Anum Fatima, Stratis Limnios, James Adams, Lukasz Szpruch, Carsten Maple, Gesine Reinert, Andrew Elliott Published: 2026-09-21 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.25155v1 We empirically audit privacy leakage by testing whether outputs from edge-neighbouring inputs remain distinguishable, using statistically valid lower bounds on the privacy loss witnessed by our attacks. Our framework compares direct-edge, local-structural, and GNN-based attacks through the geometry surrounding a target edge. Experiments across two generators and two networks show that privacy leakage is both mechanism- and network-dependent, with learned representations revealing information not captured by conventional local statistics. --- ### Benchmarking Neural Defend ARCAS 1B: A Foundational Multimodal Deepfake Detection Model Authors: Sivashankar Selvarajan, Piyush Verma, Sumit Kumar, Sharayu N. Deshmukh Published: 2026-09-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.25154v1 AI-generated imagery evolves faster than benchmark-specific detector evaluations, making a single score an incomplete account of generalization. This paper evaluates Neural Defend ARCAS 1B across benchmark families without benchmark-specific parameter updates. We retain native aggregation and supplement it with record-level measures, coverage accounting, and subgroup diagnostics. Each Results subsection identifies the release and evaluation population, reports the official metric, and describes observed error patterns. A combined analysis synthesizes shared patterns while preserving the distinction between native and pooled quantities. Cross-paper comparisons are restricted to aligned evidence; differences in release, population, preprocessing, training, or benchmark exposure are context rather than rank. The findings characterize performance on evaluated records, not universal reliability, calibration, attribution, or future adaptive attacks. By keeping benchmark-native outcomes distinct from pooled summaries, the study makes test-population, class-balance, and missing-record-coverage differences visible. It supports interpretation of detector results in research, platform-safety, and forensic-review settings, foregrounding traceable protocol conditions over claims or leaderboard comparisons. --- ### Exposing Blind Spots in Deep Imbalanced Regression Evaluation Authors: Noah C. Puetz, Jens U. Brandt, Marc Hilbert, Elena Raponi, Thomas Bäck, Thomas Bartz-Beielstein Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.25152v1 Deep Imbalanced Regression (DIR) addresses a common failure mode of regression models: target distributions are highly non-uniform, causing models to perform best in densely populated target regions even when reliable performance is required across the full target range. Despite rapid methodological progress, DIR evaluation remains constrained by three blind spots: it is dominated by image-based benchmarks, its standard many-/medium-/few-shot protocol is diagnostic but not decision-complete, and tail-region stability across random seeds has not been systematically evaluated. We revisit DIR evaluation along these three axes. First, we broaden the data domain by evaluating DIR on a multimodal virtual sensing benchmark (\textsc{MuViS}) with nine time-series extrinsic regression tasks across six physical domains, where rare target values often correspond to operationally meaningful regimes. Second, we adopt balanced MAE (\emph{bMAE}) and introduce balanced Mean Absolute Scaled Error (\emph{bMASE}), a scale-normalized metric for decision-complete comparison across methods and datasets. Third, through a repeated reevaluation of six representative DIR methods across multiple random seeds, we show that the tail regions targeted by DIR exhibit particularly high sensitivity to seed-level variability. Our results show that standard virtual-sensing models exhibit substantial tail degradation hidden by global MAE, that existing DIR methods can improve balanced performance but transfer unevenly to multimodal time-series data, and that tail-region instability remains a largely hidden failure mode under current DIR evaluation practice. Together, these findings and our publicly available code provide a reproducible basis for future DIR research toward regression systems that capture rare target regimes as reliably as common ones. --- ### Towards Sustainable Magnetic Resonance Imaging: Insights from long-term, high-resolution energy recordings across an entire scanner fleet Authors: Florian Leonhard Raab, Fiona Mankertz, Nour Maalouf, Josephine Berger, Andreas Lingg, Reza Dehdab, Sebastian Werner, Judith Herrmann, Andreas Brendlin, Sebastian Gassenmaier, Suhas Siddaramu, Fabian Wagner et al. Published: 2026-09-21 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2609.25150v1 Magnetic resonance imaging (MRI) is among the most energy-intensive diagnostic modalities in healthcare, yet its energy consumption and the factors influencing it remain insufficiently understood. This study aims to establish a comprehensive baseline of MRI energy consumption by characterizing energy demand across a scanner fleet, examining scanner utilization and operating patterns in clinical practice. Concurrently, it investigates the relationships between energy consumption and relevant operational and acquisition features. On average, a single MRI measurement consumed 0.43 kWh, while a complete examination consumed 13.50 kWh. In general, substantial differences in energy consumption were observed between MRI scanners and their corresponding operating modes (scan, idle, and eco-power mode). These variations may be related to differences in scanner operating patterns, employed examination protocols, and their resulting acquisition parameters. Idle and eco-power modes accounted for more cumulative energy consumption than active scanning. However, these energy shares should always be interpreted in relation to scanner occupancy, as utilization patterns strongly influence the distribution of energy across those operating modes. Lastly, linear regression analysis showed that energy consumption was more strongly associated with scan duration than with average power, suggesting that scan duration may be an important factor influencing MRI energy consumption. ... --- ### Dual-GNN Multilevel Coarsening for Maximum Independent Set Authors: Tianfeng Chen, Xianyue Li Published: 2026-09-21 Categories: cs.LG, math.CO arXiv: https://arxiv.org/abs/2609.25149v2 The maximum independent set (MIS) problem is a fundamental NP-hard combinatorial optimization problem with applications in scheduling, resource allocation, and network analysis. Exact solvers can provide high-quality solutions or optimality certificates, but their computational cost grows rapidly with graph size, while hand-crafted heuristics improve scalability at the expense of guarantees. Learning-based methods offer an alternative by exploiting structural patterns across graph instances, yet directly predicting independent sets can make global coordination difficult on large graphs. We instead use learning to guide multilevel graph coarsening while retaining combinatorial search for final decision making. Our Dual-GNN Multilevel Coarsening framework uses a Partition GNN to score candidate contractions and a Representative GNN to select top-k local independent-set states for each final cluster. Experiments on Erdős--Rényi graphs with up to 2,000 vertices demonstrate a favorable quality--runtime trade-off. On 500-vertex instances with certified optima, our method achieves an average independent-set size of 19.20, corresponding to 99.5\% of the optimal value of 19.30, while reducing the mean wall-clock time from 643.57 seconds for exact solving to 3.41 seconds, yielding an approximately 189$\times$ speedup. On larger graphs with 1,000 and 2,000 vertices, our method achieves the best mean solution quality among all evaluated methods. Moreover, although trained only on Erdős--Rényi graphs with edge probability $p=0.35$, the learned coarsening policy generalizes effectively across both unseen graph densities and structurally different graph families. ---