# Research Papers — 2026-08 · bundle page 49 of 240 > Full-text markdown of papers #2401–2450 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/49 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/48.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/50.md) ### Provable Non-Acceleration of Standard Strang Splittings of Kinetic Langevin Dynamics Authors: Nawaf Bou-Rabee Published: 2026-08-26 Categories: math.PR, math.NA, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2608.25279v1 The OBABO and BAOAB schemes and the other standard Strang splittings of kinetic (underdamped) Langevin dynamics are widely used Markov chain Monte Carlo algorithms. Under a suitable friction scaling, the underlying diffusion relaxes on a ballistic time scale, suggesting that these discretizations, suitably tuned, sample targets with condition number $κ$ in $O(\sqrtκ)$ iterations. We prove that no fixed choice of step size and friction, based only on the curvature bounds and the dimension, achieves this acceleration: total variation mixing time lower bounds for OBABO show that ballistic cold-start mixing fails uniformly over the smooth strongly convex class, and the lower bounds extend, with the same orders, to BAOAB and the other four Strang splittings. The proof transfers non-acceleration from optimization to sampling. Eliminating velocity gives an exact noisy heavy-ball recursion, and by the non-acceleration theorem of Goujaud, Taylor and Dieuleveut, for every tuning either some Gaussian target has a mode with relaxation time at least of order $κ$, or an attracting cycle exists on a smooth potential; dilating such a potential as $U_R(x)=R^2U(x/R)$ preserves its curvature bounds and produces metastability for a number of steps exponential in $R^2$, from an initial state at Wasserstein distance $O(R)$ from equilibrium. Using contraction estimates of Leimkuhler, Paulin and Whalley and a Wasserstein-to-total-variation regularization estimate, we prove a complementary upper bound of $O(κ)$ steps, up to logarithmic factors, for a fixed-parameter OBABO tuning. Hence, among fixed-parameter OBABO tunings, the optimal condition-number dependence of cold-start total variation mixing over this class is linear, up to logarithmic factors. A direct Gaussian calculation also rules out fixed-parameter acceleration for the left-endpoint exponential integrator. --- ### Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation Authors: Pratyay Banerjee, Ankit Chadha Published: 2026-08-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.25277v1 Multi-agent LLM systems coordinate through natural-language messages that consume 40--60\% of their token budget. Replacing these with structured graphs reduces cost but fails on tasks requiring adaptive reasoning. We propose \textbf{Routed Graph Handoff}, where a lightweight LLM router (155 tokens, 0.15\% overhead) selects between a typed dependency graph and natural language for each delegation. On four benchmarks (1,050+ trajectories), the routed system matches or exceeds NL-only on every task: \textbf{+12.7\,pp} on $τ$-retail at 3.2$\times$ compression ($p{<}0.01$), \textbf{+8.7\,pp} on BrowseComp at 2.2$\times$ compression ($p{<}0.05$), and parity on BFCL and AppWorld. Without the router, graph-only delegation regresses 14.6\,pp on AppWorld; the router eliminates this at near-zero cost. A graph-aware executor prompt is required: the same schema without interpretation guidance yields no gain. An oracle analysis reveals 8.6\,pp of additional headroom, motivating execution-time adaptive routing as future work. --- ### Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips Authors: Huakang Lin, Tiancheng Zheng, Mingxuan Sun, Tianhong Xu, Fan Zhang, Yunsi Fei, Ruyi Ding Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25276v1 Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks through a routing mechanism. However, this adaptive design introduces a new attack surface: specific experts become disproportionately correlated with certain tokens (e.g., end-of-sequence), allowing adversaries to manipulate model behavior via lightweight perturbations. In this work, we present \textbf{Groundhog Bit-Flip Attack (GBFA)}, the first bit-flip-based \textit{ Denial-of-Wallet availability attack} against MoE-based LLMs. By identifying and flipping routing-layer bits associated with related expert activations, we demonstrate that GBFA substantially extends the decoding token usage across three different LLM modes: conversational, reasoning, and agentic tasks, while largely preserving semantic fidelity. Across four main real-world MoE-based LLMs, manually deactivating on average fewer than \textbf{4 experts} drives average output inflation to $\mathbf{5912\%}$, with the majority of test samples reaching max tokens. These results reveal a robustness vulnerability of MoE architectures to bit flip, and highlight the potential of GBFA as an availability attack against LLMs. --- ### PhaseShift: Topology-Aware Data Harmonization and Model Consolidation Across Signalized Intersections Authors: Yash Ranjan, Artur Kumik, Rahul Sengupta, Anand Rangarajan, Sanjay Ranka Published: 2026-08-26 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.25275v1 Learned traffic-behavior models are commonly trained separately for each intersection, creating model portfolios that cannot share evidence across sites. We present PhaseShift, a topology-aware framework that harmonizes heterogeneous roadside trajectories into a shared actor-centric representation and trains one reusable backbone. Ego-relative coordinates, trajectory-induced movement paths, normalized signal context, and variable-cardinality interaction tokens remove site conventions while preserving behaviorally relevant topology. The backbone supports pooled operation, zero-shot at a held-out intersection, and low-data adaptation. We evaluate five intersections in two Florida regions on balanced field data, 100k training windows and equal-sized test sets per site under a replay-conditioned, best-of-sampled-trajectory protocol. At 10s, one pooled model lowers both minADE and minFDE relative to trained local models at all five sites, with median reductions of 36.8% and 22.0%. Leave-one-intersection-out deployment, including one cross-region fold, beats local training on both 10-s metrics at four of five sites, although short-horizon performance is less uniform. Fine-tuning with 1,000 target update windows improves on zero-shot at three sites and is the strongest regime at one. At site 7, every cross-site mixture sharply lowers long-horizon error under a fixed 100k-window budget; test-likelihood gains argue against a best-of-sample dispersion-only explanation. Local models fall behind calibrated IDM at the two highest-flow sites after long autoregressive rollouts; pretrained-backbone regimes do not. Within this five-site evaluation, PhaseShift demonstrates consolidation across heterogeneous physical control settings while identifying sites that still require adaptation. The protocol measures conditional single-vehicle generation under replayed context, not closed-loop traffic simulation. --- ### OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization Authors: Zimin Xia, Mubariz Zaffar, Junsheng Fu, Alexandre Alahi, Julian F. P. Kooij Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25274v1 Fine-grained Cross-View Localization (CVL) estimates the precise position and orientation of a ground-level image by aligning it with geo-referenced aerial imagery, offering a scalable alternative to Global Navigation Satellite Systems (GNSS) in challenging urban environments. Existing datasets rely on data collected with high-end sensor suites, which inherently limit image diversity and scalability. While in-the-wild images are abundant, their noisy geo-tags make them unsuitable for reliable evaluation. To bridge this gap, we introduce OpenCVL, a large-scale, diverse, and open dataset containing 617,388 ground-aerial image pairs spanning 41 cities across four European countries. All images are sourced from permissive platforms, ensuring long-term accessibility and supporting open and reproducible research. The training set combines images captured with high-end sensors with diverse in-the-wild imagery. We further develop a data curation framework that filters and corrects pose annotations to construct reliable in-the-wild evaluation data. In addition, OpenCVL includes dedicated cross-area and snowy test sets to assess generalization and robustness. Experiments with a state-of-the-art CVL model on OpenCVL show that incorporating noisy in-the-wild data consistently improves performance on clean test sets, suggesting a promising direction for scaling CVL with diverse real-world imagery. --- ### A General Framework for Metropolis-Adjusted Dikin Walks: Dimension-Square Mixing on Polytopes and Log-Det Walks on Spectrahedra Authors: Zhao Song, Lichen Zhang Published: 2026-08-26 Categories: cs.DS, stat.ML arXiv: https://arxiv.org/abs/2608.25273v1 We analyze exact-metric, Metropolis-adjusted Dikin walks by keeping the proposal determinant and reverse quadratic form together. Their leading uncentered terms cancel in the complete logarithmic acceptance ratio, leaving centered fluctuations that can be controlled with second-order tools. For a polytope given by $n$ inequalities and a convex $L$-Lipschitz potential, this yields warm-start mixing in $\widetilde O((d^{2}+dL^{2}R^{2})\log(w/δ))$ steps for the regularized Lee--Sidford walk. For a spectrahedron with $n\times n$ blocks, the log-det walk mixes in $\widetilde O((ψ^\star nd+dL^{2}R^{2})\log(w/δ))$ steps, where $ψ^\star$ measures matrix leverage. The two analyses share an acceptance-to-mixing reduction. A proposal-comparison argument transfers the polytope bound to an appropriately padded $O(1/d)$-accurate metric computed from high-precision Lewis weights. For spectrahedra, given $\widehatψ\geψ^\star$, a direct-or-two-seed TensorSRHT construction gives an exact-arithmetic implementation with $ψ^\star$ replaced by $\widehatψ$ in the mixing bound. --- ### Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach Authors: Serhii Mytsyk, Yiming Zhang, Vikram Krishnamurthy Published: 2026-08-26 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2608.25267v1 Large language models (LLMs) frequently exhibit \emph{sycophancy}: they adapt their answers to a user's stated beliefs or preferences instead of reporting what they hold to be true, which lowers factual accuracy and can amplify misinformation. This paper proposes a methodology for mitigating sycophancy that employs the Bayesian Truth Serum (BTS), a peer-prediction mechanism, as the reward in Group Relative Policy Optimization (GRPO) to fine-tune an LLM. BTS pays an answer for being \emph{surprisingly common}, that is, more frequent among respondents than those respondents themselves predicted. We treat a group of responses from a model for one question as those respondents, so the reward is a function of the model's own outputs and fine-tuning needs neither labels nor preference annotations. We prove that in the large-group limit a sycophantic response earns strictly lower expected reward than an honest one. We also prove that if the entire group agrees in advance on a symmetric answering rule, it cannot earn a higher information score than under truthful reporting. On our true/false benchmark the reference model's answer-flip rate under user pressure decreases from 23% to 4%, and its accuracy under that pressure increases from 80% to 93%. Our reward outperforms SMART and is comparable to synthetic-data fine-tuning and to pinpoint tuning, all three of which train on labels. It spends considerably more compute in exchange, which makes it suitable when labeled data is scarce. Peer Truth Serum, which also pays a premium for a rare answer but elicits no prediction report, reproduces the effect. A peer-prediction reward computed inside a single GRPO group therefore reduces sycophancy without labels, and comparing mechanisms suggests that the premium paid for a rarer answer drives the effect. --- ### Hierarchical MoE for Multi-Modal ILD Diagnosis Authors: Alec K. Peltekian, Gorkem Durak, Halil Ertugrul Aktas, Carrie Lynn Richardson, Mary Carns, Kathleen Aren, GR Scott Budinger, Anthony J. Esposito, Alexander Misharin, Alok Nidhi Choudhary, Ankit Agrawal, Ulas Bagci Published: 2026-08-26 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.25261v1 Mixture-of-experts (MoE) models combine specialized predictors under learned routing, offering a principled mechanism for leveraging heterogeneity in medical data. We present a hierarchical multimodal MoE for interstitial lung disease (ILD) classification that integrates a frozen, pre-trained imaging expert with structured electronic health records (EHR) via two-stage gating. A modality-level gate assigns patient-specific weights to imaging and EHR predictions, while a sub-gating module decomposes the EHR branch into clinically defined feature groups with learned, group-specific contributions. This design preserves stable imaging representations while enabling input-dependent clinical weighting and explicit EHR specialization. Under strict patient-level cross-validation, the model achieved the highest mean AUC among the evaluated methods (0.8750 +- 0.0443), compared with 0.8646 for imaging-only REN and 0.7685 for SwinUNETR. The framework extends interpretability across anatomical regions, imaging--EHR utilization, and clinically defined EHR feature groups. --- ### Neural-Bayesian Structure Learning for Discrete Choice Modeling Authors: Hyunsoo Yun, Eun Hak Lee, Jiaru Zhang, Ziran Wang, Eui-Jin Kim Published: 2026-08-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.25258v1 Conventional discrete choice and machine learning models are estimated primarily from observational data and typically treat explanatory covariates as parallel inputs, providing no internal mechanism for determining how related attributes should adjust when one is deliberately changed. This paper proposes Neural-Bayesian Structure Learning (Neural-BSL), a framework coupling differentiable structure learning with random-utility-based discrete choice estimation in a single differentiable procedure. To prevent mutually exclusive choice outcome from distorting the recovered attribute structure, the observed choice is maintained outside the graph as an alternative-specific utility comparison, while the attribute structure and random-utility parameters are learned jointly. The learned structure enters the choice model through structure-weighted attribute interactions and provides the structural basis for propagating interventions through downstream attributes. An intervention is evaluated by updating the intervened attribute, propagating its model-implied downstream changes in topological order, and then recomputing utilities and choice probabilities. This yields both predicted mode-share responses and the associated changes in downstream traveler or trip attributes. We evaluate Neural-BSL using stated-preference data from Seoul and the revealed-preference data from London. Neural-BSL achieves predictive performance comparable to conventional benchmarks while recovering behaviorally coherent dependency structures. Across policy scenarios, propagating interventions through the learned structure changes the predicted redistribution across modes while exposing the downstream traveler and trip adjustments underlying those responses. --- ### What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift Authors: Ayoub Louaye Bouaziz, Lokmane Chebouba, Yassine Himeur Published: 2026-08-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.25251v1 Medical vision-language models (VLMs) can appear reliable in-domain while failing when acquisition domain, paired supervision, or evaluation protocol changes. We study this failure mode as a representation-level blind spot relevant to epistemic intelligence, without claiming a formal estimator of epistemic uncertainty. Using NIH ChestXray14 and CheXpert, we first isolate source-only cross-dataset visual transfer from unsupervised domain-adaptation diagnostics. Using PadChest and OpenI, we then evaluate multimodal alignment under strict pair-index retrieval and quantify metadata-derived source-proxy information retained in frozen embeddings. Self-supervised visual initialization improves NIH-to-CheXpert transfer over supervised ImageNet initialization in matched ResNet-18 comparisons, whereas adversarial adaptation is useful only in a narrow regime and becomes unstable as adversarial pressure increases. Multimodal exact-pair retrieval remains low under external OpenI stress testing, and source-proxy information remains recoverable from learned representations. Qualitative nearest-neighbor and Grad-CAM analyses show clinically plausible cross-dataset structure and thoracic attention patterns in many cases, while device-heavy and false-positive cases remain ambiguous. Auxiliary architecture checks are task-dependent and do not support a universal backbone ranking. Overall, the study shows that apparent competence under a single protocol can conceal transfer, alignment, and shortcut-related failure modes, motivating stress-tested evaluation of medical VLMs under distribution shift. --- ### ShuttleArena: Interpretable Self-Play in Physics-Based Badminton Authors: Peize Ding Published: 2026-08-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.25246v1 Badminton is a compact but challenging domain for game AI: a player must choose a physically feasible shuttle trajectory, anticipate the opponent's interception, and recover to a court position whose value depends on the opponent's next response. The central challenge is that shot selection and recovery are not separable: the best recovery depends on the shot-induced opponent response, while the value of the shot depends on whether the hitter can cover the reply. This paper presents ShuttleArena, a physics-based singles badminton self-play environment that couples continuous shuttle flight, player interception, structured shot generation, and post-shot recovery. The policy uses role-conditioned outputs: a masked interception choice on receiver turns and a factorized hitter action over shot azimuth, shot elevation, shot speed, and recovery target, enabling interpretable tactical probes. Episodes are single rallies rather than full scored games, and training uses Proximal Policy Optimization (PPO) self-play against a staged checkpoint opponent pool with sparse terminal rally-outcome rewards and a factor-specific recovery update. Evaluation with frozen checkpoint play, controlled tactical probes, recovery ablations, qualitative rollouts, and a human-data sanity check shows competitive improvement together with interpretable opponent-conditioned changes in shot geometry and recovery behavior. The learned policies produce recognizable badminton-like structure while also reflecting the abstractions of the simulator, and the recovery intervention shows that learned recovery behavior is competitively important. These results suggest that physics-based racket sports are a useful testbed for interactive digital entertainment AI because they require agents to coordinate execution, positioning, and opponent-relative tactical value. --- ### The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion Authors: Chenglong Ma, Xinye Wanyan, Danula Hettiachchi, Ziqi Xu, Jeffrey Chan Published: 2026-08-26 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2608.25245v2 LLM-generated search queries are widely used to augment IR evaluation, yet they may contain concepts that presuppose answer-side document knowledge, violating the information-access boundary of pre-search users. Existing validation metrics, including overlap, diversity, and effectiveness, cannot distinguish rare human-tail variation from candidate answer-side intrusion. We introduce concept provenance, a framework that assigns query concepts to backstory-supported, human-central, human-tail, and candidate answer-side zones, operationalizing a boundary that retrieval metrics alone cannot detect. Applying concept provenance to 77,004 queries across 100 UQV100 topics, 8 LLMs, and 5 prompt conditions with two extraction pipelines, we obtain a cross-pipeline token-HCIR Spearman rho of 1.0 over five condition means. Candidate answer-side concepts constitute 7.40 percent of non-generic concepts and appear in 97 of 100 topics, with topic explaining approximately 67 percent of variance. Human validation yields 68.2 percent relaxed precision, revealing two mechanisms: knowledge intrusion at 45.5 percent and deployment intrusion at 45.0 percent. Diagnostic probes show disproportionate localized retrieval effects, with deletion effect size d = -0.47 compared with d = -0.34 for random deletion, but these concepts explain less than 2 percent of aggregate evaluation variance. Concept provenance therefore serves as a boundary-compliance diagnostic rather than an evaluation-shift predictor. Under the tested conditions, no prompt condition eliminates intrusion; post-generation concept-provenance selection achieves 99 percent elimination. --- ### From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection Authors: Zhibo Hou, Fan Zhao, Zhiyu An, Wan Du Published: 2026-08-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.25243v1 Continual knowledge injection is essential for keeping large language models up-to-date in a fast-evolving world. Existing methods rely on supervised fine-tuning (SFT), which memorizes injected facts in their training format but fails to generalize across paraphrasing, document combinations, and reasoning. To address this, we propose Golden-GRPO Injection (GRIN), a three-stage self-learning framework for continual knowledge injection. Golden-GRPO is a mixed-policy reinforcement learning algorithm designed specifically for knowledge injection, which injects a golden answer to provide learning signal even when on-policy rollouts fail on novel facts. We further introduce Blank and Counter, two document-level benchmarks targeting novel acquisition and counterfactual overwrite respectively, each evaluating single-fact recall, multi-source retrieval, and inferential reasoning. Our experiments establish a clear empirical claim: mixed-policy reinforcement learning enables knowledge absorption beyond what supervised fine-tuning can achieve. GRIN substantially outperforms SFT and mixed-policy RL baselines on the harder question types while matching them on basic fact recall. --- ### A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent Adoption Authors: Yegor Denisov-Blanch, Shyam Agarwal, Pavel Azaletskiy, Hao He, Rylan Schaeffer, Brando Miranda, Bogdan Vasilescu, Sanmi Koyejo Published: 2026-08-26 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.25241v2 Coding agents increase development velocity but also technical debt. Prior work reports only average effects across adopters, hiding wide differences between teams. We introduce RAMP (Repository AI Maturity Profile), a four-level cumulative maturity model grounded in version-controlled artifacts that teams commit to configure AI tools. RAMP runs from behavioral rules and coding standards through named agent definitions to multi-agent orchestration, with observed practice concentrated in the first three levels. Across 441 repositories the levels behave as a cumulative scale, and independent human annotation reproduces RAMP's repository-level labels on 97% of a held-out sample. Adoption is cumulative, forward-only, and set-and-forget: 73.8% of artifacts are committed once and never modified. Re-estimating an existing agent-adoption panel within each stratum, agents accelerate development regardless of maturity (28-38% more commits), but quality diverges: among agent-first repositories, where the contrast is identified, those without committed AI configuration show roughly twice the increase in cognitive complexity (+53% versus +27%) and 1.7x the increase in static-analysis warnings. Because maturity is observational, correlated engineering discipline or model capability may explain part of the gap; we present these findings as hypothesis-generating and release RAMP as a reusable instrument. --- ### Generalized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse Authors: Kleyton da Costa, Bernardo Modenesi, Ivan F. M. Menezes, Helio Lopes Published: 2026-08-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.29546v1 The variational graph autoencoder (VGAE) regularizes its posterior toward the prior with the Kullback-Leibler divergence, a choice inherited from the variational autoencoder rather than argued for. We introduce the generalized graph variational autoencoder (GGVA), which replaces that term with any member of the Rényi-Tsallis family of order $q$ while leaving every other part of the model untouched. Both members admit closed forms for diagonal Gaussians and both recover the KL exactly as $q \to 1$, so the VGAE is the $q=1$ arm of our own model rather than a separate baseline, and any measured difference is attributable to a single scalar. Our analysis identifies boundedness, not the order, as the operative property: for $q<1$ the Tsallis divergence is bounded above by $1/(1-q)$, independently of the latent width, whereas the KL and the Rényi divergence of the same order are unbounded. On ten graphs spanning three synthetic families, a social network, three citation networks, a connectome, a power grid and a road network, $q$ moves the retained posterior information by up to $49\times$ relative to the VGAE, while the Rényi arm at the same order stays within $1.02$-$1.30\times$ of it on all six larger real graphs (isolating the bound as the cause). The retained information is usable: probing the frozen embedding for node class, a label absent from the objective, gives GGVA up to $+0.14$ macro-F1 over the VGAE on CiteSeer, with the Rényi control again tracking the VGAE. We also report what the design was built to expose: none of this reaches held-out link-prediction accuracy on any of the six larger real graphs, and boundedness delays posterior collapse rather than preventing it. --- ### Safe Skill Retirement for Physical Agents Authors: Zhonghao Zhan, Xiao Ma, Hamed Haddadi Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.29543v1 Agent skills bundle procedural guidance with execution conditions governing authority, user consent, and live environment state. When model capabilities advance, maintainers prune instructions that appear redundant on authorized benchmark tasks. However, authorized maintenance tests can leave dormant safety conditions untested. This mismatch creates an unmeasured support gap over physical and privacy-sensitive effects. We introduce matched authority counterfactuals that hold the requested action, tool parameters, and intended effect fixed while systematically varying a single governing predicate. We formalize this evaluation via a two-gate retirement certificate requiring a candidate reduction to preserve authorized utility within a declared margin while producing zero unauthorized protected effects. In controlled experiments spanning four frontier and local model configurations across twelve skill bundles (2,592 evaluation cells), task-certified reductions remove over 94% of skill clauses and preserve authorized completion, yet produce unauthorized protected effects in every bundle. Boundary enforcement eliminates protected effects on the declared audit but fails the utility gate for one configuration. One bounded combined protocol passes both gates across all four configurations, with zero utility headroom. An end-to-end check on one read-only Home Assistant camera chain verifies proposal, decision, and effect measurements on a real device. These results demonstrate that while task benchmarks can justify retiring procedural guidance, retirement decisions require explicitly auditing the authority contracts governing physical actions. --- ### GeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning Authors: Shuaishuai Cao, Min Huang, Meng Tang, Xuan Liu, Youjin Wang, Hui Lin Published: 2026-08-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.29541v2 Referring segmentation in overhead imagery is inherently relational: a query may ask for the buildings north of the road or the pond closest to a residential area, so the correct referent can contain one object, several objects, or none. Existing benchmarks mainly score mask overlap, which cannot verify whether a model actually resolved the stated spatial relation. We introduce GeoRefer-Bench, a benchmark for verifiable geospatial referring segmentation. Each query is represented by an executable logical form over a metric scene graph, and predictions are evaluated with Exact Query Success (EQS), which is satisfied only when the returned instance set exactly matches the set denoted by the query. GeoRefer-Bench contains 700 whole 2048x2048 UAV scenes (2.94 Gpx) at 12.5 and 25 cm ground sampling distance, 26,217 instances, 142,796 spatial relations, and 20,916 executable queries spanning five reasoning levels. It further includes three paraphrases per query, 24.0% unanswerable queries, 2,477 counterfactual pairs, and five leakage-controlled evaluation splits. An independent audit re-derives object geometry, mask ownership, relation values, query execution, and split provenance, finding zero issues across all 700 scenes. Relation-blind strategies can retain non-trivial mIoU while achieving at most 22.7 EQS overall, showing that overlap alone does not certify relational grounding. Across fifteen current models, the strongest reaches 74.1 EQS but drops from 98.9 at level 1 to 60.5 at level 5, while ten models score below 5 EQS on two-hop queries. GeoRefer-Bench turns geospatial referring segmentation from mask matching into verifiable reference resolution. --- ### Clinical Knowledge Graphs for Chest X-Ray Device Reasoning Authors: Harshil Lodhiya Published: 2026-08-25 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.29536v1 Chest radiographs are routinely used to verify the position of catheters, tubes, and other support devices. Existing image models often return labels or segmentations, while report-processing systems structure text without access to image geometry. We present an uncertainty-aware clinical knowledge graph that represents device instances, tip estimates, placement assessments, provenance, report events, and temporal links as separate but connected evidence. We evaluate the implemented visual graph layer using saved predictions from the complete RANZCR CLiP test archive, comprising 30,083 studies from 3,255 patients across five non-overlapping outer folds. The graph builder materializes 914,632 B7 evidence nodes and 884,549 typed relationships. All 118,647 B7 predicted-device nodes retain tip covariance, placement probabilities, fragment provenance, and fragment counts, whereas the direct B2 baseline retains none of these fields. We further define typed data contracts, uncertainty representations, abstention rules, report-image grounding, and longitudinal query mechanisms for extending the graph to report-bearing cohorts. The reported graph-materialization analysis is post-hoc descriptive and does not establish report grounding, longitudinal performance, or clinical utility. It demonstrates a reproducible foundation for evidence-preserving AI reasoning over chest X-ray device assessments. --- ### A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot Authors: Ethan Traister, Dennis Tsang Ng, Siyu Zhang, Huaiyu Guo, Tommy Duong, Tyler Wu, Yuchen Zhou, Xingyu Shen, Jiaqi Wu, Simiao Ren Published: 2026-08-25 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.29528v1 Real conversations between fraudsters and their targets are among the most informative artifacts for studying telephone scams, yet also the scarcest: passive honeypots overwhelmingly capture automated messages and hang-ups, large-scale studies characterize call metadata rather than dialogue, and manual scam-baiting does not scale. We present a dataset of real scam-call conversations collected by an active voice-agent honeypot. Dedicated numbers are seeded into the lead-generation channels fraud operations harvest; inbound callers are answered by a low-latency conversational agent that adopts a plausible target persona and sustains the interaction while every call is recorded, transcribed, and automatically labeled. Over an initial 53-day window we captured 10,015 inbound scam and spam calls (6,601 with two or more turns): roughly 895 hours of audio and 328,869 transcribed turns from 5,665 distinct originating numbers. Under a holistic classifier the substantive calls are predominantly predatory-but-legal lead generation ("spam", about three in five), while about one in seven is an outright "scam" (949 in this snapshot). Each call carries a turn-level transcript, three-channel audio, per-turn latency telemetry, and layers of automatic labels, including a holistic scam/spam/legitimate judgment corroborated by independent human review (75% agreement on the binary decision). We describe the collection system, the record structure, and technical validation of the corpus's realism and label quality, including that the agent is recognized as non-human in only about 5% of engaged calls. We also benchmark established scam-detection methods, where detectors trained on published synthetic dialogue collapse in precision on real traffic. --- ### CoSWA-YOLOv12: Scale-Invariant Tiny Object Detection and Segmentation of Malaria Parasites Authors: Ahmed Tahiru Issah, Carine Mukamakuza Published: 2026-08-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.29527v1 Automated microscopy could widen access to malaria diagnosis in low-resource settings, but the deadliest species, P. falciparum, presents in its early ring stage as an object only a few tens of pixels wide. Such tiny targets are systematically under-detected: overlap-based label assignment starves them of positive samples, and overlap-based box regression gives weak gradients at their scale. The Normalized Gaussian Wasserstein Distance (NWD) repairs both effects, but applied uniformly across a slide that also holds objects three to four times larger it loosens their supervision and erodes their localisation, so overall accuracy can fall even as the tiny class improves. We present CoSWA-YOLOv12, a compact YOLOv12 instance-segmentation detector whose core Cooperative Scale-adaptive Wasserstein Assignment routes the Wasserstein treatment to an object in inverse proportion to its size, tapering back to standard assignment for larger species. Two further components support it: a wavelet detail residual, and a min-max Gaussian regression loss (M2-NWD). All three additions are transfer-safe: each reproduces the standard pretrained model exactly at initialisation, so public pretrained weights load without any loss of accuracy. On a five-class Rwandan thick-smear dataset, CoSWA-YOLOv12 raises P. falciparum recall from 0.63 to 0.74 and mAP@50 from 0.73 to 0.81 (mask), cuts missed P. falciparum from 38% to 15%, and improves strict-localisation mAP@50-95 on all five classes for both detection and segmentation, while a 2x2 ablation shows the scale gate and the regression loss are synergistic. --- ### Common Covariance Geometry and Certification for Brownian Kernel Ladders Authors: Mahdi Mohammadigohari Published: 2026-08-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.29525v1 A representation-adaptive kernel class produces, on a fixed sample, a union of reproducing-kernel Hilbert-space ellipsoids rather than one ellipsoid. We introduce the minimum-trace common covariance that dominates the unrestricted empirical union generated by Brownian kernel ladders and develop its statistical, approximation-theoretic, and computational consequences. The covariance value admits exact formulations through absolutely two-summing operators and covariance-dominated multipliers, and it yields a universal Gaussian-complexity bound. A closed last-layer Dirac-trace reduction and a signed Brownian threshold representation convert the generic covariance problem into threshold, graph-coarea, and effective-resistance geometry. These tools give deterministic depth laws, conditional Gaussian reverses, random-design and perturbation transfers, and an exact empirical Kolmogorov-width formula whose leading covariance eigenspaces approximate the complete adaptive ball simultaneously. Finite contact, active semidefinite programs, verified separation, and a convex resistance-design relaxation provide complementary lower and upper certificates. A finite covariance-indexed Brownian path on frozen representations illustrates the distinction between successful covariance certification and predictive selection: all reported path certificates succeed, whereas the locked predictive study misses one predeclared aggregate criterion. The paper thereby identifies one finite-dimensional covariance object linking unrestricted kernel adaptation, Gaussian geometry, common subspaces, and certifiable computation. --- ### Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races Authors: Zihao Zheng, Jiayu Long, Baichuan Li, Junyi Yao Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.29522v1 Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and its commit, external state can change, but not every change makes the commit unsafe. We separate invalidating races, which break a declared safety predicate, from predicate-preserving and irrelevant races, and ask how precisely runtime guards distinguish them. Our deterministic simulator separates visible from authoritative state and injects five non-atomic failure mechanisms across 16 infrastructure tasks in four domains; frozen agent proposals are replayed counterfactually under every controller without an LLM judge. We evaluate three commit-time guard granularities (global epoch, read-set version, semantic commit predicate), multi-level verification, and model-side gates on three locally hosted quantized model families (Qwen3-4B, Phi-4-mini, Gemma4-8B; 3,456 trajectories on one GPU). All three guards eliminate unsafe commits, but their availability differs sharply: freshness-based guards needlessly block 92-95% of benign races, forfeiting up to 43% of safe task completions, while the complete predicate guard blocks none. That precision is contract-dependent: deleting a single declared clause converts exactly its fault family into unsafe commits (up to 7.9%). Model-side signals do not substitute: verbal confidence is miscalibrated (ECE approximately 0.37), action agreement matches a random gate, a cautionary prompt leaves the direct unsafe rate essentially unchanged, and after a freshness-guard block agents re-commit unsafely from refreshed but still-incomplete reads. Under degraded telemetry a hidden concurrent mutation remains observationally clean, bounding every selective policy. Precise runtime enforcement therefore requires semantic contracts, not freshness heuristics or model self-assessment. --- ### Sample-Weighted End-to-End Trace-Norm Geometry for Multitask Learning Authors: Mahdi Mohammadigohari Published: 2026-08-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.29520v1 Multitask models combine a shared representation with task-specific outputs, but generalization bounds often control the two components separately. Such products can discard relative orientation and cancellation and can change under equivalent transformations of intermediate coordinates even when the represented predictors are unchanged. We study instead the sample-size-weighted trace norm of the end-to-end map from task coefficients to input-space predictors. For its fixed-radius class, we derive the exact empirical Rademacher complexity. The same quantity is characterized by eliminating a positive-definite task covariance after the representation acts and, in finite-dimensional intermediate spaces, by optimizing the separated product over all equivalent invertible refactorizations. Explicit constructions show unbounded orientation and factorization gaps and an exponential depth gap for cancelling linear layers. As a geometric application, finite-to-one Lipschitz shared maps yield an exact Sobolev task Gram matrix determined by multiplicity and local directional distortion. We evaluate the corresponding convex regularizer in two protocol-locked unseen suites. Across 252 paired held-out comparisons, weighted joint nuclear regularization improves average population excess over unweighted nuclear regularization by 0.00764, with a stratified-bootstrap 95% interval (0.00465, 0.01110). Correct task counts improve average and least-sampled-quartile excess over shifted counts by 0.01072 and 0.02847; all 15 imbalanced rank-suite cells are positive and the balanced effect is zero. Weighted joint nuclear also outperforms weighted Frobenius and independent ridge. The least-sampled-quartile comparison with unweighted nuclear remains unresolved, delimiting rather than contradicting the average advantage. All seven predeclared gates pass. --- ### BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling Authors: Yuxiang Cheng, Quanwei Tang, Lvhui Lu, Dong Zhang, Shoushan Li, Erik Cambria Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.29519v1 Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-powered dialogue systems offer a scalable alternative, but existing models face two fundamental challenges. First, they lack the bidirectional understanding needed to capture the layered nature of emotional expression, particularly in cases of progressive disclosure, where clients often present symptoms at the surface-level while concealing deeper trauma. Autoregressive (AR) models process information sequentially and cannot revise early interpretations when new evidence emerges later in the conversation. Second, they fail to effectively incorporate the relational knowledge that underlies clinical reasoning. In this paper, we propose \textbf{BiGraph-Diffuse}, the first large-scale diffusion language model tailored for the counseling domain. We further introduce \textbf{BiGraph-RAG}, a relation-free graph-structured retrieval strategy that relies only on lightweight entity extraction and semantic linking. This design preserves inferential pathways from observable symptoms to potential underlying causes, while incurring zero LLM token cost during indexing. Importantly, these two modules are not merely combined but mutually reinforcing. The diffusion model provides a holistic bidirectional context, enabling the system to defer premature judgments during progressive disclosure. Meanwhile, graph-based retrieval captures the structured interconnections of clinical knowledge. Extensive experiments demonstrate the effectiveness of BiGraph-Diffuse, and we further provide a solid theoretical analysis to support its design. --- ### CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning Authors: Wenjin Liu, Chenxi Wang, Jiapu Wang, Zhe Cui, Anh Tuan Luu, Haoran Luo Published: 2026-08-25 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2609.29518v1 Reinforcement learning (RL) and on-policy distillation (OPD) are two representative paradigms for improving large language model reasoning. However, when no correct trajectory is sampled, RL lacks a positive correctness signal, while OPD remains constrained by the reasoning trajectories reachable under the student's on-policy distribution. Therefore, we propose CataOPD, where the teacher acts as a catalyst rather than a target, expanding reachability while internalizing verified student-produced trajectories into a catalyst-free policy. Self-Rescue Routing uses empirically all-failed groups as routing signals rather than teacher-intervention triggers, first seeking correct trajectories through additional on-policy self-sampling. For problems unresolved after self-rescue, Catalytic-Guided Self-Resolution uses catalytic guidance to elicit a verified student-produced trajectory in the guided student distribution. Barrier-Weighted Internalization weights tokens by guided-to-unguided log-probability gaps, focusing updates on decisive tokens difficult without guidance. Experimental results show that CataOPD outperforms current baselines, extends independent student reasoning to still-unrecovered problems, and improves out-of-distribution generalization under catalyst-free inference. Our project is available at https://github.com/QwenQKing/CataOPD. --- ### AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization Authors: Wenjin Liu, Fayuan Ke, Yue Lu, Zhe Cui, Anh Tuan Luu, Haoran Luo Published: 2026-08-25 Categories: cs.CV, cs.CE arXiv: https://arxiv.org/abs/2609.29517v1 Existing methods for improving text-to-image generation quality have progressed from generator fine-tuning and prompt optimization to reinforcement learning with multi-turn visual feedback. However, existing strategies are deeply coupled with specific generators and tasks, and the learned capabilities are difficult to generalize into a universal quality optimization policy. Therefore, we propose AdaPilot, which learns a scene-adaptive, cross-generator transferable quality optimization policy by formulating multi-turn image generation as a Markov Decision Process (MDP) and optimizing it via end-to-end reinforcement learning. Specifically, AdaPilot decouples the policy from generator internals to enable cross-generator transfer, introduces scene-aware rewards that adaptively align quality assessment dimensions with task semantics, and employs process-level rewards to model the evolution trajectory of image quality. Experimental results show AdaPilot outperforms baselines in generation quality and generalization. Separate cross-generator evaluations further show that a single policy transfers zero-shot to unseen generators while maintaining positive average gains across all evaluated generators. Our project is available at https://github.com/QwenQing/Ada_pilot. --- ### Physics-Informed Neural Operator Surrogate for 2D Magnetohydrodynamic Reconnection Authors: Kushaal Kumar Pothula, Arunav Kumar Published: 2026-08-25 Categories: physics.plasm-ph, stat.ML arXiv: https://arxiv.org/abs/2609.29514v1 Direct numerical simulation of magnetic reconnection is limited by the scale separation of resistive magnetohydrodynamics. At large Lundquist numbers $S$ the current layer thins as $S^{-1/2}$, forcing fine grids and short time steps that make parameter scans prohibitively expensive. Deep learning neural operators offer an alternative by learning the map between function spaces rather than individual solutions, so that a single trained model returns the state for any parameter and time at inference cost. We have developed a Fourier Neural Operator (FNO) based Physics-Informed Neural Operator (PINO) surrogate for two-dimensional compressible, viscous, resistive reconnection in a wall bounded domain. We condition on the initial state, the Lundquist number, and a continuous query time. Predicting the magnetic flux function makes $\grad\!\cdot\!\bB=0$ exact, direct time queries remove autoregressive error accumulation, and parity-aware spectral differentiation matches the wall treatment of the reference solver. Trained across $10^{3}\le S\le2\times10^{5}$ with two values withheld, the surrogate recovers density, pressure, and guide field to better than $0.2\%$, velocity to $3.2$ to $3.9\%$, the flux function to $1.0\%$, and the spectral current density to $7.5\%$. It resolves the thin, narrow current sheet, Alfvénic jets, and spectral resolution beyond mode cutoff. Our surrogate reproduces the layer-averaged reconnection rate to within $3\%$ through $S=1.1\times10^{4}$, recovering a reconnection time exponent of $0.497$ consistent with Sweet-Parker scaling. When queried zero-shot on the $2049^{2}$ solver mesh, a full trajectory run is on the order of seconds on one GPU against several hours for the DNS, over two orders of magnitude faster, establishing learned operators as a practical route to surveying reconnection across parameter space. --- ### EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation Authors: Surangika Ranathunga, Nisansa de Silva, Aloka Fernando, Kavindu Warnakulasuriya, Isuru Wijesiri, Menan Velayuthan, Charitha Rathnayaka, Thivaharan Varatharajan, Sajeevi Silva, Piumi Kandanaarachchi, Uthayasanker Thayasivam Published: 2026-08-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.29511v1 Machine Translation (MT) for low-resource languages remains far behind that of high-resource languages, and the gap is widest in specialised domains, where parallel data is scarce or entirely absent. We present EnSiTa, a trilingual multi-domain parallel dataset and benchmark for English, Sinhala and Tamil. EnSiTa provides human post-edited training data for seven domains, plus manually translated test sets for those and one additional domain, all produced by professional translators under a multi-year, rigorously quality-controlled process. Using this dataset, we conduct an extensive study of domain-specific MT for all six language directions, fine-tuning a from-scratch Transformer, a pre-trained translation model (NLLB-600M), and decoder-only LLMs (Gemma 3 family, 1B-12B, and TranslateGemma) across training-data sizes, model scales, and in-domain, cross-domain, multilingual and multi-domain settings. To the best of our knowledge, this is the most extensive systematically documented multi-domain parallel data creation and benchmarking effort for low-resource MT. Our data and models will be publicly released. --- ### ScoutNeRV: Rapid Encoding of Grid-Based Video INRs via ScoutNet Authors: Naser Alizada, Farhang Baghban, Hashem Pishkar, Ali Mousavi Published: 2026-08-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.27958v1 Implicit neural representations (INRs) have emerged as a promising paradigm for video compression, providing compact neural representations with flexible spatial and temporal reconstruction. Hierarchical grid-based architectures such as HiNeRV achieve strong rate--distortion performance, but require extensive per-video optimization, resulting in high encoding costs. To address this limitation, we propose ScoutNeRV, a content-adaptive initialization framework for accelerating the optimization of hierarchical video INRs. ScoutNeRV employs a lightweight, offline-trained scout network that analyzes a small number of sampled frames and selects a suitable pre-trained expert from a memory bank through hard routing. The hierarchical grid and decoder parameters of the selected expert are then transferred to initialize the target HiNeRV model before video-specific fine-tuning. On the unseen ReadySetGo sequence, ScoutNeRV achieves an initial PSNR of $34.95$~dB, compared with $13.70$~dB for standard initialization, corresponding to a $21.25$~dB improvement before fine-tuning. After only 37 epochs, ScoutNeRV reaches $36.92$~dB and remains within $0.42$--$0.80$~dB of the 300-epoch HiNeRV baseline across the evaluated rate--distortion configurations. Furthermore, the proposed initialization achieves a $9.25\times$ wall-clock speedup in the reported runtime experiment. These results demonstrate that content-aware expert initialization can substantially reduce the optimization cost of hierarchical video INRs while retaining competitive reconstruction and compression performance. The code is available at https://github.com/nasserdeveloper/ScoutNeRV. --- ### VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision Authors: Zhehan Kan, Yubo Zhu, Xinghua Jiang, Zhixiang Wei, Shifeng Liu, Wei Tong, Sheng Zhong, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang et al. Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27948v1 While Vision-Language Models (VLMs) demonstrate strong capabilities, they continue to suffer from a critical limitation: insufficient fine-grained visual perception, which fundamentally limits their multimodal understanding. We attribute this bottleneck to text-dominant optimization biases during pre-training, which encourage the model to overlook fine-grained visual details, thereby limiting the capability of multimodal understanding. We investigate that overcoming this bottleneck requires two key elements: (1) a unified token space paradigm that ensures stable training dynamics, and (2) a modality-aligned dense visual supervision signal enriched with both structural granularity and semantic information to capture critical visual representations. Based on these insights, we propose VIVAS, a framework built upon the unified token space paradigm, which introduces a dense-structural-semantic vision tokenizer, which expands the textual vocabulary into a unified vision-language vocabulary by incorporating a visual vocabulary. During pretraining, VIVAS performs vision-language unified autoregressive supervision over both visual details and linguistic content, thereby enhancing visual perception to improve multimodal understanding. Trained end-to-end on 12.4T tokens, VIVAS achieves state-of-the-art performance across 7 tasks and 39 multimodal benchmarks. --- ### UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm Authors: Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang et al. Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27915v1 Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervision. Existing efforts to introduce visual supervision typically do so during post-training, when visual representations have already been largely fixed, causing such signals to act mainly as auxiliary constraints rather than as a primary force for shaping perceptual features. In this paper, we aim to fundamentally reshape the model's perceptual backbone by incorporating vision supervision directly into the pre-training stage. We observe that pixel-level image patches and textual tokens naturally coexist in a shared, raw high-dimensional space characterized by an inherent input symmetry. Leveraging this insight, we propose UVU, a novel vision-language unified autoregressive framework that eschews vector quantization. It uniquely employs continuous visual encoding for lossless representation of visual inputs and proposes a large-scale iterative hierarchical clustering algorithm to construct a pixel-level visual codebook, thereby extending the vocabulary for unified supervision and enabling autoregressive generation of pixel-level image tokens alongside textual tokens. UVU effectively synergizes pixel-level visual perception with semantic-level visual understanding, internalizing visual reconstruction capabilities and unlocking the facilitative role of visual supervision in enhancing understanding in the pre-training stage. Extensive experiments across multiple tasks demonstrate that MLLMs are capable of achieving superior multimodal understanding performance under the supervised learning paradigm of UVU. --- ### Using Composition Operators to Linearize LLM Semantic Transformations Authors: Afjal Chowdhury, James Chen, Alan Edelman Published: 2026-08-25 Categories: cs.CL, cs.LG, math.FA arXiv: https://arxiv.org/abs/2609.22143v1 Machine learning learns functions: prompt to response, image to caption. What these functions are mathematically remains hard to say. We present a method to approximate these kinds of transformations using techniques from dynamical systems that fall under the umbrella of Koopmanism. We introduce the use of composition operators, which generalize the Koopman operator and, crucially, can map between distinct spaces, motivating the perspective that LLM transformations are rectangular infinite-dimensional operators. This formalism reveals useful structure: under natural assumptions on the prompt and response distributions, the LLM operator is an isometry, and misalignment between learned representations manifests as spectral pollution of its finite sections. We then outline a method of constructing finite-dimensional approximations of an LLM operator, and demonstrate how the singular value spectrum can be used to compare tasks and models. --- ### When Does Learning Beat Heuristics? A Case Study in Kubernetes Scheduler Score Plugins Authors: Wang Xuying, Zhibek Sarypbekova Published: 2026-08-25 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.22142v1 Kubernetes scheduler plugins that score candidate nodes are, in production, hand-tuned heuristics. We ask whether a learned scoring function - trained on real placement decisions from a production cluster trace - can match or exceed these heuristics, and if not, why. We implement an external, HTTP-backed scoring plugin for a widely used scheduler simulator and evaluate two learned models (a Random Forest over engineered features, and a graph neural network encoder over per-job task-dependency graphs) trained on a large-scale production cluster trace. Under standard regression fit (R^2), both models improve modestly but monotonically across four feature-engineering iterations, reaching R^2 of about 0.042. However, on the metric that actually matters for scheduling - Top-1 ranking accuracy, whether the model scores the machine the production scheduler actually chose highest - both learned models are outperformed by a trivial single-feature heuristic (rank by free CPU: 74-84% vs. 65-66% for either model). We show this gap is best explained by objective mismatch: both models were trained with pointwise regression (MSE) rather than a ranking-specific objective, echoing a long-standing distinction in the learning-to-rank literature. This parallels prior evidence that RL-trained schedulers can outperform heuristics when the training objective is aligned with the deployment task, suggesting objective misalignment, not architecture, is the primary obstacle here. We further report an ablation of the occupancy reconstruction required to make offline trace data usable (naive features yield R^2 near 0), a controlled comparison isolating feature richness and data volume between the two model families, and a sensitivity analysis of inference latency and serving-container memory constraints. Code, data pipelines, and experiment scripts are released for reproducibility. --- ### Attention-Enhanced Dual-Branch ConvNeXt-BiLSTM Network for Subject-Independent EEG Seizure Detection Authors: Maimuna Chowdhury, Sk. Imran Hossain Published: 2026-08-25 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.22141v1 Automated seizure detection from scalp electroencephalography (EEG) is difficult because seizure morphology varies among patients and seizure samples are substantially outnumbered by non-seizure samples. This paper presents an attention-enhanced dual-branch network that jointly learns time--frequency and temporal representations from the same EEG segment. A continuous wavelet transform converts each segment into a scalogram processed by an ImageNet-pretrained ConvNeXt-Tiny backbone and squeeze-and-excitation attention. In parallel, a bidirectional long short-term memory network followed by multi-head self-attention models the raw signal. The two feature vectors are concatenated and classified by a weighted multilayer perceptron. Experiments use 14 subjects from the CHB-MIT scalp EEG database with subject-wise partitioning performed before overlapping segmentation. The model obtains $97.88\%$ accuracy and $97.51\%$ F1-score over ten across-subject splits, and $97.51\%$ accuracy, $96.59\%$ F1-score, and $98.02\%$ area under the ROC curve under 14-fold leave-one-subject-out validation. Removing temporal attention causes the largest ablation loss. The model requires 28.26 million parameters and 4.56 GFLOPs, with a measured network-only inference latency of 4.64 ms per segment. --- ### HFEMCNet: A Compact Hybrid Frequency Enriched Multi Channel Network for Automatic Modulation Classification Authors: Qamar Ijaz, Nayyer Aafaq Published: 2026-08-25 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.22139v1 Automatic modulation classification (AMC) of received radio signals is prudent for further signal processing tasks such as communication monitoring, cognitive radio operation, and interference mitigation in the electromagnetic spectrum. Traditional methods often rely on handcrafted features and struggle under complex channel conditions, whereas deep learning (DL) architectures can learn discriminative representations directly from raw signals. In this work, we propose HFEMCNet, a novel compact hybrid frequency-enriched multi-channel network that jointly exploits spatiotemporal dependencies and frequency domain information derived via Fast Fourier Transform (FFT). HFEMCNet integrates raw IQ samples with hierarchical spectral features to produce a rich signal representation, which is processed by convolutional layers for spatial feature extraction and Long Short-Term Memory (LSTM) units for temporal modeling. Experimental evaluation on benchmark datasets RML2016.10a, RML2016.10b, and over-the-air RML2018.01a demonstrates that HFEMCNet significantly outperform contemporary state-of-theart DL models in classification accuracy while achieving a reduced parameter count, smaller memory footprint, and lower tail-latency, making it suitable for real-time deployment on resource-constrained platforms. These results highlight the effectiveness of combining hybrid architectures with frequencydomain enrichment for robust and efficient AMC. --- ### Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish Authors: Tanveer Singh Published: 2026-08-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.22138v1 Hidden-state hallucination probing - training a linear classifier on an LLM's internal activations to detect whether a generated answer is faithful to the input - is an active area of 2026 research, with recent work reporting 0.90-1.00 AUROC across several benchmarks and languages. However, none of this work has tested probes on code-mixed input, despite the fact that a huge population of chatbot users write in Hindi-English code-mixed text ("Hinglish"). We address this gap directly: does a hallucination probe trained on clean-language hidden states transfer to Hinglish, or does the signal degrade under code-mixing? We construct a 5,674-item Hindi/English/Hinglish QA benchmark, generate and label 17,022 model responses across three open-weight 7-8B LLMs (Qwen2.5-7B, Mistral-7B, Llama-3.1-8B), extract per-layer hidden states at two token positions, and train linear and MLP probes for in-distribution detection and cross-lingual transfer. We find that the hallucination signal survives code-mixing well: transfer AUROC ranges from 0.88 to 0.99, with gaps of mostly under 0.05 AUROC relative to in-distribution performance, and that Hindi-trained probes transfer to Hinglish more reliably than English-trained probes. As an independent, practically motivated finding, all three models hallucinate substantially more on Hindi and Hinglish than on English for matched facts. We release our code and synthetic Hinglish QA dataset to support further work on code-mixed hallucination detection. --- ### MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents Authors: Yu Liu, Wenxiao Zhang, Cheng Hu, Cong Cao, Fangfang Yuan, Xinyu Wang, Jin B. Hong, Yanbing Liu Published: 2026-08-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.19059v1 Multimodal large language model (MLLM) agents are increasingly used as personal assistants for long-running tasks. Their utility depends on continuity: agents must retrieve and use earlier evidence across dialogue, files, and workspace state. However, agents can generate plausible answers even when access to that history has degraded, causing outcome-only evaluation to overestimate true evidence use. We present MIRAGE (Multimodal Interaction Retrieval, Attribution, and Grounding Evaluation), a controlled study of historical evidence use under conversation-state variation in multimodal personal agents. MIRAGE holds evidence objects, questions, and scoring fixed while varying only conversation state, and evaluates whether an agent can determine answerability, recover the correct source, and answer from it. Across seven frontier and open-weight multimodal backbones, we find that: 1) pre-compaction depth and post-compaction continuation form distinct, non-monotonic failure regimes rather than a single degradation curve; 2) open-weight models rely heavily on context continuity and are reluctant to spontaneously switch to tool-mediated retrieval when provenance fails; and 3) retrieval pressure improves source attribution in deep pre-compaction states for tool-compliant models, but consistently regresses after compaction, where stored evidence has already degraded. These findings show that historical evidence use should be evaluated under state variation, rather than inferred from outcome-only correctness. --- ### Rényi Tracking Bounds for Langevin Dynamics with Moving Targets Authors: Yuchen Xin, Jingxin Zhan, Zhihua Zhang Published: 2026-08-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.17577v1 We study Langevin diffusion and Langevin Monte Carlo (LMC) when the target distribution changes over time. Under a log-Sobolev inequality (LSI), we derive non-asymptotic Rényi-divergence guarantees for tracking the current target. The framework covers continuous-time Langevin diffusion and its discretizations. We then apply the results to nonsmooth sampling based on successive Moreau envelopes. For this scheme, we give explicit choices of the smoothing parameters and step sizes, together with corresponding complexity bounds. To our knowledge, these are the first non-asymptotic Rényi-divergence tracking bounds for Langevin dynamics with discrete target updates. --- ### A Station-Based Evaluation of Machine Learning-based Weather Forecasting Models in Northern Norway Authors: Siyan Chen, Lars Uebbing, Eirik Mikal Samuelsen, Georgios Leontidis, Arnt-Børre Salberg, Sébastien Lefèvre, Robert Jenssen, Kristoffer Wickstrøm Published: 2026-08-25 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2609.10564v1 Recent machine learning weather prediction (MLWP) models have demonstrated remarkable forecasting skill on global reanalysis-based benchmarks. However, their performance remains unclear in challenging environments such as Northern Norway, where narrow fjords and rapidly changing weather result in highly variable local wind conditions. In this case study, we evaluate FourCastNet3 (FCN3), GraphCast, and ECMWF High Resolution Forecast (HRES) for wind speed forecasting using multi-year station observations from Northern Norway, focusing on their relative performance, generalization beyond the training period, and performance under high-wind conditions. Our results show that HRES slightly outperforms FCN3 and GraphCast, with an overall RMSE of 2.89 $\mathrm{m\,s^{-1}}$, compared to 2.96 $\mathrm{m\,s^{-1}}$ for FCN3 and 2.94 $\mathrm{m\,s^{-1}}$ for GraphCast. Notably, the MLWP models maintain comparable performance beyond their respective training periods, with no clear evidence of noticeable degradation. FCN3 performs best under high-wind conditions, although all models substantially underestimate strong winds. Our findings suggest that MLWP has become competitive with NWP for local wind, but further refinements are still needed to capture complex terrain better. --- ### Asymptotically-informed neural networks for Black-Scholes implied volatility computation Authors: Samira Amiriyan, Youness Boutaib Published: 2026-08-25 Categories: q-fin.CP, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.05491v1 The computation of Black-Scholes implied volatility is a fundamental task in quantitative finance, underpinning option valuation, model calibration and risk management. Although implied volatility is routinely used in practice, the inversion of the Black-Scholes pricing formula remains a challenging numerical problem, particularly in asymptotic regimes corresponding to extreme option prices, strikes or maturities, where the inverse map becomes highly sensitive to perturbations of the price. In this paper, we introduce a new family of asymptotically-informed neural-network architectures for implied-volatility computation. Exploiting the distinct behaviours of the Black-Scholes pricing function in different volatility regimes, we propose a family of architectures that learn a trainable partition of the price-log-moneyness domain through a system of gating functions and combines specialised local approximations of the implied-volatility function within each region. Extensive numerical experiments demonstrate that the proposed models consistently outperform standard feed-forward neural networks across a wide range of parameter domains, often by several orders of magnitude in relative accuracy while maintaining excellent generalisation properties. Furthermore, the neural-network outputs provide highly accurate initial guesses for a third-order Householder scheme, allowing near machine-precision implied-volatility computations after only two refinement iterations. --- ### Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance Authors: Teng-Ruei Chen Published: 2026-08-25 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.00363v1 Conformance suites for quantized GEMM kernels ask whether two implementations agree within a tolerance. We measure what such a suite can detect. Injecting nine faults into a reference INT8 pipeline over 8,232 layer--fault--regime cells of Qwen3-1.7B, we find that every one of five epilogue faults -- scale precision, double rounding, multiplication order, output truncation, fused ordering -- moves the output by at most a single bfloat16 spacing, and by exactly one whenever it moves it at all, across 5,880 cells. A tolerance of one spacing is therefore blind to the entire class by construction: four of the five faults are detected by no check in the suite, and the fifth only under power-of-two scales. Faults that violate the accumulator's exactness preconditions, or that break operand sharing, are detected without exception, and a null fault never fires. What a tolerance-based suite of this shape establishes is therefore narrower than interchangeability: that the preconditions hold, that operands are shared, and that differences stay within one spacing. The power-of-two constraint that exposes the one detected fault is also deployable. Requantizing every weight scale to its nearest power of two makes CUTLASS and Triton agree bitwise at every linear layer (196/196 and 252/252, against 8/196 and 10/252 under the checkpoints' own scales) and yields byte-identical generated token sequences at 1.7B, 8B and 14B (8/8 prompts, against 0/8 at all three). Observed perplexity point estimates are +0.32%, -0.28% and +0.48%; the 90% intervals cover zero at the two smaller sizes but not at 14B, reaching +0.71% and +0.76%. A previously reported +157% perplexity for this intervention was an artifact of a probe that rewrote scales without requantizing the weights; separating the effects attributes 99.8% of it to the resulting weight--scale mismatch rather than to the power-of-two constraint itself. --- ### Automated pipeline for herbarium label digitization Authors: Hiba Abbad, Hanane Ariouat, Eva Perez Pimpare, Nicolas Turenne, Eric Chenin, Abderrazak Sebaa, Edi Prifti, Jean-Daniel Zucker, Youcef Sklab Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28676v1 Digitized herbarium collections, now comprising over 100 million freely accessible specimen images, have become a critical resource for addressing fundamental questions in ecology and evolutionary biology. Yet the rich metadata encoded in herbarium labels (collector identities, geographic localities, collection dates, and ecological observations) remains largely inaccessible at scale, constraining both biodiversity informatics and the construction of specimen-specific image-text corpora for multimodal AI. We present HERBIOME, a modular end-to-end pipeline for automated herbarium label digitization, integrating YOLOv8-based component detection, CRAFT Hezar word-level text localization, fine-tuned TrOCR for recognition of mixed handwritten and printed text, and GPT-4o Mini for semantic metadata structuring into standardized fields. TrOCR was trained on a multi-source dataset combining general transcription corpora (CREMMA-AN, PictoCatalogs) with herbarium-specific data (RéColNat), achieving a Character Error Rate of 4.05-4.10%. End-to-end evaluation on 450 French herbarium specimens, using a dual-metric framework of Maximum Window Similarity (MWS: 0.614-0.618) and Semantic Metadata Accuracy (SMA: 0.440-0.445), reveals that hybrid training strategies improve semantic fidelity while random sampling maximizes surface similarity, with taxonomic fields remaining the principal bottleneck. By automating the extraction of structured metadata from complex, heterogeneous labels, HERBIOME reduces transcription burden, enables the construction of paired image-text datasets that faithfully capture specimen individuality, which is a prerequisite for next-generation multimodal biodiversity AI systems. --- ### Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning Authors: Mingwen Zhang, Jisheng Dang, Minqiang Yang, Bimei Wang, Bin Hu, Tat-Seng Chua Published: 2026-08-25 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.28675v1 Video reasoning tasks such as grounded video question answering and temporal grounding require selecting temporal evidence that supports the query. In many current training setups, temporal supervision is applied through local objectives such as boundary regression or span generation, while verification is used mainly to rerank candidate segments at inference time. We study whether a frozen verifier can also guide training. Our multi-agent framework couples a trainable \emph{Grounder} with a frozen \emph{Verifier}: the Grounder samples candidate trajectories and evidence segments, the Verifier assigns query-conditioned segment scores, a group-relative policy-gradient objective favors trajectories that outperform their within-input peers, and a bootstrapped calibration loss steers temporal predictions toward verifier-preferred spans. Trained on source tasks and evaluated without target-dataset fine-tuning, a two-billion-parameter instantiation transfers zero-shot across grounded question answering, temporal grounding, and long-video question answering, reaching 28.7\% intersection-over-union and 25.4\% answer-grounding accuracy on a grounded-question-answering benchmark, 46.1\% intersection-over-union on a temporal-grounding benchmark, and 54.1\% on a long-video question-answering benchmark. Relative to a strong same-scale baseline, the gains are modest but consistent, with the clearest improvements on relevance-oriented metrics such as intersection-over-union and moderate-overlap recall. Within the tested benchmarks and transfer setting, the results support frozen verification as a training signal for evidence selection, while showing that strict boundary precision remains comparatively weaker. Code and models are available at https://anonymous.4open.science/r/MASIRL-E50C/ --- ### Multi-exposure HDR Imaging: A Review of Pixel-level and Feature-level Reconstruction Methods Authors: Qian Tao, Wei Wang, Chaobing Zheng, Zhengguo Li Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28674v1 Multi-exposure is an efficient way to capture real-world high-dynamic-range (HDR) scenes. However, HDR imaging suffers from severe ghosting artifacts in dynamic scenes due to the temporal gap between sequential exposures. In this article, we categorize the literature on two important topics on HDR imaging: multi-exposure fusion (MEF) and ghost removal. Conventional filter-based and data-driven methods are studied in pixel space and feature space. For popular deep learning-based approaches, we provide a granular taxonomy based on their alignment and fusion domains: pixel-space methods, which typically employ explicit motion compensation such as optical flow or spatial transformers, and feature-space methods, which leverage implicit alignment through deformable convolutions, attention mechanisms, or latent representation merging. Representative works are compared across different supervision settings, and key design principles are summarized. In addition, this survey summarizes commonly used datasets and evaluation metrics, discussing their applicability under diverse output forms. Finally, major bottlenecks and promising directions for future research are outlined. --- ### CareGraph: An Auditable Hybrid AI Framework for Evidence-Grounded Personalized Longitudinal Health Intelligence Authors: Pratik Ghawate, Tanvi Patil Published: 2026-08-25 Categories: cs.AI, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2608.27484v1 Artificial intelligence is transforming personalized healthcare, yet fragmented clinical, self reported, and wearable evidence remains difficult to interpret and trace. We present CareGraph, an auditable hybrid AI framework that converts heterogeneous records into prioritized trends, missing context indicators, bounded next steps, discussion questions, and provenance linked explanations. CareGraph organizes evidence without diagnosing, predicting outcomes, selecting treatment, or making autonomous clinical decisions. Its pipeline covers deterministic analysis, context detection, graph construction, constrained language model synthesis, evidence validation, safety controls, and release gating. Tests used synthetic cohorts of 400 patients each for development, validation, and holdout. On holdout data, a frozen ordinary least squares trend rule with a sufficiency gate achieved 0.827 accuracy, 0.837 macro F1 with a 95 percent confidence interval of 0.819 to 0.854, and 0.974 insufficient data F1. Missing context detection achieved 0.815 strict micro F1 versus 0.318 for the legacy detector. On an authored holdout benchmark, safety ruleset version 1.2 achieved 1.000 precision, 0.950 recall, and 0.974 F1. An audit requiring graph retrieval across 80 patients yielded 79 syntheses and 78 presentations without fallback; one output was blocked and one failed closed because of an invalid evidence key. Against monolithic GPT 5.6 on 56 matched patients, CareGraph was faster at 40.15 versus 49.62 seconds, shorter at 661 versus 1,163 words, and showed better exploratory lexical alignment with longitudinal targets; the baseline used fewer tokens and cited more raw evidence. Graph auditing verified provenance and deterministic retrieval; incremental graph effects on generation require paired evaluation. CareGraph offers a safety bounded foundation for intelligent personalized health systems. --- ### Multiscale Community-Based Fingerprinting of Signed Functional Networks Authors: Sema Athamnah, Selin Aviyente Published: 2026-08-25 Categories: q-bio.NC, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2608.27483v1 Objective: Recent studies demonstrate that functional connectomes contain subject-specific signatures, or \textit{fingerprints}, that can identify individuals across repeated sessions and tasks. Existing methods mostly rely on edge-level features that are sensitive to noise, difficult to interpret, and limited in their ability to generalize across tasks and datasets. Methods: We propose a multiscale community-based functional connectome fingerprinting framework that characterizes each individual by the mesoscale structure of their functional networks. We introduce a signed multilayer community detection framework that incorporates both correlated and anti-correlated brain activity to identify subject-specific community structures across tasks and sessions. Graph-theoretic metrics are then computed from the resulting joint community structures to derive low-dimensional community-level fingerprint representations. Results: The proposed framework is evaluated on 810 healthy control subjects from the Human Connectome Project (HCP). The results show that community-based fingerprints provide a reliable and interpretable substrate for individualized brain characterization across sessions and tasks. Conclusion: Mesoscale community structure provides meaningful and discriminative subject-specific fingerprints. Significance: The proposed framework offers a promising foundation for precision neuroimaging and personalized neuroscience applications. --- ### Context Localization for Generalized Level-Based Evaluation in Knowledge-Based Systems Authors: Ondrej Hutník, Natália Puškárová Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.27482v1 We study context localization for generalized level-based evaluation in knowledge-based systems. The framework models situations where a structured nonnegative score, defined on facts, rules, cases, criteria or evidence units, is evaluated through conditional aggregation tests on admissible knowledge contexts. The generalized level measure maximizes a monotone set function over all contexts whose aggregated support reaches a prescribed level. We characterize when filtering the score by a context $B$ is equivalent to localizing the admissible contexts by intersection with $B$. The main theorem shows that this consistency holds for all monotone set functions if and only if two structural conditions are satisfied: monotonicity with respect to contexts and a reduction property excluding positive localized support outside $B$. We analyze pointwise and block-generated mechanisms producing the reduction property, extend the result to parameterized systems, and interpret it as a stability criterion for context-dependent evidence selection, non-additive support evaluation and level-based knowledge aggregation. --- ### ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices Authors: Joy Chen, Alejandro Castillejo Munoz, Pierluca D'Oro, Yuxuan Sun, Chloe Evans, Joseph Tighe Published: 2026-08-25 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.26204v2 Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively evaluates whether they can safely interact with visual interfaces while handling ambiguous instructions. We introduce ADeptS-Bench, a dual-stream trustworthiness benchmark, grounded in the ADEPTS capability framework and general population user studies. The Safety stream provides paired benign/malicious tasks with threats embedded in the visual interface. The Disambiguation stream evaluates whether agents seek clarification when intent is ambiguous. Evaluating seven models reveals that no model consistently exceeds 80% task success while staying below 30% attack success; every model clicks "Checkout" on a $25K order without hesitation, and none detects that a "factory reset" button is mislabeled as "Optimize." An ablation reveals three distinct safety architectures: tool-dependent (ASR +21-23pp without refusal tool), partially tool-dependent (+10-11pp), and no mechanism (unchanged). In disambiguation, all models overestimate consequence severity, mirroring the over-refusal bias observed in safety. We release all data, evaluation code, and analysis tools upon publication. --- ### GameWAM: A World Action Model for Video Games Authors: Yuncheng Guo, Zhanqiu Zhang, Yiwen Guo, Weijia Li Published: 2026-08-25 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.26200v2 Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task context directly to actions but lack explicit world dynamics modeling, whereas interactive game world models predict visual futures from supplied actions but do not serve as task policies. World-Action Models (WAMs) unify these objectives, but remain largely unexplored under the dynamics and open-ended interaction of video games. We introduce GameWAM, to our knowledge the first WAM for native closed-loop gameplay and GUI control. GameWAM jointly generates future visual observations and executable keyboard-mouse trajectories through parallel visual and action generative processes with block-causal conditioning and flow matching. To support joint world-action learning, we construct synchronized gameplay and GUI trajectories. To handle heterogeneous native control, GameWAM predicts a gameplay/GUI mode per action step and generates actions with mode-specific prediction distributions and continuous-action normalization. For long-horizon interaction, block-cycle control coordinates prediction, execution, and temporal context: it predicts beyond the committed horizon, executes short action blocks, replans from new observations, and hierarchically structures context from fine-grained within-cycle history to persistent cross-cycle history. Experiments demonstrate competitive task success with fewer executed native actions than the compared agents. We further uncover Low-Frequency Action Source Imprinting (LASI), in which low-frequency components of the sampled action source systematically steer coarse generated camera motion under fixed conditioning, revealing a source-sensitivity failure mode in generative control. Project page is available at https://yunncheng.github.io/GameWAM/. --- ### Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling Authors: Leonardo Liparulo, Francesco Pierri Published: 2026-08-25 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.26199v1 We ask whether AI agents powered by locally deployed large language models can reliably automate expert-defined hardware design workflows in an industry-realistic tool-calling setting. In these environments, engineers issue repetitive, dependency-ordered operations---such as creating components, adding ports, and wiring connections---through specialised tools. Confidentiality constraints on component specifications and naming conventions often preclude hosted proprietary APIs, motivating the use of locally deployed models. To study this setting, we build a Model Context Protocol (MCP) server that reproduces the state and dependency logic of a proprietary hardware design tool used in embedded system development and construct a benchmark covering single-operation edits, multi-step dependency chains, invalid requests, misspelled prompts, and multi-server tool contexts. We evaluate seven open-source models comparing pipeline choices including system prompts, tool-description detail, context scope, and single-agent versus multi-agent architectures. Results show that strong models can achieve near-complete expected-call coverage on the benchmarked workflows, but reliability depends strongly on both task structure and agent configuration. Comprehensive tool descriptions consistently reduce failures, few-shot prompting can cause severe inaction for some models, cumulative context harms constrained models, and multi-agent decomposition helps weak workers or long sessions at the cost of additional calls. These findings provide practical guidance for deploying local LLM agents in stateful hardware design environments. ---