# Research Papers — 2026-09 · bundle page 175 of 266 > Full-text markdown of papers #8701–8750 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/175 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/174.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/176.md) ### When is global evolutionary search useful for variational quantum algorithms? A landscape-first study Authors: Vojtěch Novák, Ivan Zelinka Published: 2026-09-13 Categories: quant-ph, cs.NE arXiv: https://arxiv.org/abs/2609.14594v1 Variational quantum algorithms recast state preparation as classical nonconvex optimization, but it is often unclear when multistart local search suffices and when population-based global search justifies its evaluation cost. Using a landscape-first design, controlled QAOA experiments identify two mechanisms making local search unreliable: parameter reuse across circuit layers and competition between 2-local and 3-local cost terms. Increasing QAOA depth alone does not replicate this effect. We test these mechanisms across eight unseen spin glasses, fresh $N=10$ and $N=12$ instances, and standard MaxCut, transverse-field Ising, and Heisenberg models. On all eight unseen spin glasses, adaptive differential evolution (DE) achieves lower median error than both multistart BFGS and multistart Powell on the two difficult constructions, whereas the independent-depth control does not. The parameter-reuse effect transfers to MaxCut at both sizes, while standard VQE models remain favorable to local search. A pre-benchmark landscape score combining random-start local outcomes and 1D parameter slices is fixed from confirmation data before evaluating new optimizers. It predicts whether adaptive DE outperforms multistart BFGS by over one spectral-range percentage point on 50 new quantum objectives with 80--86% condition-level accuracy. The clearest indicator of global-search utility is that local search frequently traps in inferior basins, rather than circuit depth or curvature anisotropy. The findings motivate whether quantum circuit complexity can be traded for harder classical optimization when robust global search is available. --- ### SENTINEL: A Multi-Pathway Architecture for Detecting Living-Off-the-Land APT Attacks on Windows Command Lines Authors: Ahad Bin Islam Shoeb, Kamrul Hasan, Jamal Uddin Tanvin, Liang Hong, Imtiaz Ahmed, Md Arif Billah, Al Amin Published: 2026-09-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.14593v1 Living-Off-the-Land (LOTL) is the dominant evasion technique of Advanced Persistent Threat (APT) actors, exploiting legitimate Windows utilities to conduct malicious operations without deploying custom malware and enabling state-sponsored campaigns to maintain persistent access within military and critical defense infrastructure for extended periods. Existing detection methods fail against obfuscated commands and multi-stage attack sequences, as demonstrated by the Volt Typhoon APT campaign, which maintained undetected access to U.S. critical infrastructure for over 18 months using exclusively signed Windows utilities. We present SENTINEL, a multi-pathway architecture integrating BERT-based semantic encoding, character-level CNN for obfuscation invariance, inter-command attention for multi-stage pattern recognition, and autoencoder-based anomaly scoring. Evaluated on a balanced Volt Typhoon benchmark derived from Microsoft and CISA threat intelligence advisories, SENTINEL achieves 92.0% accuracy on documented state-sponsored attack commands and 91.2% on obfuscated variants, compared to 74.0% and 72.0% for standalone BERT. Per-class analysis reveals that models achieving over 98% overall validation accuracy on imbalanced data exhibit only 44-58% malicious recall on balanced adversarial sets. Character-level processing contributes 5.6 percentage points of obfuscation invariance, and the 8.0 percentage point gap over augmentation-only baselines confirms structural architectural value beyond data-driven robustness alone. --- ### AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical Socio-Technical Systems Authors: Murat Kantarcioglu Published: 2026-09-13 Categories: cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2609.14592v1 Artificial intelligence systems are rapidly becoming critical components in healthcare, finance, public services, and other safety-critical domains. Yet the engineering practices used to evaluate these systems remain predominantly model-centric, emphasizing properties such as accuracy, robustness, fairness, and interpretability before deployment. These properties are necessary but insufficient once an AI system operates within an ever changing socio-technical environment characterized by distribution shifts, institutional constraints, human feedback loops, privacy requirements, and interactions among multiple AI agents. This vision paper introduces AI Deployment Accountability Engineering (ADAE), a proposed AI engineering subdiscipline concerned with establishing measurable, continuous, and actionable accountability for deployed AI systems. ADAE treats accountability as a deployment-layer property rather than solely as a property of an individual model. It seeks to determine whether an AI-enabled system continues to operate within acceptable risk limits, identify the contexts in which failures emerge, attribute failures across interacting technical and human components, translate technical failures into downstream consequences, and support timely intervention. We articulate a research agenda built around four interconnected pillars: structured discovery of context-dependent failure modes, privacy-preserving accountability measurement, system-level risk analysis for agentic AI, and translation of technical failures into operational, and institutional risks. The broader goal is to establish foundational principles, mathematical tools, and system architectures for accountable AI deployment across safety-critical applications. --- ### Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design Authors: Amin Meghrazi, Srinivasan Parthasarathy, Andrew Perrault Published: 2026-09-13 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2609.14591v2 Participation in federated learning (FL) comes at a cost. Clients trade off privacy, communication, and compute costs for potentially greater gains in model efficacy. This paper explores this tradeoff under the aegis of individual rationality (IR) versus autarky, the basic game-theoretic requirement that the federation provide utility no worse than local training. Using the above as the design target, we examine pathwise performance of FL, as a per-round bound on cumulative surplus rather than only an asymptotic equilibrium guarantee under different degrees of client data heterogeneity. Along the learning path, clients can remain below their local-training baseline for hundreds of rounds. The natural remedy is to cap each client's per-round contribution so that this shortfall stays bounded. We prove that such a cap drives all contributions to zero, with high probability, when its tolerance is small relative to the warm-up deficit, and we observe learning collapse under it even at low heterogeneity. We then propose a design that combines a short-term participation guarantee, enforced after an announced grace window, with personalized model evaluation, while preserving the incentive properties of the underlying mechanism. We provide a theoretical basis for this approach and empirically demonstrate that, after the grace window, clients meet IR on nearly all rounds without harming overall performance under low to moderate heterogeneity; under severe heterogeneity, the design shows promising outcomes for clients compared to their local baseline at some cost in accuracy. --- ### Reverse Spatio-Temporal Disease Progression Modelling Authors: Ulugbek Shernazarov, Moucheng Xu, Inomjon Ramatov Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14590v1 Deep learning-based spatio-temporal disease progression models commonly overlook the incubation period of progressive diseases, limiting the use of those models in early interventions, which are vital for not easily reversible diseases such as Alzheimer's. This is because, the existing deep learning based longitudinal disease-progression models are almost always run forward: from an observed baseline they predict future decline. In many clinical settings, however, imaging begins only after pathology is suspected or already visible, the earlier, healthier patient-specific reference was never acquired. To address this, we propose to study reverse disease progression prediction: given later diseased anatomy, reconstruct the unobserved healthier anatomy that preceded it. We use a two-stage model in which a frozen 3D vector-quantised autoencoder defines a compact discrete latent space, while a Neural Ordinary Differential Equation (ODE) learns continuous-time dynamics in that space. A recurrent encoder reads late observations in reverse temporal order, initialises the latent state, and the ODE is integrated backwards across the trajectory. On a controlled Morpho-MNIST benchmark with a sinusoidal perturbation, our model successfully recovered the unseen previous states from later observations of the non-monotonic trajectory. On longitudinal brain MRIs from Alzheimer's Disease Neuroimaging Initiative, at the task to recover the previous unseen trajectory towards healthy states of the patients from observed later diseased states, our model outperforms the baselines that uses copy-nearest and mean-observed, with positive disease-reversal scores in every diagnostic stratum. We hope that our work can provide insights and tools towards discovering the incubation periods from single-shot scans, and developing early interventions of diseases based on imaging. --- ### A Building as a Repository: KIR, a Typed Intermediate Representation for Agent-Authored Building Information Models Authors: Dmitry Kuklev Published: 2026-09-13 Categories: cs.CV, cs.SE arXiv: https://arxiv.org/abs/2609.14578v1 Autonomous agents that author building information models need more than access to a host API. They need a representation of what they intended, what a compiler decided on their behalf, what was refused, what was observed after execution and what remains unknown. We present KIR, a typed intermediate representation in which a building is authored as a program held in a versioned repository and lowered to host applications as build targets. KIR is organised around seven ways in which a generator writing into a stateful, partially observable host goes silently wrong, and gives each a representation in data: ambiguous selectors become typed refusals with candidates; defaults keep their provenance; obligations that will not be checked are named before execution; vacuous witnesses are rejected statically; a lost transaction response becomes the state UNCONFIRMED with a verify-before-retry rule; the reverse path obeys a census invariant; and decisions are bound by digest to the state they were made against. On a pinned snapshot with 83 operation contracts and Revit as the only backend, offline experiments refuse 29 of 42 stress-test programs with diagnostic codes and no uncaught exception, name 38 of 377 witness obligations as unwitnessable, admit 31 of 100 combinations of execution, witness and acceptance states under seven stated invariants, and find no vacuous witness in 219 certificate runs; a 60-storey tower is 11,263 characters as KIR against 3,709,235 characters of emitted C#. Native Revit runs are reported from project records and kept separate from reproduced results. A controlled comparison with agents that write host code directly is specified but not yet executed; it is the principal open question. --- ### AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory Authors: Sushan Adhikari Published: 2026-09-13 Categories: cs.CY, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.14572v1 Teaching abstract theoretical computer science (TCS) concepts such as algorithm analysis and complexity theory is challenging because students must handle formal proofs and asymptotic reasoning that conventional resources rarely explain in an adaptive, on-demand way. We present AlgoRAG, a specialized Retrieval-Augmented Generation (RAG) system that couples a large language model (LLM) with a curated, domain-specific knowledge base to address these challenges. The knowledge base integrates authoritative textbooks, 847 lecture slides, 312 practice problems with solutions, 156 worked proof templates, and 89 complexity worksheets. AlgoRAG incorporates domain-specific optimizations including mathematical entity recognition, notation-aware retrieval, and pedagogical re-ranking. We evaluate AlgoRAG on 179 curated exam-style questions spanning asymptotic analysis, recurrence relations, dynamic programming, graph algorithms, NP-completeness, sorting, and divide-and-conquer. The system achieves a 100% success rate with a mean response time of 38.0 seconds. While BLEU-4 scores are zero -- a known limitation of n-gram matching on mathematical proofs where equivalent reasoning may use entirely different notation -- AlgoRAG attains ROUGE-1 F1 of 0.0963, ROUGE-L F1 of 0.0683, and a pedagogical quality score of 0.7620, indicating that responses are well-structured and didactically sound even when surface wording diverges from reference answers. Performance is especially strong on NP-completeness (ROUGE-1 F1 = 0.1285, pedagogical quality = 0.7643) and graph algorithms (ROUGE-1 F1 = 0.1023, pedagogical quality = 0.8086). These results support the conclusion that RAG is an effective architecture for personalized theoretical-CS instruction, providing correct, context-rich explanations even for highly abstract topics. --- ### Domain-specific Pretraining Profile and Transformer Performance: Evidence from Modeling Digital Pragmatics in Arabic-English Code-switching Authors: Fahad Al Hussen, King Saud University, Riyadh, Saudi Arabia, Mohammed Q. Shormani, Ibb University, Ibb, Yemen Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14571v1 This study highlights the role of domain-specific pretraining profile (DSPP) in Transformer performance for modeling digital pragmatics in Arabic-English code-switched discourse. It evaluates MARBERT and XLM-R(oBERTa), with BERT serving as a general-purpose baseline. The models were evaluated on their ability to classify context-sensitive pragmatic functions in code-switched social-media discourse. 11695 unique X posts were collected via Python and utilized for the study. The study employs a quantitative and qualitative NLP approach, following a supervised pipeline. Findings unveil that MARBERT consistently surpasses XLM-R with validation Macro F1 increasing from 0.39 to 0.84 and validation loss decreasing from 0.55 to 0.19. On an independent test set, it achieved 0.96 accuracy, 0.83 macro precision, 0.87 macro recall, and 0.85 Macro F1, while XLM-R achieved 0.92 test accuracy but a substantially lower Macro F1 of 0.52. This was also supported by class-level performance where MARBERT outperforms XLM-R considerably with F1 improvements ranging from +0.33 to +0.60, demonstrating a clear advantage in modeling Arabic digital pragmatics. The study concludes that Transformer performance depends more on DSPP than multilingual coverage alone, as the latter does not guarantee optimal performance on a highly specialized pragmatic classification task. --- ### Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection Authors: Ulugbek Shernazarov, Charitha Ruwansiri Weerakon Basnayake, Abdelkhaleq El Jarjini, Noel Crespi, Praboda Rajapaksha Published: 2026-09-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.14570v2 Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We study these factors independently: inference topology and source of inter-agent diversity. In a controlled $2 \times 3$ matrix, we cross parallel aggregation and sequential refinement with stochastic sampling, role prompting, and learned QLoRA specialization, under a fixed three-call budget and output protocol within each backbone. Using Qwen2.5-14B-Instruct and Llama-3.1-8B-Instruct, we evaluate all six configurations on multilingual low-resource emotion detection across nine languages. Parallel learned specialization is strongest on Qwen at 52.83 Macro-F1 and reaches 52.94 on Llama. On Qwen it also exceeds same-backbone zero-shot, few-shot, CoT, and seven-call self-consistency baselines. The preferred topology depends on diversity source: sequential refinement helps stochastic and prompted settings, while the learned Width advantage shrinks from 2.83 points on Qwen to 0.17 on Llama. Depth-wise analysis suggests that later learned specialists can overwrite correct early predictions, although the aggregate effect is backbone-dependent. Overall, how agents are differentiated produces larger performance shifts than topology, which should be evaluated jointly with specialization. --- ### Evaluation of optimisation and Bayesian inference methods for reaction rates in atmospheric chemical mechanisms Authors: Valery Ashu, Wenqing Peng, Zhi-Song Liu, Heikki Haario, Andreas Rupp, Taiwo Ashu, Petri Clusius, Lukas Pichelstorfer, Zihao Fu, Michael Boy Published: 2026-09-13 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.14569v1 Constraining reaction rate coefficients is a central challenge in the development of explicit atmospheric chemical mechanisms, particularly for autoxidation systems where many reaction pathways are only indirectly observed through high-resolution mass spectrometry. In this study, we evaluate rate-coefficient optimisation methods for a toy-case autoxidation mechanism using synthetic data with known ground truth. Two complementary approaches are compared: ODE-constrained neural-network optimisation, which provides efficient point estimates of uncertain rate coefficients, and the Markov Chain Monte Carlo (MCMC) approach, which samples the posterior distribution of rate coefficients and quantifies parameter uncertainty. The methods are tested using direct concentration observations and mass-spectral observations under different noise levels. For unperturbed and low-noise synthetic observations, both methods converged towards the known rate coefficients, with the neural-network optimiser providing faster point estimates. Under high-noise conditions (with the signal-to-noise ratio approximately S / N = 1), however, MCMC was substantially more robust in recovering the rate coefficients. The posterior analysis shows that mass-spectral aggregation broadens credible intervals even at low noise, and that high-noise mass spectra can leave many individual reaction rates weakly identifiable. Posterior predictive validation nevertheless shows how broad parameter uncertainty constrained by MCMC remains consistent with accurate reproduction of the observable mass spectrum. These results demonstrate that point-estimation and Bayesian sampling methods provide complementary information: neural-network optimisation is effective for informative data, whereas MCMC is essential for diagnosing uncertainty, non-uniqueness, and identifiability in noisy or aggregated inverse problems. --- ### Learning Multi-Agent Task Assignment and Navigation in the Factory: from Simulation to Real Robots Authors: Abdalwhab Bakheet Mohamed Abdalwhab, Giovanni Beltrame, David St-Onge Published: 2026-09-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.14567v1 Reinforcement learning (RL) has shown considerable promise for robotic decision-making, yet deploying multi-agent RL (MARL) on physical multi-robot systems in industrial environments remains challenging. This paper investigates the real-world applicability of decentralized MARL for multi-robot multi-machine tending. We propose Feature-fusion Multi-Agent Proximal Policy Optimization (FMAPPO), which fuses 2D LiDAR measurements with task-specific state information to enable safe decentralized multi-robot task assignment and navigation. A complete simulation-to-reality pipeline was developed using high-fidelity robotic simulation and ROS2 and deployed on physical mobile-manipulator platforms operating under realistic real-world conditions, with the robotic arms disabled during the experiments. We further investigate the sensitivity of the learned policy to command update frequency, an important consideration for real-world deployment. Comparative evaluation in simulation demonstrated that FMAPPO significantly outperformed state-of-the-art baselines with a large effect size, achieving improvements of 106\% and 21\% in parts delivery and 48\% and 11\% in parts collection over MAPPO and SMAPPO, respectively. FMAPPO also increased machine utilization by 31 and 10 percentage points, respectively, while reducing collisions by 18\% and 15\% and increasing the safety score by 14 and 6 percentage points compared with MAPPO and SMAPPO, respectively. Furthermore, real-world experiments demonstrated that the learned decentralized policies can coordinate multiple robots to service multiple machines while maintaining safe operation under real-world sensing and control constraints. Videos of the real-world experiment are available online https://anonymouspapers123.github.io/FMAPPO/. --- ### TATK: Triple-Aware Top-K Learning with Knowledge-Grounded Verification for LLM-based Sequential Recommendation Authors: Yuchen Guan, Jiaye Liu, Yifei Han, Zhenxi Zhang, Yixuan Weng, Bin Li Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14565v1 LLM-based sequential recommenders usually cast next-item prediction as text generation, but this interface is poorly matched to full-catalog top-K ranking. We propose TATK, a Triple-Aware framework that couples Top-K Learning (TKL) with Knowledge-Grounded Verification (KGV) for LLM-based sequential recommendation. Top-K Learning combines context-aware metadata-KG prompt grounding with position-aware top-K rewards, aligning training with ranking utility; Knowledge-Grounded Verification then applies structure-aware reranking over the top-M candidates after a single LLM forward pass, using the same metadata-derived item graph. We evaluate TATK on Musical Instruments, CDs and Vinyl, and Video Games from Amazon Reviews 2023 under a matched R2ec-style full-catalog protocol. Experiments use Gemma-2-2B-It and Qwen2.5-3B-Instruct backbones, compare against sequential, generative, KG-augmented, and reasoning-enhanced baselines, and include component, reward-shape, sequence-perturbation, reranking, relation-quality, and candidate-pool diagnostics. TATK improves over the matched R2ec reproduction on all 36 reported metrics. On NDCG@10, it improves Qwen by 8.05%, 4.26%, and 3.78% on the three datasets, and improves Gemma by 27.03%, 10.52%, and 10.23%, while keeping inference within 1.17x of Base RecPO latency. The diagnostics show that structural evidence is most useful for recoverable top-M candidates with reliable KG support, and should be gated when metadata relations are sparse or noisy. --- ### Small Object Detection in Drone Aerial Imagery with LAF-YOLOv10 Authors: Quratulain Nayeem, Fahmina Taranum, Mohammed Mudassir Uddin Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14560v1 General-purpose object detectors lose accuracy on UAV footage, where targets span only a handful of pixels and onboard compute is limited. Prior work composes independently-validated architectural techniques into one detector, assuming gains reported in isolation transfer once combined. We stress-test that assumption directly. LAF-YOLOv10 integrates four techniques into YOLOv10n: a Partial Convolution C2f (PC-C2f) backbone block, an Attention-Guided Feature Pyramid Network (AG-FPN), a P2 detection head replacing the large-object P5 head, and Wise-IoU v3 regression, asking whether their combined effect matches what each contributes alone. We train LAF-YOLOv10 three times (seeds 42, 123, 256) on VisDrone-DET2019, benchmark against unmodified YOLOv10n, and use TIDE error decomposition, per-category breakdown, per-component ablation, attention/loss comparisons, zero-shot transfer to UAVDT, and held-out/test-dev evaluation to localize where the combination succeeds or fails. Composability does not hold here. LAF-YOLOv10 reaches 24.0+/-0.4% mAP@0.5 at 2.14M parameters, 7.8 points below YOLOv10n (31.8%), a deficit that transfers to UAVDT (-10.0 points) and is confirmed by held-out and test-dev evaluation (23.5%, 22.5%). Background false positives, localization error, and duplicate detections move in the direction AG-FPN and Wise-IoU were designed to push. Ablation traces the deficit to a specific source: the P2/-P5 head swap costs 2.5 points independently plus a 2.5-point interaction penalty when layered onto a backbone weakened by PC-C2f, whose own 2.0-point loss is consistent with a partial pretrained-weight transplant (73/150 backbone tensors transfer). The failure is attributable to a specific interaction, not the four components individually. Composability must be verified directly, not assumed. Code/checkpoints: https://github.com/Mudassiruddin7/Small-Object-Detection-in-UAV-Imagery. --- ### Selecting k Paths with the Minimum Longest Path Length in the Stochastic Semi-Bandit Setting Authors: Shunsuke Aoki, Atsuyoshi Nakamura Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14557v1 When performing parallel data transmission through a network using multiple paths, it is practically important to minimize the maximum transmission time among the selected paths. This study addresses an online problem in which $k$ paths from an origin vertex to a destination vertex must be selected at each time step within a network represented as a directed graph. Here, the number of paths going through each edge in each parallel data transmission is limited to its capacity, and the time required for transmission is determined stochastically. We formulate the semi-bandit problem of selecting a set of paths to minimize the maximum traversal time among the selected paths and propose an algorithm to solve it. --- ### Neyshekar: An Open Persian Read-Speech Corpus for Automatic Speech Recognition Authors: Ahmad Amirivojdan, Farzad Nadiri, Abolfazl Alizadeh, Shaghayegh Yaraghi Published: 2026-09-13 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.14542v1 Neyshekar is presented as an open Persian read-speech corpus designed for coverage of both formal and informal language, named entities, and longer utterances. In version 6, 62,279 validated recordings totalling 99.02 hours are provided from 190 contributors, with 34,541 distinct recorded prompts. The prompt pool was assembled from human-written material, contextualised homographs, and reviewed language-model-generated text. Text entries were normalised with the shekar library, which supports both formal and informal Persian, and every submitted recording was reviewed against a common validation rubric. About 24% of released clips are classified as informal by an automatic classifier; these register labels are not human-validated. Item-level rater labels are provided for reproducible agreement estimation, opaque per-clip contributor identifiers make the speaker-disjoint partitioning auditable and support contributor-clustered uncertainty estimates, and a text-disjoint test subset is included for evaluation beyond previously seen prompts. Per-contributor recording load and reference-free signal quality are characterised for every released clip. Corpus characteristics are compared with Persian Common Voice under shared processing. Utility is assessed through two ASR architectures, three optimisation seeds, WER and CER, and independent evaluation on the public PSRB sample. Against duration-matched Common Voice training at approximately 32 hours, in-domain WER is reduced by 9.5 points for Whisper and 11.6 points for XLS-R, and by approximately eight points for both architectures on the independent PSRB sample. Transfer and mixture benefits are not consistently observed across architectures and training budgets. The corpus is released under CC0; code and data are made available through the project repository at https://github.com/amirivojdan/neyshekar. --- ### GNN4PPM: Multi-Target Predictive Process Monitoring with Relational Graph Convolutional Networks Authors: Ana Costa, Johannes Mäkelburg, Luise Pufahl Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14534v1 Predictive Process Monitoring (PPM) aims at predicting at runtime and as early as possible the future states of a process execution. Common tasks include predicting the next event, the time to completion of a trace, and outcomes. Existing approaches typically consider an event from the perspective of the executed activities along with their timestamps and case identifiers. This leads to the disadvantage that in real-life settings, there is much more information recorded in the event log that is not captured or completely ignored when performing prediction tasks. We introduce GNN4PPM, an approach that predicts all next events along with their complete data payload at once. We represent event information in a heterogeneous knowledge graph that captures the event log as an RDF semantics, and train the embeddings with a Relational Graph Convolutional Network (R-GCN). Our approach is promising in comparison to existing solutions, and experiments with state-of-the-art solutions prove the accuracy and applicability of GNN4PPM in complex settings. --- ### Proving olympiad geometry theorems on a superconducting quantum processor Authors: Ning Wang, Zheng-Zhi Sun, Zhengyi Cui, Yiren Zou, Aosai Zhang, Fanhao Shen, Jiarun Zhong, Zehang Bao, Zitian Zhu, Han Wang, Jia-Nan Yang, Jiayuan Shen et al. Published: 2026-09-13 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2609.14533v1 Automated theorem proving seeks to use computational systems to prove or disprove mathematical and logical statements (1, 2). It underpins a wide range of applications, and enhancing theorem-proving capabilities remains a central objective in artificial intelligence (3). Although recent neuro-symbolic systems have achieved remarkable progress (4-7), their operation is ultimately constrained by classical computational architectures. Quantum computing (8), by contrast, enables information encoding and coherent parallelism beyond classical limits (9-14), raising the possibility of accelerating structured symbolic deduction (15). Here we report the experimental realization of automated geometry theorem proving on a fully programmable superconducting quantum processor. We develop two complementary quantum proving frameworks. The first implements Wu's algebraic elimination method using quantum pseudo-division, with multivariate polynomials represented in superposition states, enabling quantum algebraic theorem proving. The second implements the full-angle method as backward symbolic reasoning through a hybrid quantum strategy-guided architecture, demonstrating a general route toward quantum symbolic proof search. As illustrative examples, we prove two theorems on a superconducting quantum processor: the perpendicularity of the diagonals of a square and a 1978 International Mathematical Olympiad geometry problem. Our results establish, at the experimental level, automated logical reasoning as a viable task for near-term quantum processors and provide a concrete pathway toward quantum-enhanced symbolic intelligence. --- ### Multi-source conformal prediction: leveraging heterogeneity via localization Authors: Rohan Hore, Anirban Chatterjee, Sayantan Choudhury Published: 2026-09-13 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.14531v1 Many modern prediction tasks involve data from multiple heterogeneous sources, while the test distribution may differ substantially from any individual source. Although heterogeneity poses challenges, it also offers an opportunity: different sources may provide complementary information, with some regions of the feature space better represented in one source than another. We propose Multi-Source Randomly Localized Conformal Prediction (MS-RLCP), which builds on the local coverage properties of randomly localized conformal prediction (RLCP) (Hore and Barber, 2025) and extends it to multiple sources through data-adaptive source selection. Under the widely adopted assumption of a shared response distribution conditional on the features across sources and the test population, we establish finite-sample coverage bounds using an interpretable notion of envelope distribution that captures their aggregate feature-space representation. Our analysis allows the test feature distribution to be absolutely continuous with respect to the envelope, extending beyond mixtures of source distributions. Under additional regularity conditions, we also establish asymptotic test-conditional coverage. Simulations and real-world experiments demonstrate the effectiveness of MS-RLCP across varying levels of data heterogeneity. --- ### Sharing standardized image-derived data in computational pathology using DICOM Authors: Daniela P. Schacherer, Christopher P. Bridge, David Clunie, Igor Octaviano, André Homeyer, Markus D. Herrmann, Olivier Gevaert, Tabita Ghete, Markus Metzler, Henning Hoefener, Tahsin Kurc, Curtis Lisle et al. Published: 2026-09-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.14530v1 Development and evaluation of computational pathology methods require access to large and diverse datasets. Over the past decade, various initiatives invested significantly into collecting, centralizing, and sharing pathology imaging data. In contrast, sharing of image-derived data such as region-of-interest delineations or segmentation masks is less well developed. In this work, we describe our approach to encoding and sharing image-derived pathology data in a standardized manner within the National Cancer Institute (NCI) Imaging Data Commons (IDC), a platform that hosts and provides public access to de-identified radiology and pathology data. The IDC relies on the Digital Imaging and Communications in Medicine (DICOM) standard for data harmonization, yet the adoption of DICOM for pathology image-derived content has remained largely unexplored until now. Here, we present five representative datasets harmonized by conversion from their original representations into DICOM and shared publicly in the IDC. We demonstrate the benefits of this harmonization, describe contributions to critical open-source tooling, and discuss technical considerations relevant to broader adoption of DICOM for pathology image-derived data. --- ### Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement Authors: Farha Nausheen, Khandakar Ahmed, Farina Riaz Published: 2026-09-13 Categories: quant-ph, cs.CL arXiv: https://arxiv.org/abs/2609.14529v1 Rigorous empirical validation of quantum machine learning on natural language tasks remains scarce. We evaluate a 10-qubit hybrid quantum-classical variational circuit (2,148 parameters) for paraphrase detection across three benchmarks: MRPC, Quora Question Pairs (QQP), and adversarial PAWS. On QQP (n = 10 seeds), the circuit achieves 75.53% +/- 0.75%. accuracy, statistically outperforming parameter-matched classical baselines (DeepMLP: p = 0.015, Cohen's d = 1.20; F1: p < 0.001, d = 2.32) and surpassing DistilBERT-4bit with 31,191 fewer parameters. On MRPC the optimal 2-layer variant reaches 92% of BERT-base accuracy at 54,000 lower parameter cost. Circuit depth analysis reveals a dataset-depth scaling effect; entanglement analysis via the Meyer-Wallach measure identifies multi-qubit entanglement as the primary performance driver (r = 0.85 across four variants). Adversarial evaluation on PAWS reveals emergent robustness: 98.2% recall versus 81.6% classical (+16.6 pp, d = 1.24, p < 0.001), without adversarial training. These results constitute the first systematic parameter-matched multi-benchmark empirical validation of hybrid variational circuits for NLP. All results are from classical simulation; hardware validation is future work. --- ### Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation Authors: Eduin E. Hernandez, Luis F. Garcia, Nurassyl Askar, Sergio A. Diaz, Stefano Rini Published: 2026-09-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.14528v1 Multi-Hop Knowledge Graph Question Answering (KGQA) tasks require models to assemble relational evidence along paths in a KG to answer natural-language questions. However, existing KGQA systems typically focus on predicting the final answer without explicitly modeling or validating the intermediate reasoning steps, obscuring whether the correct answers arise from faithful multi-hop reasoning. To address this limitation, we re-frame multi-hop KGQA as a question-conditioned graph navigation problem. We refer to this formulation as THESEUS - Traceable Hop-wise Evidence SEarch in a Unified Semantics. In this setting, an agent receives a KG, a question, and a topic entity, and traverses a sequence of relations towards the answer, making the reasoning path explicit. To systematically study this formulation, we provide three key contributions. (i) We augment the existing KINSHIP and MQuAKE resources into navigation-ready KGQA datasets with annotated evidence paths and paraphrased questions. (ii) We design evaluation protocols to measure path fidelity, robustness to linguistic variation, and performance across multi-hop and multi-answer questions. (iii) We adapt established path-based KG completion agents - MINERVA, MultiHopKG, and SQUIRE - to operate on full question embeddings rather than symbolic single-relation queries, enabling their trajectories to be guided by natural-language semantics. Together, these contributions advance KGQA research toward systems where traceability is fundamental: answers are accompanied by explicit reasoning paths whose agreement with reference evidence can be systematically evaluated. --- ### Selective Tool Use for Agentic Change Visual Question Answering in Remote Sensing Authors: Yakoub Bazi, Mohamad M. Al Rahhal, Mohamed A. Mekhtiche, Mansour Zuair Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14523v1 Change visual question answering (Change VQA) requires understanding semantic changes across bi-temporal remote sensing images. Although vision language models (VLMs) have shown promising performance on this task, they remain unreliable when answering questions that require explicit transition statistics, area measurements, or spatial information. To address this limitation, we propose a selective tool use framework in which a single VLM either answers directly or invokes a deterministic change analysis tool to obtain question specific evidence. Specifically, the selected tool operates on bi-temporal semantic maps and returns a structured observation, which the same VLM uses to generate its final answer. To support this framework, we construct a tool augmented extension of CDVQA covering eight question families and three tools for transition, spatial, and temporal analysis. Tool use supervision and observations are derived automatically from the original semantic annotations, without additional manual labeling. We then adapt Qwen3.5-4B using Low Rank Adaptation (LoRA) to jointly learn direct answering, tool invocation, and evidence conditioned answering. Experiments on 7,164 test questions show that selective tool use with reference semantic maps improves overall accuracy from 73.77% to 88.79% and average family accuracy from 69.11% to 89.65%. When the semantic maps are predicted automatically, the framework achieves 77.47% overall accuracy and 75.06% average family accuracy. These results demonstrate the benefit of question-specific semantic evidence for Change VQA, while highlighting the influence of semantic prediction quality on the resulting performance. Code and tool-augmented annotations will be made publicly available at https://github.com/yakoubbazi/ToolChangeVQA. --- ### CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction Authors: Zhirui Gao, Renjiao Yi, Yunfan Ye, Ruizhen Hu, Chenyang Zhu, Wei Chen, Kai Xu Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14521v1 Recovering editable 3D parametric curves from 2D images is a fundamental challenge in computer graphics, bridging pixel-based perception and vector-based CAD modeling. Existing NeRF- and 3DGS-based methods often rely on dense calibrated views, precomputed 2D edge maps, and costly per-scene optimization, limiting their applicability to casually captured real-world inputs. We propose CGGT, a Curve-Grounded Geometry Transformer that directly grounds 3D-consistent 2D curve instances in the image space from sparse, unposed multi-view images. CGGT combines a geometry-aware transformer encoder for multi-view feature learning with a curve-aware masked-attention decoder for cross-view instance association. In a single forward pass, it predicts camera parameters, dense depth maps, and instance-level 2D curve masks, which are then lifted into 3D and refined through a fast parametric optimization stage to recover compact, editable 3D curve primitives. To support structured curve learning, we introduce Wireframe-100K, a large-scale dataset comprising 100,000 CAD models with diverse topologies, realistic multi-view renderings, and accurate parametric curve annotations. Extensive experiments show that our framework achieves substantial improvements in both reconstruction accuracy and efficiency, particularly under challenging sparse-view settings and in separating persistent 3D structural edges from view-dependent image edges caused by silhouettes, textures, and appearance variations. Despite being trained solely on synthetic data, CGGT generalizes well to real-world images, demonstrating its potential for practical CAD-style wireframe reconstruction from unconstrained visual inputs. --- ### Toward a Layer-2 Trigger for AI/ML Lifecycle Management in 6G Authors: Dharmendra Kumar Published: 2026-09-13 Categories: cs.NI, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.14517v1 3GPP has progressively expanded AI/ML lifecycle management in the radio access network, from one-sided model control to Release 20 support for two-sided CSI-feedback model pairing. Yet a basic control question remains: when monitoring detects degradation, how quickly must a corrective action take effect? To expose this dependency, we stress-test three activation and rollback strategies in a surrogate regime-shift environment using 150 independently trained PPO candidate policies, each evaluated over 20 matched noise realizations. We add 0-40 control-step delay only to corrective lifecycle commands. With no added delay, stability-gated blending reduces mean post-shift cumulative SLA deficit from 47.02 to 7.57 violation-steps relative to hard cutover; at 40 steps, the deficit rises to 44.38, only 5.6% below the hard-cutover baseline. KPI-threshold rollback loses its advantage within only a few control intervals, while blending degrades more gradually. These results do not set a physical 6G latency bound. They show why timing requirements matter for corrective actions: lifecycle performance depends on when the command takes effect. Motivated by Layer-1/Layer-2 Triggered Mobility, we examine a standards split in which Layer 3 retains lifecycle configuration while a compact Layer 2 trigger is considered only for the latency-critical subset, together with pair-consistency, local-fallback, and security/freshness requirements. --- ### OptoAgent: A Trustworthy Multi-Agent Framework for Opportunistic Vision Micro-Screening in Classroom Environments Authors: Toqeer Ali Syed, Ali Akarma, Adeel Ahmad, Hammad Muneer Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14514v1 A child with reduced distance vision often does not know that anything is wrong. Children adapt, move closer, and rarely report the difficulty, so the problem can survive years of schooling before an adult notices. School screening addresses part of this, but it runs on a schedule, depends on staffing, and is separated from the classroom moments where the difficulty appears. Smartphone and web-based acuity tests have widened access, yet every one of them still needs somebody to start a test. We present SightSentinel, an architecture that turns a wall display a child already reads from into a recurring screening site. Ordinary educational content carries short calibrated optotype probes, and eight specialized agents divide the work. Perception agents recover viewing distance, recognition accuracy, approach behavior, gaze stability, response latency, and interocular difference from each encounter. A quality agent discards observations taken under bad geometry, poor lighting, or inattention. A longitudinal agent accumulates only the surviving evidence against the child's own baseline, and an orchestrator reports a Vision Concern Score routed through a safety gate whose output range excludes diagnosis, refraction, prescription, and reassurance. The design question is whether many cheap, noisy, well-gated encounters can reach a referral decision that one scheduled test reaches late or misses. We state the formulation, the architecture, a four-stage validation protocol against clinical reference standards, and the conditions under which the approach should be rejected. --- ### Beyond Scene Description: Multi-Agent Orchestration for Non-visual Access to Virtual Worlds Authors: Toqeer Ali Syed, Ali Akarma, Adeel Ahmad, Danial Hameed Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14512v1 Virtual worlds now host classrooms, meetings, conferences, shops, and social venues, and nearly every interaction they expose assumes a user who can scan a three-dimensional scene, follow avatars, and read floating panels. Blind and visually impaired (BVI) users are left with assistive tools that each solve one task in isolation: naming an object, reading text, describing a scene, or planning a route. A live virtual room defeats that model: obstacles, speakers, gestures, chat, slides, and notifications arrive together, and a tool that narrates all of them trades a visual barrier for an auditory one. This paper presents MetaBlind, an architecture that distributes nonvisual access across eight specialized agents, spanning perception, navigation, social and object interaction, communication, safety and trust, memory, and personalization, and that places an Accessibility Orchestrator between those agents and the user. Agents publish candidate information into a shared accessibility context instead of speaking to the user directly. The orchestrator scores each candidate on safety relevance, goal relevance, urgency, confidence, user relevance, and estimated listening load, then releases only the items it judges relevant at that moment through speech, structured audio, or haptic output. We give the selection step a formal statement, specify the orchestration cycle as an algorithm, and define an evaluation protocol against a single-agent assistant. MetaBlind is reported at the design stage, with no prototype measurement or user study, and the protocol states which outcomes would support the design and which would refute it. --- ### Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference Authors: Enda Yu, Dezun Dong, Xiangke Liao Published: 2026-09-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.14507v1 Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV serves two complementary purposes---transferring to the GPU for attention computation, or computing in-place on the CPU---which demand opposing physical states. The optimal split between them varies with workload, yet existing KVCache abstractions offer only storage semantics over a monolithic object of a single physical state, and cannot express dynamic load balancing. We propose InplaceKVCache, the first KVCache abstraction whose format fixes each byte's physical residency at write time, so that the CPU--GPU load balance can be adjusted without moving data after placement. It realizes this as a four-region layout along two dimensions---device affinity and access pattern---turning load balancing into pure scheduling. Built on this abstraction, WriteScope splits CPU--GPU shares along the sequence dimension, and a portable roofline performance model determines the optimal CPU share as sequence length evolves, with online feedback tracking CPU cost drift. On three MoE models (DeepSeek-V2-Lite, Qwen3-30B-A3B, Mixtral-8$\times$7B) with a 32~GB VRAM budget, WriteScope supports end-to-end inference at the 1M-token aggregate scale. In the long-context regime ($\ge$8K), it achieves geometric-mean speedups of $1.5\times$--$2.5\times$ on A100 and $1.4\times$--$1.7\times$ on V100 over four reproduced baselines, while vLLM, SGLang, and KTransformers fail even with a doubled KV budget. A DeepSeek-V4-Flash case study validates composition with native sparse attention. --- ### Should All Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness Authors: Salma Alsinan, Maksim Makarenko, Sixiu Liu, Ali Aldawood, Ibrahim Hoteit Published: 2026-09-13 Categories: cs.LG, eess.SP, physics.geo-ph arXiv: https://arxiv.org/abs/2609.14504v1 Geophysical data collected from active field sites are often contaminated by complex and heterogeneous noise, obscuring weak seismic events, and complicating automated interpretation. Although deep learning offers promising solutions for seismic processing, its performance is highly sensitive to the nature of training noise, especially under out-of-distribution (OOD) conditions. This study investigates the influence of noise parameters, such as type, scale, and complexity on the performance, generalization and robustness of neural networks in two geophysical tasks: first break picking and denoising. We simulate seismic-while-drilling data and apply controlled input source noise augmentation using stochastic generators to vary the noise characteristics. Different neural networks are trained on fixed noise types and scales, then evaluated across both seen and unseen noise scenarios. We incrementally increase the complexity of the noise by introducing compound noise mixtures and assess the performance of the model under increasingly challenging OOD conditions. This yields a robustness matrix that captures the generalizability of each model relative to its training configuration. Results indicate that larger noise scales boost generalization, and that effective alignment between noise type, task complexity, and architecture is key for maximizing generalization gains. In addition, training with compound noises mitigate weaknesses associated with single-noise training, acting as an additional implicit regularizer to improving robustness. These findings highlight key factors influencing model resilience in noisy geophysical environments and offer guidance for developing deep learning models that generalize effectively across diverse and unpredictable noise conditions. --- ### When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems Authors: Seyed Morteza Emadi Published: 2026-09-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.14500v1 AI scaling studies increasingly evaluate systems that combine a pretrained model with retrieval, search, verification, tools, and interaction. Yet a higher score under a larger budget does not by itself show where additional resources are best spent. This critical integrative review asks when a reported scaling result supports a resource-allocation decision. It compares evidence across pretraining, test-time computation, retrieval, and agent evaluation, distinguishing the performance of a tested procedure from the best performance achievable under a resource limit. The synthesis shows that three mismatches recur across this evidence: success counted before an answer is chosen, information a deployed system will not have, and costs left out of the comparison. A capability surface expresses performance as a function of budgets, mechanisms, and available information. Worked analytical examples show how the evaluation metric, deployment volume, selection rule, and stopping policy can alter an allocation conclusion. A resource envelope provides a structured record of the task, development and run-time resources, information access, and procedure behind a reported score. Its application to a published comparison illustrates which conclusions the evidence supports and which deployment questions remain unresolved. The resulting framework specifies the comparisons needed to choose among feasible systems and motivates experiments on the transfer of allocation rules across tasks and operating conditions. It does not propose a universal scaling law or infer general intelligence from benchmark gains. --- ### EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition Authors: He Zhang, Siyu Yuan, Siyu Liu, Sizhen Bian, Bin Guo Published: 2026-09-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.14498v1 Sensor-based human activity recognition (HAR) is fundamental to ubiquitous and wearable computing, yet existing foundation models are largely designed for cloud-scale deployment and struggle with real-world sensing shifts, including unseen users, devices, sampling rates, and sensor placements. We present \textbf{EdgeHAR}, an edge-native compact sensor foundation model designed for wearable intelligence. Unlike conventional models that entangle activity knowledge with acquisition variations, EdgeHAR learns transferable representations by factorizing sensor signals into three latent codes: an \textbf{(i)Activity-Semantic Code} capturing reusable activity knowledge, a \textbf{(ii)Motion-Dynamics Code} modeling temporal patterns, and an \textbf{(iii)Acquisition-Context Code} representing sensor-specific variations. This disentangled design enables efficient adaptation to new users, devices, placements, and activity classes with limited target-domain data. By incorporating lightweight adaptation modules, EdgeHAR achieves foundation-model-level transferability while satisfying edge constraints in computation, memory, latency, and privacy. Experiments across heterogeneous HAR datasets demonstrate that EdgeHAR maintains competitive recognition performance under distribution shifts with substantially reduced deployment cost. EdgeHAR establishes a practical paradigm for compact, edge-first foundation models for ubiquitous sensing systems. --- ### MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images Authors: Yunkai Zhuang, Qihang Yan, Zicheng Zhang, Guangtao Zhai Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14495v1 Image colorization is an inherently ill-posed task, since a single grayscale image may correspond to multiple plausible colorized results. Consequently, conventional full-reference image quality assessment (IQA) metrics fail to accurately reflect human perceptual preferences for colorized images. In this paper, we present MCIQA-2K, a large-scale multi-dimensional benchmark specifically designed for no-reference quality assessment of colorized images. We construct a dataset containing 2,000 colorized images generated by five representative colorization models, together with human annotations across three perceptual dimensions: color smearing, semantic color misalignment, and global naturalness. Building upon the proposed benchmark, we further introduce MCIQA, a dedicated multi-branch NR-IQA framework for colorized images. Extensive experiments demonstrate that MCIQA significantly outperforms existing full-reference and no-reference IQA methods on the proposed benchmark, while also exhibiting competitive generalization capability on several widely-used IQA datasets. The dataset and code are publicly available at https://github.com/ARBEZ-ZEBRA/MCIQA. --- ### Retrieval-Guided Fine-Tuning as Noisy Estimation: Risk bounds and Architectural Analysis Authors: Bhargav Lad, Yifan Hao Published: 2026-09-13 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.14485v1 Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retrieval during training remain theoretically undercharacterized. We study this question by modeling RAG-FT as an estimation problem in a multi-task linear regression framework, using an OLS proxy for single-layer linear self-attention to obtain finite-sample risk bounds. Under homoscedastic retrieval noise, we show that retrieval failure decays exponentially with task separation relative to noise, and derive explicit finite-sample conditions under which RAG-FT achieves lower risk than both target-only and full-corpus training. We then introduce a Distance-Proportional Noise (DPN) model, in which retrieval quality degrades with rank, and compare two estimators under the same retrieval process: the OLS proxy and the literal, uniform-weight forward pass of linear self-attention. We prove that the attention estimator's bias diverges as $Θ(n^{2q})$ even under exact retrieval, while OLS risk remains $Θ(d/n)$ for every noise exponent $q>0$. These results locate the instability not in noisy retrieval itself, but in the fixed, unweighted aggregation of the literal LSA forward pass, which reweighting by reliability empirically removes. We validate the predicted rate separation through direct simulation of the DPN model. --- ### PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance Authors: Avijit Dasgupta, Shayon Dasgupta, Zakaria Laskar, C. V. Jawahar, Karteek Alahari Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14473v1 Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical activities. For these assistants to become integral to daily life, they must do more than identify objects; they must provide precise, step-by-step instructions that align with a user's real-time progress. While Multimodal Large Language Models (MLLMs) show promise in general visual understanding, their ability to deliver grounded, sequential guidance for fine-grained manipulation tasks remains largely unverified. In this paper, we choose the jigsaw puzzle as a strategic testbed for this capability. Unlike general object recognition, puzzle solving demands high-precision spatial reasoning, the ability to distinguish between minute geometric variations, and a rigorous adherence to sequential logic. We investigate this capability through PuzzleMate, a novel framework focused on jigsaw puzzle solving captured through an egocentric viewpoint. We deploy PuzzleMate in a user-in-the-loop study to evaluate how well state-of-the-art MLLMs perceive the current puzzle state and generate actionable next-step instructions. Our analysis reveals seven key bottlenecks that limit their effectiveness. Building on these insights, we propose a benchmark that enables systematic evaluation of MLLMs' reasoning capabilities for puzzle solving. Our findings reveal a substantial performance gap in current models like GPT-5.2 and Gemini-2.5-Pro; while these MLLMs are highly capable, they struggle to navigate the intricate reasoning and sequential logic essential for jigsaw puzzle assistance. --- ### PRI-Net: A Lightweight Multimodal Framework for 3D UAV Localization Authors: Zhixuan Chen, Jialiang Lu, Zhong Ye, Yinghui He, Guanding Yu Published: 2026-09-13 Categories: cs.CV, eess.SP arXiv: https://arxiv.org/abs/2609.14469v1 Accurate 3D localization of unmanned aerial vehicles (UAVs) remains challenging for existing multimodal approaches due to sparse LiDAR geometry, modality-imbalanced fusion, and redundant feature transmission over constrained edge-to-server links. To address these limitations, we propose PRI-Net, an efficient and lightweight multimodal fusion framework for UAV localization that integrates point cloud splatting, residual attention fusion, and an information bottleneck. Specifically, a 3D point cloud splatting (3DPCS) strategy is introduced to transform sparse LiDAR observations into geometrically consistent dense depth maps. A residual attention fusion (RAF) module is then designed to alleviate modal bias by using an image branch for coarse estimation and a gated fusion branch for refinement. In addition, a multimodal information bottleneck (MIB) module compacts features by filtering task-irrelevant redundancy. Experiments show that PRI-Net achieves high localization accuracy with lightweight architectures, while reducing feature dimensionality and improving edge-to-server UAV sensing efficiency and robustness. --- ### Bridging the Modality Gap in Long-Form Clinical Audio: A Comparative Study of Lightweight and Heavyweight End-to-End SOAP Generation Authors: Ziyu Zhang, Mingchen Shao, Wenjie Tian, Tianlun Zuo, Longhao Li, Lei Xie Published: 2026-09-13 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2609.14467v1 Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded ASR systems perform well, end-to-end (E2E) models often struggle with information loss and hallucinations on extended audio. For the BeTraC 2026 challenge, the ASLP team presents a fully E2E multimodal system that generates structured SOAP notes directly from audio, bypassing intermediate transcripts. We constructed a 1.41-million-sample multi-task corpus and applied a multi-stage pipeline: domain pre-training, supervised fine-tuning, and reward optimization. Evaluating the architecture under both Lightweight (3B) and Heavyweight (30B) constraints reveals that each training stage progressively enhances performance. Furthermore, scaling to 30B parameters substantially boosts concept extraction and summarization quality. Ultimately, our E2E systems consistently outperform representative cascaded ASR+LLM baselines, proving the efficacy of direct multimodal optimization for clinical documentation. --- ### DynEoMT: Learning Object Dynamicity from Online Segmentation Queries Authors: Calvin Galagain, Martyna Poreba, François Goulette Published: 2026-09-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.14466v1 Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the observing camera. This dynamicity attribute cannot be inferred from semantics alone and is confounded by camera ego-motion. We introduce \method, an online framework that augments query-based video segmentation with region-level dynamicity prediction. It jointly produces the original segmentation outputs and a dynamic or static state for each predicted region. At inference, DynEoMT uses only the current frame and propagated queries, without optical flow, depth, camera pose, previous RGB frames, or feature maps. Because established video segmentation benchmarks do not annotate this attribute, we also introduce a class-agnostic offline supervision pipeline using camera-compensated optical flow and confidence-aware temporal filtering. Across VIPSeg, OVIS, YouTube-VIS 2022, and VSPW, DynEoMT achieves balanced accuracies of 84.3, 68.0, 68.6, and 87.6, respectively, while largely preserving segmentation performance. These results show that segmentation-region dynamicity can be learned from propagated queries, enabling its online prediction without a dedicated motion-processing pipeline at inference. The complete code will be released as open source to enable full reproduction of the method and experiments. --- ### AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video Authors: Jiaming Tan, Mingliang Zhai, Zhen Li, Yuwei Wu, Chuanhao Li, Kaipeng Zhang Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14462v1 Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existing approaches face a representation trade-off: perspective models operate on local views and must preserve off-screen content over long rollouts, whereas broader spatial coverage is typically obtained by synthesizing full-sphere videos or constructing explicit 3D representations. Motivated by the complementary roles of global context and selective local acuity in visual perception, we present AlayaVista, a camera-controllable streaming video world model that decouples panoramic world evolution from perspective observation synthesis. Given a single perspective image, AlayaVista constructs a 360-degree scene prior using a pretrained panorama expansion model and then evolves the scene as a camera-conditioned panoramic latent state. A latent viewport renderer maps this state to the requested perspective video latents, while a perspective refiner restores details, suppresses artifacts, and performs super-resolution. To support efficient streaming, we adapt the panoramic generator to chunk-autoregressive generation and distill both panoramic generation and perspective refinement into few-step processes. To provide the supervision required by this design, we construct MUGEN, a large-scale real-world panoramic video dataset containing 1,318 hours of videos at resolutions of at least 4K, together with rich semantic and geometric annotations. --- ### Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning Authors: Itai David, Daphna Weinshall Published: 2026-09-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.14451v1 Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the pseudo-labels that are then used to update the model. In the cold-start regime, where at most a few labels per class are available, this coupling is ill-posed, since the classifier cannot supervise itself before it has learned. To address this problem, we propose VAST (Veracity-Aware Semi-Supervised Training), which decouples these two stages. Probabilistic beliefs over the unlabeled set are first inferred directly from the geometry of a frozen self-supervised embedding and only then distilled into an inductive classifier. The construction rests on the Veracity Matrix, a kernel-based structure that aggregates label evidence across the data manifold and admits an interpretation as a Dirichlet posterior under a per-observation powered-likelihood model. Additionally, we introduce Veracity Propagation, a self-terminating belief-spreading step that extends coverage beyond the kernel neighborhood of the labeled set. Under a controlled protocol in which all methods receive identical frozen embeddings and labeled sets, VAST outperforms the strongest graph-based SSL baselines at every operating point across three datasets, with statistically significant gains in 7 of 9 comparisons, while producing a deployable inductive classifier rather than requiring transductive graph inference. Compared with end-to-end confidence-gated SSL, we further find that these methods underperform in this setting and, in our experiments, do not consistently exceed labeled-only performance. --- ### Towards Identifying the Dataset Biases Causing Phantom Transfer Authors: Jonas Jürß, Pietro Liò Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14449v1 Recent work has shown that a teacher model can transfer a bias to a student through a dataset from which every explicit reference to that bias has been filtered out, and that no data-level defense reliably removes or detects it even when knowing what bias to look for. Aiming to shed light on the hidden traces of these biases, we show that a simple signature based on Sentence BERT embeddings can identify the topic of such a bias with a Matthews correlation coefficient of 0.83 if the teacher model used by the attacker is known and 0.46 if it is not. Additionally, we observe that different teacher models appear to express the same bias through different vocabulary. --- ### NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass Authors: Ali Derogar Odolou, Reza Nazari, Mostafa Salehi Published: 2026-09-13 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.14448v1 Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to detect patterns of truthfulness and factuality. A less-studied approach is to identify feed-forward neurons correlated with hallucination. We propose a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset. We transfer the selected neuron identities to train hallucination classifiers on other factual question answering datasets. Our work provides empirical evidence that probes trained using the features from the selected neurons perform on par with probes trained on internal states. We also analyze the distribution of selected neurons and the effect of layer depth on detection performance. --- ### From Visual Attribution to Clinical Reasoning: Explainable Parkinson's Disease Screening from Hand-Drawn Patterns Authors: Aritra Dey, Utsav Kumar Nareti, Chandranath Adak, Soumi Chattopadhyay, Krishna Gopal Sasmal, Saeed Anwar Published: 2026-09-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.14441v1 Parkinson's disease (PD) manifests early neuromotor impairments that become observable in controlled hand-drawn patterns such as spirals and meanders, where tremor-induced oscillations, stroke irregularity, and curvature instability reflect underlying motor degradation. In this work, we present an explainable framework for PD screening from offline hand-drawn patterns that integrates discriminative visual modeling with clinically grounded reasoning. The predictive model captures distributed structural distortions and fine-grained texture variations. It is evaluated under subject-disjoint protocols to ensure reliable generalization. To move beyond black-box classification, we introduce a multi-stage explainability pipeline that combines visual attribution with structured symptom abstraction. Salient regions are identified using attention- and gradient-based localization, followed by extraction of clinically meaningful motor descriptors quantifying contour roughness, curvature irregularity, stroke variability, and tremor-frequency energy. These descriptors are subsequently translated into coherent clinical rationales through a language-based reasoning module, linking model evidence to established PD symptomatology. By bridging visual attribution and clinical interpretation, the proposed framework advances interpretable document intelligence for neurological screening using hand-drawn patterns. Experimental results on publicly available Parkinson's disease handwriting datasets demonstrate competitive predictive performance and clinically consistent explanations. --- ### Context-Aware Mutual Learning for Blind Image Inpainting and Beyond Authors: Haoru Zhao, Yufeng Wang, Zhaorui Gu, Bing Zheng, Haiyong Zheng Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14439v1 Blind image inpainting, aiming to recover contaminated images in the case of unknown masks, is a challenging task. Motivated by the perspective of human vision and knowledge, blind image inpainting can be decomposed into two stages: mask estimation and image inpainting based on the estimated mask. The two-stage idea exhibits evident advantages in enhancing inpainting quality and augmenting the generalization capability of unknown real-world contamination by explicitly employing the estimated mask for image inpainting compared to one-stage scheme. This two-stage idea has also been intuitively implemented. However, existing two-stage methods excessively emphasize the unilateral relationship of mask estimation to image inpainting, and may overlook the mutual relations between them. Specifically, mask estimation can provide more contextual semantics for image inpainting to strengthen the understanding of semantics, and image inpainting can offer more contextual details (e.g., textures and edges) for mask estimation to improve the learning of details. In this work, we propose a novel Context-Aware Mutual Learning (CAML) framework for blind image inpainting that joints mask estimation and image inpainting to mutually exploit contextual information. In the CAML framework, we design the Inpainting-Guided Context-Mutual (IGCM) learner to acquire the complementary contextual details from image inpainting for assisting mask estimation, and the Estimation-Guided Context-Mutual (EGCM) learner to strengthen the understanding of contextual semantics from mask estimation for assisting image inpainting. Ablation studies validate the efficacy of our CAML. Extensive experiments show that our CAML achieves state-of-the-art performance on both blind image inpainting and additional vision tasks, i.e., snow removal, shadow removal, and watermark removal, indicating its superiority. --- ### A latent dimension of Condorcet's jury theorem for multiple AI advisers Authors: Kazutoshi Sasahara, Aoi Naito, Ryo Fujie Published: 2026-09-13 Categories: cs.CY, cs.AI, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2609.14438v2 When the same question is asked of multiple AI advisers, as in self-consistency and LLM-as-a-judge panels, Condorcet's jury theorem predicts that adding independent, competent advisers makes the majority more reliable. The theorem, however, has a latent dimension when viewed from the user's vantage: adding advisers also makes disagreement more visible. A binomial model reveals that this ``visible dissent'' becomes nearly inevitable as the number of advisers grows, and that reliability and disagreement approach certainty at rates that cross at an adviser accuracy of 4/5 (0.8); below it, visible dissent eventually becomes more likely than a correct majority. Even ideal panels of independent and competent advisers can be correct in aggregate but appear divided; such disagreement does not by itself indicate aggregation failure. The way advisers split also provides a common basis for predictive multiplicity, reconciliation load, and reliance miscalibration. These results separate aggregation from disclosure and turn the latter into testable questions about how disagreement should be presented and interpreted. --- ### Lightweight Generalized DeepFake Face Detection with WAVIE: Wavelet Augmented Vision Intermediate Embeddings Authors: Arya Pulkit, Aditya Ruhela, Akarshan Kapoor, Arnav Bhavsar Published: 2026-09-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.14437v1 Deepfake detection systems often exhibit significant performance degradation when deployed on unseen manipulation methods, limiting their reliability in real-world multimedia environments. This lack of generalization poses critical challenges for misinformation mitigation, digital forensics, and human-centric AI systems. Existing detectors perform well on the forgery methods they are trained on, but their accuracy drops sharply on unseen pipelines. To bridge this generalization gap, we propose WAVIE (Wavelet Augmented Vision Intermediate Embeddings), an end-to-end architecture that combines complementary spatial and frequency cues on top of a frozen CLIP backbone. WAVIE projects intermediate transformer embeddings through a lightweight learnable module, applies a three-level Daubechies-6 (db6) discrete wavelet transform (DWT), refines the low-frequency branch while preserving the high-frequency branch, reconstructs the feature via inverse DWT, and performs classification. Trained only on FaceForensics++, WAVIE achieves AUROC = 0.852 on Celeb-DF-v1, 0.852 on Celeb-DF-v2 and 0.831 on WildDeepFake (WDF) at the frame level, outperforming several state-of-the-art generalization baselines. Extensive ablation studies confirm the importance of both the wavelet module and the intermediate-feature aggregation for cross-dataset performance, highlighting the necessity of jointly leveraging spatial and frequency domains. These results position WAVIE as a strong baseline for deepfake detection in the wild. --- ### Has Scientific Talent Shifted from Depth to Breadth?Evidence across Papers, Knowledge Inputs, Careers, and Teams Authors: Xiaoshn Nee, Haobo Zhong, Xiaomin Ni Published: 2026-09-13 Categories: cs.DL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.14425v1 Generative artificial intelligence raises a central question for scientific training and organization. Is research shifting from deep specialization toward broad individual knowledge? We examine this proposition across papers, cited knowledge, contributor histories, and teams using 47,959 articles from six fields over 2010-2025, 51,736 resolved cited works, and chronologically reconstructed prior publication histories for 1,754 randomly selected index contributors. From 2010 to 2022, team size increased by an estimated 37.3% (95% confidence interval (34.4%, 40.3%)), while paper topic breadth declined by 0.0144 on a 0-1 hierarchical distance scale. Cited knowledge was stable to modestly broader, revealing a divergence between focused outputs and the reach of knowledge inputs. Established contributors' prior breadth increased by 0.0190 (-0.0078, 0.0459) by 2019-2022, within a +/-0.05 equivalence bound assessed in sensitivity analysis. In mature citation windows, one standard deviation of focal depth was associated with 8.2% higher 1 + FWCI (1.9%, 14.9%); average breadth and interaction associations were smaller under the specified equivalence bounds. Post-2022 deviations from earlier trends were not systematic, and recent changes did not vary clearly with baseline AI intensity across 83 subfields. The findings support a differentiated structure of scientific expertise in which focused individual accumulation coexists with expanding collaboration and sustained access to diverse knowledge inputs. --- ### Certification cost of quantum models: measurement correlation, not parameter count Authors: Pavel Sulimov, Claude Lehmann Published: 2026-09-13 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2609.14424v1 Reporting the Fisher geometry of a trained variational quantum model is routine; quoting the shot budget that would establish it is not. Certifying an empirical Fisher matrix to relative Frobenius error $\varepsilon$ under coordinate-wise parameter shift costs $Θ(B p^{2} V/(\varepsilon^{2} G))$ circuit executions, where $V$ is the measured readout variance and $G$ the measured squared gradient norm, with uniform allocation optimal in that class. One constant reproduces the cost of two circuit families whose exponents differ by a full power of $p$. The exponent is an identity in how $nV$ and $nG$ scale with the register, holding family by family to $0.001$ across 624 matrix-product-state cells once the finite-$p$ prefactor is removed. The cubic cost is therefore a finite-size window, set by whether the readout light cone grows with the register. A product family to 256 qubits gives $1.966$ (95% CI $1.934$--$1.997$); a brickwork entangler falls from $2.853$ below ten qubits to $1.715$ beyond sixty-four; a blocked entangler gives $1.984$ at a fixed cone width against $3.034$ at a proportional one. Fixed device connectivity fixes the cone, so a cubic budget from a small simulation overestimates a large machine, on top of hardware multipliers $2.07\times$ ($1.41$--$3.02$), $2.38\times$ and $1.91\times$ on ibm_marrakesh, ibm_fez and ibm_kingston. Cost-optimal readout weights cut the measured shot budget by $2.67\times$ ($1.33$--$4.00$) on hardware, flat from four to twelve qubits. A discrepancy model fitted on cheap circuits transfers its mean inside the calibration grid and, at six larger sizes named before the data, does not: nominal 90% intervals cover 36%, and split conformal is the only rung that stays near nominal. --- ### Safety Signals to Verify NetOps Agents with Action-Level Granularity Authors: Tobias Labarta, Frederik Pahde, Novak Boškov, Maximilian Dreyer, David Birkenberger, Manzoor Ahmed Khan, Sebastian Lapuschkin, Wojciech Samek Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14422v2 Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. While agents have proven their value in incident summarization and telemetry signal extraction, their effectiveness as autonomous control-loop engines heavily relies on their long-horizon reliability. One such setting is the datacenter fabric, where an agent must respond to alarms and operator intents while abstaining from high-risk actions that may cause or extend downtime. Abstention, however, presupposes that an action's impact is known pre-execution, which necessitates a per-action ground truth that NetOps agent benchmarks do not provide. We construct such a ground truth for the network repair task of NetArena. A symbolic replay of the emulated network, validated against the environment at every turn, yields the exact value of every action. From the action-level value, we derive two pre-execution targets, namely whether an action reduces the repair distance (progress) and whether it increases it (harm). We show across 10 agent models, that agent verifiers leveraging internal signals predict both harm and progress more reliably than a baseline using observable signals only. Perspectively, we aim to use these signals as safety feedback to an agent harness to abstain from risky actions and protect the target system. --- ### A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification Authors: Leon Fernando, C Dombawala, P. Hettigoda, Vanodhya G. Warnasooriya, Ishara Neranjana, Rashmika Nawaratne Published: 2026-09-13 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2609.14419v1 Person re-identification (ReID) is essential for multi-camera surveillance and tracking, yet remains difficult due to viewpoint and illumination changes, occlusion, background clutter, and low resolution imagery. We propose a generative AI integrated multimodal ReID framework designed explicitly for robustness under missing cues and low latency deployment. The key idea is a cost aware early-exit cascade that prioritizes inexpensive, high confidence evidence and only triggers expensive modalities for ambiguous cases. Our system integrates (i) global visual embeddings from segmented person regions, (ii) automatically generated fine grained semantic attribute descriptions generated by vision-language models (VLMs), and (iii) optional facial embeddings when face observations are reliable. To optimize the balance between accuracy and latency, we use a cost aware early-exit cascade instead of fusing all modalities. Specifically, we first inspect the top-k retrieval results to determine whether the query is unambiguous. If the best match is clearly separated from the remaining candidates, we stop early and return the result to minimize latency; in ambiguous cases, we keep multiple hypotheses and invoke additional modalities (face/semantic) with adaptive reliability weighting to refine the decision. We report person re-identification performance using mAP and Rank-1 accuracy on the Market-1501 and DukeMTMC-reID benchmarks. The proposed adaptive early-exit cascade resolves 60.7% of DukeMTMC-reID queries and 68.4% of Market-1501 queries without invoking semantic reasoning, reducing computational overhead while maintaining competitive retrieval performance. --- ### Surrogate-Assisted Genetic Programming with Phenotypic Characterisation in Dynamic Multi-Mode Project Scheduling Authors: Yuan Tian, Yi Mei, Mengjie Zhang Published: 2026-09-13 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2609.14418v1 Dynamic multi-mode resource-constrained project scheduling requires decisions to be made under precedence constraints, limited resources, multiple execution modes, and uncertain activity durations. Genetic programming (GP) can automatically evolve heuristic rules for such problems, but its simulation-based fitness evaluation is computationally expensive. This study investigates phenotypic characterisation (PC) in surrogate-assisted GP to evolve higher-quality scheduling heuristics under a fixed budget of full simulation-based fitness evaluations. A key question is how GP individuals should be encoded into phenotypic characterisations to support effective fitness estimation. To answer this question, three PC encoding schemes with different levels of information richness are designed: priority-value encoding, which preserves raw rule outputs; rank encoding, which captures candidate ordering; and binary encoding, which represents final scheduling decisions. These encodings are combined with different distance metrics to measure behavioural similarity between GP individuals. The experimental results show that binary encoding with Euclidean distance provides the most effective and robust surrogate guidance. Further analyses show that surrogate estimation accuracy alone does not fully explain the performance differences. The PC representation also determines how effectively phenotypically redundant offspring are removed and how much behavioural diversity is retained after preselection. Ablation experiments further demonstrate that duplicate removal and surrogate preselection provide complementary benefits, with their combination producing the largest improvement. These findings highlight that effective surrogate-assisted GP depends not only on identifying promising offspring, but also on controlling redundancy and preserving useful diversity during evolutionary search. --- ### A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migration Authors: Oleg Grynets, Oleg Kaskun, Alona Seletska, Daryna Tukalo, Vasyl Lyashkevych Published: 2026-09-13 Categories: cs.LO, cs.AI, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2609.14413v1 Large language model (LLM)-based database migration is often treated as direct code transformation, although enterprise Oracle systems contain heterogeneous SQL and PL/SQL artifacts with different dependencies, execution order, complexity, and validation needs. This paper proposes a hybrid dependency-aware framework that identifies migration tasks, builds a cross-file dependency graph, condenses cyclic dependencies, and uses task specifications to generate specialized migration agents at runtime. The deterministic path combines ANTLR-based parsing with typed dependency extraction, while an LLM fallback is invoked only for units that cannot be parsed reliably. On a corpus of 116 Oracle files, the pipeline produced 1,037 units with zero coverage gaps and 1,271 AST-derived dependencies. The fallback processed 165 parse-error units, recovered 496 additional validated dependencies, eliminated unresolved-dependency units, and increased resolved internal edges from 446 to 527. The graph contained four dependency-respecting phases, while cycle handling was validated separately using Tarjan SCC condensation. A complementary experiment on 1,006 PL/SQL files regenerated 623 scripts (~62%), of which 380 (~61%) executed successfully in PostgreSQL 16. Tables achieved about 85% regeneration success, whereas no query regenerations succeeded under the evaluated specification-mediated baseline, and procedural objects remained strongly dependent on schema context. These results motivate dependency-aware context delivery, task-specific validation, and differentiated agent routing. The paper also formalizes task-to-agent mapping, introduces monitoring and diagnostics for execution feedback, and defines a controlled comparison of monolithic, static-decomposition, dependency-aware, and dynamically orchestrated migration strategies. ---