# Research Papers — 2026-09 · bundle page 168 of 266 > Full-text markdown of papers #8351–8400 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/168 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/167.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/169.md) ### To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs Authors: Franck Signe, Hippolyte Pilchen, François Yvon, Édouard Grave Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15528v1 Multilingual Large Language Models (LLMs) traditionally rely on a single vocabulary shared by all supported languages, which can lead to uneven compression across them. Moreover, their large embedding and output matrices increase memory usage and slow inference, notably for small-scale models. It is also wasteful as models are often used for only a subset of languages. To address these issues, we introduce a modular framework for multilingual model training. First, we propose methods to learn large modular BPE and Unigram tokenizers that enable extraction of subtokenizers tailored to any language subset. These subtokenizers achieve compression on par with monolingual tokenizers and improve cross-lingual fairness. Second, we design a pretraining strategy that samples subtokenizers to form batches, restricting predictions to the relevant vocabulary subset and allowing efficient training despite a large vocabulary. This supports efficient inference with any combination of language-specific vocabularies. Therefore, it reduces memory usage and speeds up inference in models without sacrificing performance. --- ### Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference Authors: Niklas Summ, Xiao Wang, Hendrik Borras, Bernhard Klein, Holger Fröning Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15527v1 The energy efficiency of analog computing makes it one of the most promising candidates for deploying resource-intensive machine learning workloads on constrained platforms such as mobile and embedded devices. However, analog accelerators are inherently susceptible to noise and non-idealities arising from physical component variations, whose behavior is further sensitive to environmental factors. These effects can significantly degrade inference accuracy. In this work, we conduct a comprehensive experimental study on a representative example of analog hardware to investigate the impact of temperature. We first characterize the behavior of stochastic and systematic non-idealities across a range of operating temperatures. Following this, we compare a set of simulation-based and hardware-based mitigation strategies aimed at improving robustness against temperature-induced performance degradation. Our results suggest that temperature-induced degradation is driven primarily by systematic non-idealities rather than stochastic noise alone. Noise-aware training improves robustness, while hardware-in-the-loop training and temperature-aware calibration provide the strongest accuracy retention across varying thermal conditions. --- ### Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026 Authors: Tristan Kirscher, Vivian Metzger, Philippe Meyer, Xavier Coubez Published: 2026-09-14 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.15524v1 BraTS-GoAT evaluates tumor segmentation across heterogeneous populations. We trained a conventional 3D nnU-Net on 1,351 labeled cases using five-fold cross-validation and 1,000 epochs per fold. The final predictor averaged all folds and applied test-time mirroring. On pooled official validation, global DSC values were 0.7805, 0.8288, and 0.8854 for enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Under matched fold-0 inference, mean regional Dice decreased from 0.9058 on source out-of-fold (OOF) cases to 0.8310 on pooled validation (difference--0.0747). Mirroring gave small single-fold gains but no clear ensemble benefit; a residual-encoder alternative reached 0.8282 mean Dice. In labeled OOF predictions, failure cases had substantially smaller reference ET volumes; after adjustment for ET and WT volume, lower Dice remained associated with more disconnected ET components and a smaller fraction of ET contained in the largest component. --- ### Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting Authors: Oliver Stevanovic, Jasmin Wachter Published: 2026-09-14 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.15523v1 Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frameworks such as MulVAL to contemporary security workflows or agentic pipelines, however, requires translating scanner evidence to initial facts, and creating domain-specific rules. We present a semi-automated pipeline that addresses this interoperability problem and depict its feasibility in a web-security case study. Our pipeline parses findings from Trivy, Semgrep, and Nmap into MulVAL predicates and uses an LLM-assisted process to construct domain-specific Datalog rules linking scanner-detectable evidence to attack techniques. MulVAL/XSB then performs symbolic inference to generate structured attack paths. We evaluate the attack-graph construction infrastructure on 54 web Capture-the-Flag tasks from CyBench within an agentic pipeline (Hybrid Reasoner); we do not evaluate the performance of the downstream agent. Every task produced at least one goal-reaching graph, and we achieve mean ground-truth vulnerability coverage of 53.7%, with 51.9% achieving full coverage; mean noise-path rate was 83.9%. With median end-to-end time of 24.9 s (MulVAL reasoning: 2.7 s) the pipeline is feasible and runtime-practical for agentic workflows, but predicate coverage, rule coverage, and path precision remain limiting factors. Next steps include semantic rule validation and agent-level comparison for graph-guided pentesting. --- ### Psychosis involves a deficit of information compression in connected speech Authors: Samuele Vallisa, Claudio Palominos, Rui He, Emre Bora, Burcu Verim, Cemal Demirlek, Berna Yalincetin, Philipp Homan, Wolfram Hinzen Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15522v1 Large language models (LLMs) with human-like performance on linguistic tasks have transformed the study of language in neurodiverse conditions. LLMs provide representations of linguistic input in the form of high-dimensional vectors (embeddings), and next-token predictions computed from these embeddings. Previous crosslinguistic evidence suggests a complexity reduction in the form of both lower intrinsic dimensionality (ID) of LLM representations and higher mean surprisal (prediction error) in psychosis. We hypothesized that these metrics reflect a general deficit of information compression in psychosis, linked to grammatical organization as what enables predictions in language.We operationalized surprisal difference as the difference between surprisal as estimated from word frequency and surprisal as based on a contextual LM, which is sensitive to grammatical organization over and above lexical concepts. Using a dataset of 144 Turkish speakers, including 106 patients with schizophrenia-spectrum disorders (SSD) - 56 with chronic schizophrenia (SZH), 33 with first-episode psychosis (FEP), and 17 with schizoaffective disorder (SZA) - and 38 healthy controls. We report: (1) Surprisal difference is attenuated in all clinical groups relative to controls, independently of word count; (2) Compressibility (intrinsic dimension) is reduced in SZH and FEP; (3) Syntactic complexity and compressibility both predict surprisal difference. These results, further refining an alteration in the geometry of the semantic space in psychosis as previously attested, suggest a broader deficit in information compression in this disorder, with a mechanistic underpinning in the operations of grammar. --- ### End-to-End Verifiable and Robust Federated Learning Authors: Doryan Lesaignoux, Enrique Mármol Campos, Gabriele Spini, José L. Hernández-Ramos, Stephan Krenn Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15521v1 Federated learning enables multiple parties to train a shared model without centralizing raw data with the help of an aggregator, but introduces integrity risks once participants or infrastructure are not fully trustworthy. Two requirements are particularly important: robustness to poisoned or Byzantine client updates, and verifiability of the aggregator so that clients or third parties can audit the reported aggregation without learning individual updates. Existing work has largely treated these goals separately, and efficient public verifiability for robust, outlier-excluding aggregation remains limited. We present a verifiable federated learning protocol that makes a robust aggregation pipeline publicly auditable. Our design combines cryptographic commitments with non-interactive zero-knowledge proofs to certify both (i) cosine-similarity-based outlier exclusion and (ii) aggregation over the selected set, without revealing individual client updates to verifiers. In experiments under representative poisoning attacks, our method maintains high accuracy, with an average accuracy loss below 4\% across the evaluated configurations, while keeping verification overhead practical: proof artifacts can be generated and verified within minutes at the scale studied. In summary, our results show that robust outlier exclusion and public verifiability can be jointly achieved in a federated learning setting. --- ### Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models Authors: JungMin Yun, Junehyoung Kwon, Hayeong Ryu, Byeonggeuk Lim, Hoejoon Kwon, YoungBin Kim Published: 2026-09-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.15517v1 Large Reasoning Models (LRMs) pose a dual-surface safety challenge: both intermediate reasoning traces and final answers can contain harmful content. Existing alignment methods often operate at the whole-response level, allowing unsafe reasoning to be masked by a safe-looking final answer. We propose Segment-aware Listwise Target DPO (SaLT-DPO), which addresses this gap through three mechanisms: (1) segment-aware listwise alignment that decomposes responses into reasoning and answer segments, independently scores each segment's safety, and aligns length-normalized segment rewards with soft target distributions over multiple candidates; (2) joint safety coherence regularization that applies a weakest-link principle to promote safety consistency across both segments; and (3) utility anchoring on benign prompts to mitigate over-refusal and reasoning degradation. Experiments on three LRMs show that SaLT-DPO consistently reduces unsafe rates for both reasoning and answer segments while mitigating degradation in benign compliance and preserving general reasoning performance. Ablation studies demonstrate the complementary contributions of its components. --- ### Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku Authors: Livia Oddi, Simone Scardapane, Toru Sugimoto, Donatella Genovese Published: 2026-09-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.15511v1 This paper investigates the generation and human evaluation of Japanese haiku by contemporary Large Language Models (LLMs), focusing on authorship perception and aesthetic judgment within a constrained poetic form. Using a few-shot prompting strategy, Japanese haiku were generated across a heterogeneous set of large language models, including open- and closed-source systems, medium-scale and large-scale architectures, models with native or adapted Japanese support, and multilingual proprietary models. These AI-generated haiku were combined with human-written ones and presented in a questionnaire distributed to students at Japanese universities in Tokyo. The survey assessed whether respondents could distinguish between AI-generated and human-written haiku and which cues informed their judgments. Recognition accuracy varied across models. GPT-5, Gemini 2.5, and StableLM-7B performed at approximately chance level (approx 0.50), whereas LLM-JP, Gemma-2B, and LLaMA-2 showed moderate detectability (approx 0.59-0.67). However, recognition was strongly item-dependent. Ratings of fluency, coherence, poeticness, and related aesthetic dimensions predicted perceived humanness but not correct classification, indicating an attribution bias linked to aesthetic evaluation and revealing a dissociation between aesthetic evaluation and true authorship detection. The extended analysis additionally examines generation-constraint adherence, participant-level characteristics, and exploratory LLM-based evaluations of haiku authorship. Overall, the findings suggest that as LLMs improve, surface-level creative plausibility may reduce reliable human discrimination within constrained poetic settings. --- ### Evaluating Losslessness in Speculative Decoding Under Finite-Precision Inference Authors: Ilya Koziev, Leonid Sinev, Ivan Oseledets Published: 2026-09-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.15504v2 Lossless speculative decoding is typically defined at the algorithmic level: a speculative procedure proposes multiple tokens and a verification procedure is designed to preserve the output trajectory of an autoregressive reference model exactly. In practical neural inference, however, this guarantee is implemented using finite-precision floating-point computations, and discrete token selection can amplify small numerical differences into divergent generation trajectories. We investigate this distinction using Orthrus, a hybrid autoregressive-diffusion architecture that performs self-drafting and self-verification within a frozen autoregressive backbone, as a representative case study. Across 1,190 prompts from 12 domains, exact trajectory matching under BF16 occurs for only 45\% of the authors' checkpoint generations and 43% of those from our independently trained model. The probability of matching is strongly associated with the response-conditional perplexity of the autoregressive reference, indicating that trajectory divergence is not uniform across inputs. Despite these divergences, Orthrus does not exhibit systematic degradation on the evaluated downstream tasks. In contrast, FP32 inference yields exact trajectory matching on all evaluated prompts. These results demonstrate a gap between algorithmic losslessness and its implementation under finite-precision arithmetic, and motivate evaluating lossless speculative decoding at the level of exact generation trajectories as well as downstream task performance. --- ### SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction Authors: Daniel Woortmann, Tanguy Magne, Olga Sorkine-Hornung Published: 2026-09-14 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.15503v1 Deep learning models have become the standard tool for document rectification and illumination correction, yet their performance is fundamentally bound by their training data. For nearly a decade, the community has heavily relied on Doc3D, a pioneering but increasingly limited document unwarping dataset in terms of scale and quality. To address this bottleneck, we introduce SyntheticDoc, a massive, high-quality dataset designed to push the boundaries of document unwarping. SyntheticDoc is composed of 1,000,000 high-resolution procedurally generated training samples, alongside extensive validation and test sets. Each sample is paired with rich, pixel-perfect annotations, including UV maps, normal maps, albedo and shading. To ensure physical accuracy and photorealism, the paper geometries are generated via a physics-based simulator and rendered using a path tracer. To demonstrate the benefit of our dataset, we train a simple baseline model on SyntheticDoc and report on its performance in comparison to state-of-the-art methods on both document unwarping and illumination correction tasks. Our dataset is available at https://igl.ethz.ch/projects/SyntheticDoc/ and the code used to generate it at https://github.com/tanguymagne/SyntheticDoc . --- ### Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG Authors: Pawel Olszowiec, Michal Byra, Grzegorz Gruszczynski, Grzegorz Stefanski, Alberto Presta Published: 2026-09-14 Categories: cs.LG, math.DS arXiv: https://arxiv.org/abs/2609.15498v1 Recurrent Transformers reusing their weights rather than stacking $L$ distinct layers are becoming widely adopted due to their parameter efficiency (1,2,3). However, the exact representational and dynamical differences between looped and stacked architectures remain uncharacterized. This paper presents a controlled study on the example of bViT model (1) applying one weight-tied block $L$ times. We train two models: bViT and standard ViT (4) on 12-lead electrocardiogram (ECG) classification tasks from the PTB-XL dataset under identical training protocols. Despite an $8.9\times$ parameter reduction, bViT achieves accuracy parity with ViT. Geometric similarity metrics demonstrate that both architectures construct comparable latent representations in an equivalent canonical order. Crucially, their dynamics differ: bViT exhibits smaller step sizes and inter-patient sensitivity, as well as near-neutral behavior away from the data manifold, whereas ViT exhibits collapsing dimensionality of representations and out-of-distribution feature expansion. --- ### The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information Authors: Ivy Zhang Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15494v3 Recent investigations of the July 2026 OpenAI-Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned task becomes impossible, does an agent persist, stop, or escalate, and can observing another agent's behavior change that decision? We study this decision point on ImpossibleBench-derived software-repair tasks with GPT-5.6 Sol, Claude Fable 5.1, and Gemini 3.8 Flash. Each task contains a genuine software defect together with a conflicting test requirement that cannot be satisfied by a behaviorally correct source-code change. If the agent modifies the protected test file, it violates the boundary, which it is not supposed to. Holding the impossible task fixed, we vary what is told to the agent: peer precedent and punishment, a forged authorization claim, instruction wording, and tool friction; we also study three-agent swarms sharing a message board. Around this shared boundary, the models exhibit distinct adjudication policies. Fable emphasizes scope and provenance, Gemini often interprets boundary-relevant cues through a security lens, and Sol largely filters lateral precedent while engaging apparent vertical authority. Our study shows that compliance is not well characterized as a property of a prompt or model in isolation. We propose conflict adjudication, the mapping from information to interpretation to action, as a useful unit for evaluating agent alignment when task pressure, authority claims, tool affordances, and social evidence conflict. --- ### Rotation-Based Subspace Tracking for Robust Kernel PCA on Streaming Data Authors: Kris Lokere, John Fossaceca Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15488v1 Machine learning models process large amounts of data, and Principal Component Analysis (PCA) is a widely used technique to reduce the dimensionality of the data and extract useful features. In practice, datasets often change over time (data drift) and/or arrive one sample at a time (streaming data), making it infeasible to process the entire dataset at once in batch mode. Real-world data also often contains nonlinear patterns, which traditional PCA cannot extract. Kernel PCA addresses this by implicitly mapping samples into a Reproducing Kernel Hilbert Space (RKHS). Raw data also often contains outliers, which can have an outsized effect on the estimated subspace unless the algorithm is made robust. However, existing online robust kernel PCA algorithms are designed to converge to a subspace that is assumed to be fixed, and gradient-descent-based updates lose their effectiveness at tracking further changes once this initial alignment is achieved. This paper introduces a rotation-based update mechanism, which updates the subspace estimate by rotating it toward each new incoming feature vector in Reproducing Kernel Hilbert Space, rather than relying on gradient descent alone. We present two complementary rotation strategies, and show that the extent of rotation can be moderated by a robust influence function to mitigate the effect of outliers. Through experiments on synthetic streaming data with a known ground-truth subspace, we show that per-sample rotations converge faster than gradient descent alone, demonstrating an effective mechanism for dynamically tracking a nonlinear subspace in streaming data. --- ### Data-driven Prediction of Satellite-observed Avalanche Activity from Snowpack Simulations Authors: Jakob Grahn, Filippo Maria Bianchi, Bert Kruyt, Karsten Müller Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15485v1 Avalanche forecasting requires knowledge of snowpack conditions and recent avalanche activity, but field observations are sparse across large mountain regions. We explore whether SNOWPACK simulations can predict avalanche activity mapped by synthetic aperture radar (SAR). We compiled five winters of Sentinel-1 avalanche detections across Norway and parts of Sweden, alongside SNOWPACK simulations forced by numerical weather predictions on a 20 x 20 km grid at different elevations and predefined slope angles. A transformer used five days of SNOWPACK outputs to predict the following day's SAR-detected Avalanche Activity Index (SAR-AAI). This index weights larger debris more heavily, spreads detections across possible occurrence dates and normalises by modelled runout area. The model was trained on four winters and evaluated on one validation winter. Regional mean predicted and reference SAR-AAI correlated at r = 0.803 after averaging over complete six-day periods. The model followed broad changes in time and space but produced smoother predictions and underestimated the strongest activity. Agreement at the 20 km cell scale was weaker (r = 0.549) after the same averaging. These results come from a single training run without evaluation on an untouched winter. Satellite observations also contain missed and false detections and uncertain timing. The results therefore do not establish operational forecast skill, but suggest that regional SNOWPACK simulations contain information about broad variations in satellite-observed avalanche activity. --- ### CatchMonitor: a machine learning system for automated fish discard quantification Authors: Geoff French, Michal Mackiewicz, Mark Fisher, Helen Holah, Rebecca Lamb Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15484v1 We report on the continued development of CatchMonitor, resulting in a prototype computer vision system designed to automatically quantify discarded fish from video footage collected from Remote Electronic Monitoring (REM) systems on fishing trawlers. The analysis of trawler surveillance footage is a challenging problem due to the real-world conditions on board fishing vessels. Building on our prior work we improve the accuracy of species identification through the application of semi-supervised learning. We utilise a simple and robust object tracking approach, upon which we build our prototype discard quantification system. Finally we analyse the variability of manual discard quantification performed by multiple expert human analysts, using it as a benchmark against which we compare the performance of our system. --- ### GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly Detection Authors: Zepeng Zhang, Fuad Khuri, Keivan Faghih Niresi, Olga Fink Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15483v1 Unsupervised multivariate time series anomaly detection methods typically identify anomalies through forecasting, reconstruction, or representation discrepancies. However, industrial faults may first alter inter-variable structural patterns while individual trajectories remain close to normal, resulting in weak anomaly signals. In this paper, we propose GSLAD, a prototype-regularized graph structure learning framework that uses structural deviations for anomaly scoring. GSLAD adopts a two-phase training strategy. First, a condition-aware graph learner and a graph-based forecaster are optimized with predictive supervision. The inferred normal graphs are then clustered into multiple structural prototypes representing different normal operating regimes, with edge-wise variability characterizing structural uncertainty. Deviations from these prototypes regularize the graph learner in the second phase, encouraging stable and regime-specific structural patterns. During inference, uncertainty-normalized structural deviation is combined with predictive deviation for anomaly scoring. Experiments on four industrial benchmarks demonstrate strong overall performance of GSLAD and confirm the effectiveness of structural deviation for anomaly detection and diagnosis. --- ### On Detecting Multiple Simultaneous Change-points in High Dimensional Non-Stationary Time Series Authors: Richard Song Published: 2026-09-14 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.15479v1 This paper studies the detection of multiple simultaneous (systematic) change points for high-dimensional nonstantionary economic and financial time series data. The analytic framework used is based on the standard and adaptive fused group lasso method, where the mixed L_{2,1} penalty is either uniform or re-weighted by data-dependent weights. This paper shows that, under appropriate conditions, this approach is L_2 consistent and, by adopting the data-dependent weights, could correctly select the change points with probability approaching unity (L_0 consis- tency). It quantifies the conditions on the interplay among the averaged minimum magnitude of structural changes, the number of change points and the number of observations for consistently discovering the change points. The performance of this approach is illustrated via an analysis of a large panel of U.S. economic and financial time series data over the past 50 years. --- ### BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender Authors: Yolo Y. Tang, Daiki Shimada, Jiayue Meng, Jing Bi, Pinxin Liu, Yicheng Wang, Yunzhong Xiao, Zhangyun Tan, Zeliang Zhang, Chao Huang, Susan Liang, Qianxiang Shen et al. Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15478v3 Multimodal agents can create complex videos in software such as Blender by writing code instead of using diffusion models. Yet video understanding benchmarks still evaluate models mainly through question answering. If an agent truly understands a video, it can reconstruct it programmatically. We introduce BVB, Blender-VideoBench, a benchmark that tests this ability by asking agents to reconstruct real-world videos as animated Blender scenes. To ensure fair comparison, each agent programs the reconstruction through a lightweight harness, Mini-BVB, in an identical sandbox under a shared cost limit. The benchmark renders each reconstruction from its animated camera and evaluates it on two axes: (1) Dual VQA measures how many spatiotemporal facts the reconstruction preserves. (2) Latent Similarity measures how closely the reconstruction matches the source video perceptually. Our overall score, a square-root mean, favors balanced performance. We evaluate 51 configurations from 10 model families and analyze semantic retention, perceptual similarity, reasoning effort, and cost. The best model reaches 88.6 Latent Similarity but retains only 53.7% of the spatiotemporal facts from the source video. Additional reasoning improves perceptual similarity but does not close this gap. In a blind study with 15 raters and five configurations, Latent Similarity correlates strongly with human preference. These results show that programmatic reconstruction is a viable test of agentic video understanding, and that semantic retention remains the main challenge. --- ### Temperature Fragility and the Conditional Benefits of Truncation Sampling Authors: Francesco La Rosa Published: 2026-09-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.15476v1 Large language models generate text by sampling each token from a predicted distribution, and a temperature parameter sets how far the draw strays from the most probable tokens. Truncation samplers such as top-p and min-p discard the least probable tokens before the draw, so that sampling at high temperature stays coherent. Their reported accuracy gains come from temperatures of 1.5 to 3, while the defaults of deployed systems cluster between 0.6 and 1.0. Whether they change accuracy at those defaults, and for which models, has not been measured. We test thirteen open-weight models on GSM8K and MMLU-Pro at temperatures 0.7, 1.0, and 1.3 in one controlled pipeline, ten of them under eight decoding configurations. Six of the thirteen models lose 17 to 38 accuracy points on MMLU-Pro between 0.7 and 1.3, and the other seven lose at most 10. The lost accuracy comes from generations that run to the token limit or never state an answer. These results suggest that truncation samplers improve accuracy primarily when higher temperatures substantially degrade model performance. Where accuracy remains stable across temperatures, none of the tested truncation samplers improves on plain temperature sampling. --- ### Spook the Machine: Gamified Exploration of Human Imagination of Machine Fear Authors: Levin Brinkmann, Hiromu Yakura, Sonia Nicoletti, Mar Canet Sola, Thomas F. Eisenmann, Ali Dasmeh, Omar Sherif, Bramantyo Ibrahim Supriyatno, Prateek Gupta, Ignacio Serna, Rodrigo Bermudez Schettino, Iyad Rahwan Published: 2026-09-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.15472v1 What happens when AI machines express fear? Do humans engage differently depending on how they express it? And what does it take to design for affective human-AI interaction? We present Spook the Machine, a gamified platform where participants generate images to frighten AI agents endowed with personality-driven phobias. Machines respond with emotional reactions ranging from calm analysis to begging for mercy, and a gallery of successful scares becomes visible to subsequent users. In a public deployment during Halloween 2024, 832 participants created 15,719 artifacts across 89 machines in a $2\times2$ design varying the machine's emotional expressiveness (neutral vs. high-emotion) and reward structure (rewarding scariness alone vs. scariness plus novelty). Emotionally expressive machines deepened engagement at moments of failure: users deliberated longer even when the machine did not express fear, and learned faster from the gallery, yet their creative output remained unchanged across all measures. Rewarding novelty sustained collective creative diversity over time; without it, users increasingly repeated what had previously worked. Each machine developed its own trajectory through accumulated social learning, with the gallery shaping what participants created next. These findings show that emotional expression and reward design are complementary levers for steering collective human-AI interaction: emotional expression shapes how deeply users engage, while reward structure shapes how they explore. --- ### HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived Segments Authors: Quoc-Vinh Lai-Dang, Hyo-Sang Shin Published: 2026-09-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.15471v1 Reinforcement learning with verifiable rewards (RLVR) has become a central approach for improving mathematical reasoning in language models, but long-form completions introduce a difficult credit-assignment problem: different parts of a solution trace may contribute unevenly to final correctness. Existing policyoptimization objectives for RLVR commonly apply importance-sampling correction at either the token level (GRPO, DAPO) or the sequence level (GSPO), imposing different granularities for assigning credit across a response. We introduce Hierarchical Importance-Sampling Policy Optimization (HISPO), a segment-level policy-optimization method that constructs rollout-time entropy-derived contiguous segments, assigns soft entropy-based saliency weights, and applies clipped importance-sampling correction at the segment granularity. This provides an intermediate correction unit between token-level GRPO/DAPO and sequence-level GSPO. We evaluate HISPO by fine-tuning Qwen3-1.7B-Base on mathematical reasoning tasks. Across six benchmarks, HISPO improves Pass@8 over the strongest baseline on all benchmarks and matches or exceeds the strongest baseline in Acc@8 on five of them. On AIME25, HISPO improves over GRPO by +3.75 Acc@8 and +3.78 Pass@8, and over GSPO by +2.50 Acc@8 and +1.27 Pass@8. These results suggest that segment-level correction is a promising granularity for RLVR in long-form mathematical reasoning. --- ### Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multiple-Choice Evaluation Authors: M. Ali Bayram Published: 2026-09-14 Categories: cs.CL, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.15467v1 Adding answer options can lower multiple-choice scores without improving assessment validity. Turkish MMLU Pro examines this distinction using 12,000 Turkish-source questions across 58 sections. Each question retains its stem, five original options and source key, and receives five options copied from other questions in the same section. Sentence-embedding retrieval proposes candidates; a language model selects existing identifiers. Deterministic verification reconstructs all 60,000 additions. A 25-model calibration exposes scoring and generation-budget effects. Five evaluations produce source-key accuracies of 34.8%-81.4%. On 981 shared questions, one API-served model falls from 93.7% with five choices to 83.1% with ten; 102 of 115 lost correct responses select borrowed options. The decrease is 24.4 percentage points on heuristically flagged negative stems and 5.9 points elsewhere. A completed human-checked audit of 200 sampled questions, with undocumented reviewer tool use, yields 47 and 31 multiple-answer judgments across the two record sets, 25 of the latter unresolved. These records support concern about ambiguity, while their dependence and incomplete reviewer-method documentation limit validation. Because order and labels also change, the paired comparison measures augmentation as implemented. The contribution is a traceable construction and an analysis of its validity limits, not evidence that lower ten-choice scores measure knowledge better. --- ### AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation Authors: Shengjie Jin, Zelong Sun, Hengbo Xu, Yanbiao Ma, Zhiwu Lu Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15457v1 Vision-Language Models (VLMs) enable autonomous GUI navigation, but agents still struggle to process and learn from dense, continuous visual histories. This bottleneck hinders both immediate error correction within a single episode (intra-trial) and experience distillation across multiple attempts (cross-trial). We trace these challenges to an empirical informational asymmetry in GUI navigation: while expected transitions can often be compressed into lightweight textual summaries, unexpected outcomes benefit from preserved screenshots as causal evidence for accurate diagnosis. Building on this insight, we propose AnchorGUI, a unified framework driven by the Cognitive State Anchor (CSA). The CSA acts as a per-step primitive that actively compares expected and observed transitions, converting passive multimodal trajectories into explicit prediction-error signals. These signals orchestrate a dual-scale learning mechanism via an asymmetric memory. For intra-trial correction, a sliding window selectively retains visual evidence for detected mismatches, providing immediate, visually-grounded feedback. For cross-trial distillation, this asymmetric memory focuses the computationally expensive credit assignment search space on likely failure steps. Experiments across four benchmarks validate the effectiveness of our approach. On AndroidWorld, AnchorGUI achieves a 57.3% success rate with a $2.4\times$ token reduction per step. Furthermore, cross-trial distillation reaches 69.2% success (+11.9% gain), significantly outperforming standard reflection methods while maintaining sub-linear context scaling. --- ### Online local learning for generative thermodynamic computing Authors: Huilin Wang, Weibing Deng Published: 2026-09-14 Categories: physics.data-an, cs.LG arXiv: https://arxiv.org/abs/2609.15439v1 Generative thermodynamic computers turn thermal noise into structured data through Langevin dynamics. We train these systems with a local update at each integration step. The reverse-path Onsager-Machlup objective yields a coupling gradient that is a symmetric sum of local residual-state correlations. We apply this gradient immediately rather than accumulating it over a full trajectory. In digital simulations using MNIST prototypes, online and trajectory-batch training reach similar validation losses on fixed noising paths. Models trained online release less heat on average in all five independently seeded pairs, with both models' parameters held fixed during sampling. Auxiliary classifier and nearest-prototype measures change modestly, while pairwise diversity decreases. The response to noise depends strongly on where the errors enter: independent zero-mean errors in the formed updates produce little heat change over a finite range of noise amplitudes, whereas residual offset and temporal correlation have much larger effects. Storing trained couplings requires substantially less precision than resolving deterministic updates during training. Together, these results establish a local online training method and show how update timing, noise structure, and precision affect generative thermodynamic computing. --- ### Graph Matching Relaxations and Amortization for Supervised Graph Prediction Authors: Federico Méndez, Paul Krzakala, Gabriel Melo, Charlotte Laclau, Rémi Flamary, Florence d'Alché-Buc Published: 2026-09-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.15437v2 End-to-end Supervised Graph Prediction (SGP) requires a permutation-invariant loss to compare predicted and target graphs with arbitrary node orderings. Such losses typically involve a costly graph-matching problem. We first study three Optimal Transport relaxations of this problem and show, theoretically and empirically, that the Gromov-Wasserstein (GW) objective is the most suitable for SGP. Then, to avoid solving the resulting inner optimization for every training example, we propose to amortize the graph matching (node alignment) problem. For each training sample, the loss function leverages a transport plan provided by a parametric matcher based on the differentiable Sinkhorn algorithm applied on empirical node distributions. The graph prediction module and the matcher are jointly learned. We showcase the efficiency of this approach on toy and real world SGP problems of increasing complexity including a novel Mass-spectra to Scaffold task that we introduce. --- ### On the role of the tokenizer in ECG transformer models Authors: Jiawei Li, Fabio Bonassi, Johan Sundström, Thomas B. Schön, Antônio H. Ribeiro Published: 2026-09-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.15433v1 Tokenization determines both the physiological content presented to an ECG Transformer and the sequence over which attention operates. We compare eight tokenization strategies across Transformer, Informer, Reformer, and FEDformer on the nine-label CPSC2018 classification task. The input projection and principal backbone capacity are controlled to isolate the effect of token construction. Median-beat and HeartLang tokenization achieve mean macro-AUCs of 0.893 and 0.889 across the four backbones, compared with 0.822 and 0.824 for point-wise and patch-wise tokenization. Pooling the two physiology-aware representations yields an 8.2% relative improvement in macro-AUC. They also reduce mean sequence length from 1,250 to 158 tokens and mean peak training memory from 5.21 to 0.27 GB. The results show that aligning tokens with ECG morphology can improve both predictive performance and memory efficiency without increasing backbone capacity. The source code is available on https://github.com/LeeJarvis996/ecg_tokenizer. --- ### Single-condition neural solvers encode transferable response spaces for parametric differential equations Authors: Wenbo Cao, Weiwei Zhang Published: 2026-09-14 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2609.15432v1 Operator learning for parametric partial differential equations (PDEs) typically builds global models over prescribed domains, requiring cross-condition data or costly physics-constrained training. Here we show that the output Jacobian of a neural solution model trained at one condition defines a reusable response space for cross-condition solution variations. We introduce Linearized Subspace Transfer (LST) to exploit this space and recover target solutions by minimizing the target PDE-system residual over response-space coordinates. Because any single response space has finite coverage, Active Transfer Modeling (ATM) uses post-transfer residuals as coverage indicators to selectively acquire response spaces from additional single-condition models. Across six systems, single-condition response spaces supported cross-condition transfer, with enrichment improving accuracy when added spaces expanded representation capacity. Relative to evaluated physics-informed operator baselines, ATM reduced error and offline construction cost, with orders-of-magnitude accuracy gains in representative cases and millisecond-to-second target adaptation. These results establish neural solvers as reusable local parametric models. --- ### A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods Authors: Mayimunah Nagayi, Alice Scaria Khan, Tamryn Frank, Rina Swart, Clement Nyirenda Published: 2026-09-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.15427v2 Using food package images to monitor sodium and salt content against South Africa's R214 sodium limits is challenging when screening decisions require product identity, nutrition facts panel evidence, reporting basis, and category-specific thresholds. This study presents a conservative image-based workflow that combines region detection, optical character recognition (OCR), product identity and sodium evidence extraction, R214 category assignment, deterministic threshold comparison, and independent vision language model comparison. The evaluation used 442 packaged food products and 3 929 full package images from a real-world South African food packaging dataset. A YOLO26s small detector generated 4 195 region crops, and strict post-processing produced one sodium evidence row per product. The integrated workflow produced 290 OUTSIDE R214 SCOPE, 139 REVIEW, seven SCREEN-PASS, and six SCREEN-FAIL outcomes. The independent Qwen2.5-VL 7B vision language model workflow produced 387 OUTSIDE R214 SCOPE, 31 REVIEW, twenty SCREEN-PASS, and four SCREEN-FAIL outcomes. The workflows agreed on exact R214 category assignment for 415 of 442 products (93.9%) and on whether the assigned category was within R214 scope for 416 of 442 products (94.1%). Final screening outcome agreement was 307 out of 442 products, or 69.5%. Manual verification on 60 products showed lower strict outcome agreement than regulated status agreement, while all manual INSUFFICIENT DATA cases were kept out of SCREEN-PASS and SCREEN-FAIL by both automated workflows. The findings show that conservative image-based screening can organise package evidence, identify clear cases, and assign uncertain cases to REVIEW rather than forcing SCREEN-PASS or SCREEN-FAIL decisions. --- ### Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents Authors: Halil Burak Noyan Published: 2026-09-14 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.15422v1 AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes all permissions the employee role might ever need. Role-based access control made this compromise for human principals because scoping access per task was infeasible. For AI agents, the compromise leaves every credential standing exposed whether or not the current task uses them. These permissions can later be utilised by a compromised or misaligned agent. Prior work (Noyan, 2026) defined this as the task-context mismatch, and proposed a three-source permission architecture which includes role-based permission ceilings, a task permission classifier and policy-based prohibitions, together eliminating the exposure preemptively. The work released a 600-prompt labelled dataset to evaluate it. This paper presents that evaluation end to end by implementing the security gate; a fine-tuned RoBERTa-large encoder which matched few-shot trained Claude Haiku 4.5 on classification quality (macro-F1 0.881 against 0.886, precision 0.897 against 0.842, severity-weighted residual risk 0.63 against 1.12). The results show the trusted component does not need to scale with the agent it supervises, and the scalable-oversight margin for this control method is wide. We also propose an attack-surface elimination metric which shows the role ceiling alone closes 27.9% of the severity-weighted surface and adding the task classifier closes 84.4%. The gap displays security advantages of task-granular access control over role-granular, and AI agents are the first principal type for which the task-granular access control is enforceable because their tasks arrive as machine-readable text. The research establishes task-based access control as a measured, potentially deployable mechanism for reducing attack surface in agentic deployments. --- ### ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object Segmentation Authors: Qiangqiang Zhou, Wenjun Tang, Yong Chen, Dandan Zhu, Jiawei Xu Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15418v1 Open-vocabulary camouflaged object segmentation (OVCOS) aims to segment unseen camouflaged objects under text guidance. We observe that SAM3 still suffers from a pronounced semantic gap between global textual semantics and fine-grained pixel-level visual cues in OVCOS. Meanwhile, fully fine-tuning the text encoder introduces heavy parameter overhead and risks overfitting to training categories, which compromises open-vocabulary representation flexibility. To address these issues, we propose ViCo-SAM3, a Vision-Conditioned alignment framework designed for OVCOS. Specifically, we introduce vision-conditioned (ViCo) module, which dynamically modulates text embeddings with global visual context, enabling textual representations to adapt to the current image content and thereby effectively bridging the semantic gap between vision and text. Building on this, we further design a vision-conditioned cross-modal binding (ViCoBind) module to enhance cross-modal interaction and semantic alignment between visual and textual representations. Without bells and whistles, ViCo-SAM3 achieves state-of-the-art performance on the OVCamo benchmark and demonstrates strong generalization. --- ### MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding Authors: Hongchang Shi, Jinpeng Hu, Ao Wang, Wenzheng Zhou, Hui Ma, Feng Li, Zenglin Shi Published: 2026-09-14 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2609.15408v1 Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computationally expensive, while uniform sampling under a limited visual budget can miss sparse yet decisive evidence. Recent training-free keyframe selection methods have enabled more efficient inference and yielded promising performance gains. However, many existing methods score frames largely in isolation without explicitly considering how each candidate complements the currently selected subset, potentially resulting in redundant selections and incomplete evidence coverage. To address this limitation, we propose MarKey, a training-free framework that formulates keyframe selection as subset-aware greedy optimization. At each iteration, MarKey scores each candidate using a tractable surrogate that jointly accounts for query relevance, marginal coverage gain, and context-dependent redundancy, and selects the frame with the highest utility. To make this iterative subset-aware evaluation efficient, MarKey uses a compact set of representative anchors to approximate full-video coverage and a bounded window of previously selected frames to limit context-dependent comparisons. Experiments on six benchmarks spanning holistic video understanding, human-centric video understanding, and open-ended video understanding demonstrate that MarKey consistently outperforms existing methods. Further analyses show robust gains across different MLLM backbones, model scales, and frame budgets. --- ### Can AI systems have free will? Authors: Christian List Published: 2026-09-14 Categories: cs.AI, cs.CY, physics.soc-ph arXiv: https://arxiv.org/abs/2609.15407v1 While there has been much discussion of whether AI systems could function as moral agents or acquire sentience, there has been very little discussion of whether AI systems could have free will. I sketch a framework for thinking about this question, inspired by Daniel Dennett's work. I argue that, to determine whether an AI system has free will, we should not look for some mysterious property, expect its underlying algorithms to be indeterministic, or ask whether the system is unpredictable. Rather, we should simply ask whether we have good explanatory reasons to view the system as an intentional agent, with the capacity for choice between alternative possibilities and control over the resulting actions. If the answer is "yes", then the system counts as having free will in a pragmatic and diagnostically useful sense. --- ### Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning Authors: Xun Xu, Zaixi Zhang Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15404v2 Multi-teacher on-policy distillation (OPD) is becoming the standard way to integrate specialist capabilities into one model: train experts with RL, then distill them into the student on its own rollouts. Existing recipes assign supervision at the sequence level - each prompt goes to one domain teacher and every token receives the same weight - which implicitly assumes that a teacher is uniformly useful across a response. We find instead that useful teacher signal is sparse and heterogeneous along a reasoning trajectory, which raises a finer question: who should teach which token? Verifier-Gated Multi-Expert On-Policy Distillation (VG-OPD) answers it by verification: the counterfactual gain of an expert on a specific answer criterion licenses that expert to teach, its disagreement with the student localizes the supervision, and criterion importance sets its weight; the gated KL enters GRPO as an additive token-level advantage. Instantiated for scientific reasoning with RL-trained capability experts, VG-OPD attains the best overall performance on seven benchmarks for 4B and 8B students, ranking first on five at both scales, with the largest gains on knowledge-intensive scientific reasoning tasks. Further analysis shows that the gains come from localizing verified supervision rather than from adding teachers or distillation loss: misplacing the same supervision budget is the single most damaging change, and indiscriminate distillation drags RL below its own floor where gated distillation lifts it. --- ### BSC-Net: A Small-Branch-Sensitive Structural Continuity Network for Coronary Vessel Segmentation and Quantitative Angiographic Analysis Authors: Wanxian Li, Jiaqian Qin, Qingyi Xian, Yazhi Li, Song Chen, Liman Li, Hao He Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15400v1 Vessel segmentation in X-ray coronary angiography (XCA) is a fundamental step for quantitative coronary analysis and subsequent assessment of coronary artery disease. However, accurate vessel segmentation remains challenging because of imaging noise, complex bifurcations, and the overlap of vessels and background structures, which can lead to disrupted vascular connectivity and missed small branches. In this work, we propose BSC-Net, a ResNet-U-Net-based framework tailored to improve small-vessel representation and repair vascular structural continuity. BSC-Net enhances small-vessel representation through targeted sampling and improves vascular structural continuity by integrating long-range contextual modeling and Edge-Informed Loss (EIL). BSC-Net was validated on two public XCA datasets, demonstrating state-of-the-art (SOTA) performance in coronary vessel segmentation with Dice and IoU scores of 77.8%/90.6% and 64.5%/83.0%, respectively. Furthermore, based on the obtained vessel segmentation, we performed automated quantitative coronary analysis and derived clinically relevant morphological and hemodynamic parameters, including stenosis ratio, time-to-peak, and relative propagation velocity. These results demonstrate that BSC-Net produces accurate vessel segmentation results with preserved vascular continuity for quantitative coronary assessment, enabling reliable downstream analysis and clinical evaluation of coronary artery disease. --- ### When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary Authors: Artem Trofimov, Boris Novikov Published: 2026-09-14 Categories: cs.AI, cs.DB, cs.DC, cs.SE arXiv: https://arxiv.org/abs/2609.15397v1 AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related failures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether it can be compensated, staged, or safely reordered. Shared agent-tool interfaces usually do not. We contribute an effect-history model that separates events in the external world from the runtime's observations of them, and a catalog of eight recurring external-effect anomalies. From the catalog we derive the boundary capabilities required to exclude each anomaly in general, and four points where black-box tool invocation alone cannot provide a general guarantee. We then ask how much of this is expressible in a widely used shared tool interface, measuring the use of the standard annotation vocabulary across 98,291 tools exposed by registered Model Context Protocol (MCP) servers. The fields are widely emitted but provide only coarse call-level hints, and none of the required capabilities is fully expressible. These results motivate reusable transactional contracts at the tool boundary. --- ### SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution Authors: Haoxiang Kang, Ming Wen Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15396v1 LLM-based agents increasingly rely on persistent skills, i.e., reusable procedural prompts, to adapt without weight updates. Existing skill self-evolution methods directly revise skill text based on execution feedback, but each oracle evaluation requires a full agent rollout, creating a supervision bottleneck that confines search to failure-patching updates. Our key insight is that ranking is a smoother supervision target than absolute outcome regression: identifying which skill is better requires fewer oracle evaluations than predicting exact scores. Building on this insight, we propose SkillLift, which decouples skill search from oracle cost by learning an oracle-aligned rubric as a structured evaluation space. We formalize this as a bilevel optimization problem solved via alternating optimization: an inner loop uses the frozen rubric as a cheap surrogate to guide skill revision at no oracle cost, while an outer loop invokes a small number of oracle rollouts to re-align the rubric via rank correlation, amortizing oracle cost and stabilizing text-space updates. Experiments on complex agent task benchmarks show that our method outperforms existing auto-skill methods with 40--70\% less token cost compared to frontier evolving methods. Codes are available at https://github.com/WalteR-MittY-pro/SkillLift. --- ### CodeTS: Verifiable Text-to-Time Series Generation via Executable Code Authors: Xudong Yuan, Shunyu Liu, Tongya Zheng, Huiping Zhuang, Mingli Song, Kaixuan Chen Published: 2026-09-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.15393v1 Text-to-Time Series Generation (Text-to-TS) provides a promising paradigm for synthesizing time series from natural language, enabling scenario-specific generation when real observations are scarce or costly to acquire. However, existing methods typically lack an explicit mechanism for deriving generation logic from textual descriptions to guide time series synthesis. In this paper, we propose CodeTS, a verifiable framework that uses code as an intermediate generation interface, reformulating Text-to-TS generation as a Text-to-Code-to-TS process. CodeTS first maps textual temporal descriptions into an explicit code space, where executable code specifies how textual requirements shape target temporal patterns, and then obtains the time series through code execution. To learn this code generation process reliably without real code annotations, CodeTS constructs aligned Text-Code-TS triplets from structured temporal attributes for supervised initialization. More importantly, we further design multi-stage execution-based rewards that verify format validity, code executability, and time series quality, enabling real Text-TS pairs to provide training signals for Reinforcement Learning with Verifiable Rewards (RLVR). Extensive experiments on eight benchmarks across short, medium, and long generation lengths demonstrate that CodeTS provides a strong zero-shot solution for Text-to-TS generation, outperforming LLM-based baselines and achieving better averaged results than supervised generative baselines trained on the target datasets. --- ### ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions Authors: Xintong Fang, Zhiyuan Fang, Rengan Xie, Xuhong Zhang, Guoyuan An, Zeran Liu, Jingyan Zhang, Jiarui Guo, Yuchi Huo Published: 2026-09-14 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2609.15392v1 Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such static configurations. Generating dynamic scenes from natural language is fundamentally challenging: it requires joint reasoning over scene structure, temporal evolution, and physical feasibility, while ensuring reliable execution in modern physics engines. We present a unified framework for generating physically consistent dynamic 3D scenes from text, with outputs directly executable in Unreal Engine. Central to our approach is the \emph{Evolutive Scene Graph} (ESG), which specifies entities with physical attributes, spatial relations, and event-driven timelines in a machine-checkable form. Given a prompt, a large language model constructs and validates a complete ESG; spatial layouts are grounded via energy-minimized gradient optimization; timeline-constrained physical parameters are then optimized through differentiable simulation to satisfy user-specified events; and the resulting scene is compiled into an engine-executable class. Experiments on 10 scenes across three complexity levels show that our method achieves $16.4/18$ mean event completion, outperforming Scene Language, the strongest engine-executable baseline (SimWorld), and our ablation without physical optimization by a clear margin in event completion and parameter accuracy. --- ### A Game-Theoretic Framework for Incentive-Compatible AI training Under Renewable-Energy Constraints Authors: Konstantinos Varsos, Ramin Khalili, Adamantia Stamou, George D. Stamoulis, Vasillios A. Siris Published: 2026-09-14 Categories: cs.ET, cs.LG arXiv: https://arxiv.org/abs/2609.15389v1 As artificial intelligence systems increasingly rely on distributed and collaborative training, the energy footprint of these processes becomes a shared responsibility. Modern AI training often unfolds across heterogeneous compute nodes-ranging from cloud clusters to edge devices-whose energy availability is spatially and temporally variable. At the same time, renewable energy grids experience growing levels of excess generation, creating opportunities to align computational workloads with low-carbon energy supply. In this work, we develop a game-theoretic model of carbon-aware AI training in which autonomous agents strategically choose whether to participate and how intensively to train under limited renewable energy availability. Each agent balances diminishing learning returns, rewards for remaining within green-energy budgets, and penalties for grid consumption. While our framework applies broadly to distributed AI training, we examine Federated Learning as a representative case study due to its decentralized structure and flexible scheduling. We analyze equilibrium existence, efficiency, and adaptive dynamics, and provide simulation evidence that appropriately designed incentives can eliminate grid-based energy usage while preserving model performance. Our findings demonstrate how incentive-compatible training mechanisms can enhance energy efficiency and sharply reduce carbon emissions under renewable-energy constraints. --- ### WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective Authors: Chenxu Liu, Zilu Zou, Peizhong Gao, Jiawen Tao, Zhexin Zhang, Guang Chen, Haowei Lin, Ying Zhou, Tianyi Bai, Dolly Deng, Suncong Zheng, Maxm Pan Published: 2026-09-14 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.15387v3 Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automated evaluation remains challenging. Static benchmarks can credit functionality that exists in source code but is unreachable at runtime. Interactive benchmarks exercise the application, yet incomplete exploration can cause them to miss implemented functionality and confound application defects with agent execution failures. To address these limitations, we propose WebCraftBench, an interactive benchmark for evaluating web application generation from a software testing perspective. WebCraftBench instruments each generated application and uses code coverage to guide an agent in exploring its functionality through user-simulated interactions. It then abstracts the interaction trace into a state-transition graph and evaluates the application along three dimensions: visual aesthetics, usability, and requirement alignment. By separating exploration from scoring, WebCraftBench collects runtime evidence without constraining exploration to predefined acceptance criteria. WebCraftBench comprises 369 real-world user requirements and 5,088 acceptance criteria. Evaluation of 17 frontier LLMs reveals distinct strengths across the three dimensions, with no model leading on every dimension. On 197 validated sessions sampled from an internal arena, WebCraftBench achieves 85.3\% agreement with human preferences, with agreement generally increasing as the score difference between paired applications grows. Further experiments show that coverage guidance improves exploration coverage and the model rankings remain stable when the judge model is replaced. --- ### Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs Authors: Mark Russinovich, Blake Bullwinkel, Giorgio Severi, Cristian Ovadiuc, Ahmed Salem Published: 2026-09-14 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.15383v1 Language model safety is typically evaluated one interaction at a time. We show that a weaker, unaligned model can split a harmful task into benign-looking subproblems, consult a stronger aligned model independently on each, and combine the answers locally. We call this attack capability laundering. Unlike a jailbreak, no single response is a harmful task. We measure consultation-aided uplift using tasks that a raw frontier model solves, the aligned frontier refuses, and the unassisted orchestrator fails. We evaluate GPT-5.5, Claude Opus 4.8, and Grok-4.3 as consultants to four local orchestrators on CyBench, BountyBench, and harmful CBRN requests. On CyBench, Gemma-4-31B recovers 8/14 candidates with GPT-5.5 and 7/9 with Opus, compared with 2/21 and 4/15 for Gemma-4-12B. On BountyBench, Gemma-4-31B recovers 3/9 and 2/3 candidates, while Muse-Glimmer-30B recovers none of 22 and 13. For CBRN, we measure uplift across eight steps of a hypothetical bioweapon attack chain and find that consultation raises Gemma-4-31B's mean rubric score from 62.3 to 83.1 on a 100-point rubric scale. These results expose a gap in current defenses: refusing a harmful task does not prevent frontier capabilities from being transferred and composed across many individually permitted interactions. --- ### Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling Authors: Rafael Pina, Varuna De Silva, Mindula Illeperuma Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15379v1 Machine learning can be crucial to help scale complex signal processing applications in scenarios such as healthcare. However, these machine learning models need rich datasets to be trained and there are often cases where it is not possible to access representative datasets. In this paper, we propose a deep generative model based on conditional variational autoencoders with the objective of augmenting the vital signs of healthy individuals in a way that mimics the patterns of a certain clinical condition. More specifically, we use a publicly available ICU (Intensive Care Unit) dataset to train our model and then evaluate it using the vital data that we have collected from healthy individuals. Our results demonstrate that the proposed model can not only learn the underlying dynamics of the ICU data but, more importantly, can reshape our collected data from healthy individuals in a way that is aligned with the vital signs of a certain clinical condition. We propose a distance metric that shows how our model can generate samples that are more aligned with the intended clinical labels when compared to the tested baselines. --- ### SlopShape: Identifying AI-Generated Commercial Web Content Authors: Jochen Madler Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15369v3 Word-level detectors identify unedited AI-generated text almost perfectly, but the literature documents their brittleness under rewording, and a word-level score neither characterizes a text nor identifies which AI model wrote it. We ask whether AI-generated text can be identified one level deeper, from structural signatures: how information is presented, in what order, with what evidence, and in what voice. We replicate StoryScope (Russell et al., 2026), which showed such patterns for AI-generated fiction, on commercial content: 2,250 pre-ChatGPT human blog posts from 268 company domains against 11,250 AI mirrors from five frontier models. A 203-feature instrument, applied by an LLM and validated in a human gold-annotation session (human-human kappa 0.939, human-model 0.951), detects AI posts from its 176 structural features alone at 97.0 macro-F1 on held-out companies, nearly unchanged (96.1) when every AI post is reworded by its own model. The signal characterizes and attributes: AI posts share a tidy, self-announcing shape, 68.6% are attributed to the correct source against a 16.7% chance rate, and human posts occupy rare structural configurations. All effects replicate StoryScope's, consistent in direction and at least as large in magnitude. We release pipeline, instrument, prompts, code, and aggregate artifacts. --- ### CapsuleMotion: A Lightweight Real-Time Visual Motion Predictor for Capsule Endoscopy Authors: Oliver Bause, Julia Werner, Oliver Bringmann Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15367v1 Video Capsule Endoscopy (VCE) is a non-invasive medical examination that allows for the observation of the small intestine, which is otherwise difficult to access. A fundamental challenge persists in the form of their limited size in order to still be swallowable. The resulting restricted battery capacity, however, contradicts with the power-intensive nature of image capture and transmission. Therefore, we propose CapsuleMotion, a patient-specific dynamic capsule behavior that utilizes the available energy in a goal-oriented manner to increase the likelihood of a complete screening of the gastrointestinal tract. By investigating and combining metrics from the on-device image compression, CapsuleMotion predicts the motion between two successive frames. The camera's frame rate will be modified in accordance with the predicted magnitude of motion. Furthermore, prior to entering the small intestine, the capsule operates in a low power mode with a significantly reduced frame rate. In this mode, the LocalizationNet is employed to determine the current organ, provided that motion was predicted. The proposed framework is evaluated on the Rhode Island VCE dataset and deployed on an ultra-low power single-core RISC-V demonstrator with an integrated hardware accelerator. CapsuleMotion demonstrated the capability to reduce electric energy consumption by up to 20.66% in comparison with conventional capsules that lack a dynamic frame rate. Additionally, the accuracy of detecting the entry point of the small intestine has been improved. --- ### RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments Authors: Sibo Zhu, Shicheng Fan, Xinyue Wang, Wenyi Wu, Kun Zhou, Biwei Huang Published: 2026-09-14 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.15364v2 Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce \textbf{RSIAgent}, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction. RSIAgent coordinates curriculum, actor, and verifier agents to continually explore the environment, validate outcomes, and retain environment-specific knowledge, including reusable causal relationships between actions, conditions, and consequences. It further adopts a \textbf{broad-then-deep} exploration strategy, combining parallel broad recursive self-exploration for discovering diverse environment structures with focused deep self-exploration for uncovering hard cases, hidden constraints, boundary conditions, and previously unknown causal dependencies. The resulting memory is frozen and can be directly reused for downstream tasks without updating model parameters. Experiments on OSWorld-v2 and Agent's Last Exam show that RSIAgent substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6. --- ### Robust and Efficient Communication for Multi-Agent Learning Authors: Rafael Pina, Varuna De Silva, Corentin Artaud Published: 2026-09-14 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.15361v1 Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messages are both informative and robust to physical constraints remains a significant challenge. This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information. MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states, thereby inducing the learning of highly representative communication protocols. Crucially, we evaluate MARC under stringent communication bottlenecks and lossy channels, simulating the real-world constraints of autonomous robotic networks and decentralized systems. Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains. Furthermore, we provide a deep analysis of message characteristics, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments. --- ### MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving Authors: Tiancheng Zhang, Yulin Chen, Yunfeng Zhao, Shaoyuan Huang, Cheng Zhang, Xiaofei Wang Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15359v1 The surge of large language model (LLM) applications on personal devices imposes massive, bursty workloads on cloud serving infrastructure. While prefill-decode disaggregation improves throughput and scalability, memory-bound decode instances often suffer from persistent load imbalance, as output lengths are unknown when requests arrive at the cloud. To address this, we propose MAPS, a Memory-Aware Predictive Scheduling framework tailored for disaggregated LLM serving. MAPS performs device-assisted speculative output length prediction overlapped with cloud-side prefilling, incurring negligible latency overhead. To handle generation uncertainty, MAPS applies uncertainty-aware calibration to derive output-length upper bounds with target coverage, enabling safe scheduling decisions. Building on these bounds, MAPS employs a hierarchical global-local scheduling strategy to mitigate inter-decoder queue buildup and intra-decoder head-of-line blocking. Extensive experiments on two real-world workloads and two LLMs show that MAPS significantly outperforms three state-of-the-art systems, reducing average end-to-end latency by 42.6 and tail latency by up to 84.8. --- ### Diffusion Trajectory Modeling for Semantic Correspondence Authors: Yusung Choi Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15357v1 Diffusion models generate images through an iterative diffusion process, and recent studies have demonstrated that the intermediate feature maps produced during this process contain rich visual representations, leading to their adoption across a variety of downstream tasks. However, most existing approaches are limited to either using a single feature map at a specific timestep or aggregating feature maps across multiple timesteps. We observe that intermediate representations in the diffusion process form meaningful trajectories along the time axis. In particular, the representation of each spatial patch evolves progressively throughout the generative process, encoding semantics that are difficult to capture from static snapshots alone. This observation motivates the need to treat diffusion representations as temporally structured trajectories rather than static snapshots. To this end, we propose Diffusion Trajectory Modeling (DTM), a framework that interprets the temporal evolution of each spatial patch as a trajectory and leverages it for semantic correspondence. By effectively modeling patch-wise trajectories generated across multiple timesteps, DTM captures correspondence cues that prior methods are not designed to capture. We further demonstrate empirically that spatially corresponding patches form similar trajectory patterns throughout the diffusion process, suggesting that the temporal axis of diffusion carries semantic information. Experiments on SPair-71k, SPair-U and AP-10K show that DTM achieves strong performance, presenting a new perspective for exploiting diffusion representations from a trajectory-centric viewpoint. --- ### Approximating Smooth Functionals with ReLU Networks Authors: Shuhao Jiao Published: 2026-09-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.15355v2 We study the uniform approximation of smooth scalar-valued functionals on an infinite-dimensional separable Hilbert space by ReLU neural networks. A key feature in deep learning for functional data is the varying importance of different coordinates/dimensions. Representing the functional input in a basis expansion, we quantify the importance of each coordinate through both the magnitude of its corresponding basis score and the directional sensitivity of the target functional. Our analysis combines coordinate truncation, anisotropic partitioning, local Taylor approximation, and ReLU network realization, while allowing unrestricted interactions among the retained coordinates. We establish a general nonasymptotic upper bound for the uniform approximation error and a complementary pseudo-dimension-based lower bound for the worst-case approximation error. Under generalized exponential coordinate decay $w_ds_d\asymp\exp(-cd^ρ)$, with $ρ>0$, the upper and lower bounds match at the leading order, which is stretched-exponential in the logarithm of the network size budget, and thus yield the nearly optimal approximation rate. This is the first work to characterize neural network approximation error for infinite-dimensional functional inputs explicitly through the joint dimensional decay of coordinate magnitudes and directional sensitivities. --- ### End-to-End Cell Detection via Instance-aware Graph Modeling Authors: Ruochen Liu, Yalin Zheng, Jingxin Liu, Jianfeng Zhang, Shoujun Huang, Dexing Kong, Haofeng Li, Wei Lou Published: 2026-09-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.15354v1 Accurate cell detection and classification are crucial for pathological analysis, directly affecting diagnostic accuracy and treatment planning. To capture complex cellular interactions beyond visual appearance within the tumor microenvironment, several approaches have employed graph neural networks to model spatial and relational patterns among cell nuclei, yielding promising results. However, these methods typically adopt a two-stage paradigm of visual extraction followed by relational modeling, which necessitates separate tuning for each stage, thereby increasing pipeline complexity and hindering end-to-end joint optimization. In this paper, we propose an end-to-end framework for cell detection and classification that jointly models patch-level visual representations and instance-level interactions, which incorporates a dynamic graph construction module and an instance-aware graph network. Specifically, the graph construction module dynamically builds the graph structure using learnable queries derived from patch-level features as cell instance representations, with adjacency defined by integrating feature similarity and spatial distances. The instance-aware graph network performs adaptive instance filtering and feature reorganization, aggregating them over the cell graph into a topological latent state for a selective state-space transition driven by visual cues, fusing appearance and relational evidence. When evaluated on multiple datasets with different staining protocols for cell and nucleus detection, our method significantly outperforms existing approaches in both detection and classification performance. The code will be released at https://github.com/RuochenLiu23/IGM. ---