# Research Papers — 2026-09 · bundle page 75 of 266 > Full-text markdown of papers #3701–3750 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/75 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/74.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/76.md) ### Can Circuit Alignment Predict OOD Generalization? Authors: Ayan Banerjee, Abhra Chaudhuri, Josep Llados, Umapada Pal, Anjan Dutta Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31996v1 Can out-of-distribution (OOD) generalization be predicted from a trained model's weights alone, without any target-domain data? Existing representational similarity metrics (CKA, SVCCA, RSA) compare activations rather than forecast generalization. We show they are provably insensitive to structural rerouting in the computational graph, the very change distribution shift induces. We close this gap with the Circuit Alignment Score (CAS), which compares class-specific circuits across domains via graph kernels, decomposed into same-class coherence and cross-class confusion. Casting CAS as a Lebesgue integral over the domain distribution, we prove its Monte Carlo estimate recovers the ground-truth ranking of learners by OOD accuracy, with pairwise inversion error vanishing at rate $O(1/M)$, where $M$ is the number of sampled domains. Across $48$ learners on PACS, CAS attains $0.88$ rank correlation with OOD accuracy, versus $0.58$ (CKA), $0.23$ (SVCCA), and $0.14$ (RSA), with similar trends on other benchmarks and even against data-dependent methods, making it the first provably consistent predictor of distributional robustness requiring neither target-domain data nor labels. The code is available at: https://github.com/ayanban011/ACE --- ### Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents Authors: Jihan Yao, Sihan Zeng, Shangbin Feng, Zhiyuan Fan, Banghua Zhu, Yulia Tsvetkov Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31995v1 Long-horizon coding agents receive verifiable rewards only after completing expensive sequences of tool calls. This increases inference cost, amplifies early wrong hypotheses, and can lead to sparse terminal reward and unstable training. We introduce Contextual Early Reward (CER), which predicts terminal reward through behavioral evidence in a trajectory prefix. CER synthesizes adaptive rubrics specific to the current task and stage through experiences summarized from related historical tasks. In test-time scaling on SWE-bench Verified, CER improves RM@8 over the strongest baseline by 4.2 percentage points (pp) on Nemotron 3 Ultra and 2.0 pp on Qwen 3.6 27B; on Nemotron, it takes only 15.3% tokens to match the best baseline performance. In RL training experiments, CER exceeds full-rollout TMax by 1.9 pp while using 52.7% fewer online policy-and-judge tokens. Together, CER provides an interpretable, efficient, and dense evaluation method for long-horizon coding agents. --- ### Identifiability Limits of Gravitational Wave Phase Deviations: Multiclass Classification with a Multihead Neural Network Authors: Lavinia Heisenberg, Shayan Hemmatyar Published: 2026-09-25 Categories: gr-qc, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2609.31993v1 We study how well gravitational-wave phase deviations can be identified using a neural network with classification and regression heads. The classification head distinguishes general relativity (GR) from six parametrized post-Einsteinian phase families with exponents $b\in\{-7,-5,-3,-1,+1,+2\}$; the regression head predicts the logarithm of the coupling magnitude, $\log_{10}|β|$. The network input is a response function quantifying the sensitivity of waveform mismatch to waveform deformations. We use stationary Gaussian noise with the Advanced LIGO design spectrum for 262 sources and a measured Hanford spectrum from the third observing run (O3) for 132 sources, and also test injections into recorded Hanford strain. On the two Gaussian datasets, the network identifies the exponent of deviations clearly above the noise with accuracies of $0.427$ and $0.329$. To interpret these results, we compare the network with an approximate classifier built from predicted waveform residuals for the six phase families and same sources. The two classifiers often confuse the same families. Examining residuals left by different phase corrections, we link these errors to similarities between the underlying deviations. On selected recorded Hanford strain, networks trained on simulated or recorded noise achieve overall classification accuracies close to those on simulated Hanford noise. Of thirteen neural-network variants tested on the Advanced LIGO design dataset, the recurrent network has the highest mean classification accuracy for loud deviations, although all variants remain below the approximate classifier. The network nearly matches that classifier's accuracy, indicating that identification is limited by similarities between neighboring phase families rather than by the network, for known intrinsic source parameters. --- ### Mechanistic Interpretability Reveals Shared Causal Subspaces in Brain-to-Speech Decoders Authors: Maryam Maghsoudi, Ayushi Mishra, Sanghamitra Dutta Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31992v1 Decoding covert speech, such as mimed or imagined, from brain activity is harder than decoding vocalized speech. Cross-modal transfer, where information from one speech form helps decode another, is a promising remedy; yet how a decoder internally represents and processes brain activity from different speech forms remains unclear. In this work, we ask: which internal neurons of a decoder carry cross-modal information, and are these neurons shared across different speech forms? To answer these questions, we leverage mechanistic interpretability, using recordings of the same sentences in vocalized, mimed, and imagined input pairs for activation patching. We insert the decoder's internal activity for a sentence in one condition into its processing of the same sentence in another and measure the change in decoding accuracy. We find that no single neuron drives this benefit; instead, it arises from small groups of neurons, with vocalized speech as the most useful source. These groups are largely condition-specific in the early stage of the decoder but overlap in the later stage. These findings point toward more data-efficient covert speech decoders through training objectives that encourage shared later-stage representations learned mainly from vocalized data. --- ### CSI-Agent: LLM-Assisted Few-Shot Adaptation for Cross-Domain Wi-Fi CSI Sensing Authors: Tianya Zhao, Chuan Liu, Xuyu Wang Published: 2026-09-25 Categories: cs.AI, cs.NI arXiv: https://arxiv.org/abs/2609.31990v1 Wi-Fi channel state information (CSI) has enabled device-free sensing applications such as human activity recognition. However, CSI sensing models remain brittle in cross-domain deployment, where changes in users or environments can produce incorrect predictions. Existing solutions usually treat this problem as an offline model-design problem, by pretraining a stronger representation or applying one fixed adaptation method to the entire target domain. In practice, labeled target data are scarce and different classes may fail in different ways under the same domain shift. To address this, we propose CSI-Agent, an evidence-seeking LLM agent that reformulates cross-domain CSI adaptation as a deployment-time decision-making problem. Rather than processing raw CSI or making sample-level predictions, CSI-Agent summarizes target-domain behavior into sensing-grounded class-level evidence. It establishes a strong target-adaptive default from complementary CSI views and uses an LLM planner to determine whether each class should retain the default or invoke a specialized action. Deterministic verification and bounded execution further reduce unreliable interventions. We evaluate CSI-Agent on four public datasets using five cross-domain splits covering device, user, environment, and compositional shifts. Under 1-shot adaptation, CSI-Agent achieves the best target-domain performance across all splits and improves the average Macro-F1 by about 16\% compared to the strongest baseline method. --- ### Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game Authors: Vivek Anand, Muthu Chandrasekaran, Shiva Chaitanya Published: 2026-09-25 Categories: cs.CL, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.31989v1 We study communication between two frozen large language models from different providers, with different tokenizers, accessed through their API endpoints. The two play a referential game: one sees an object and describes it in a short fixed-length message over a small alphabet; the other must pick that object out of a candidate set. Neither model's weights are updated. Each agent's prompt is rewritten by an isolated prompt optimizer whose reflection model reads that agent's scored interactions. In the positional setting, optimized prompts carry a shared code that generalizes to held-out objects above a measured no-codebook baseline, including when the memory window is removed. In a second setting, independent per-letter blocks no longer fit within the message, although a whole-object place value code does. The base system fails to establish reliable communication: the sender struggles to retain an injective rule, and the receiver has too few confirmed examples in view. A sender collision penalty, retention of successful interactions, and sequential optimization enable successful place value communication in some runs. Outcomes vary across runs and reflection models. In successful runs, the protocol is written into the optimized prompts, where it can be read and audited directly. --- ### Lagrangian and Hamiltonian Neural Networks With a Dissipative System Authors: V. Rayamajhi, J. Singal Published: 2026-09-25 Categories: cs.LG, physics.class-ph arXiv: https://arxiv.org/abs/2609.31988v1 We investigate the applicability of Lagrangian and Hamiltonian Neural Network models to a dissipative system that has explicit time dependence in its Lagrangian, Hamiltonian, and total energy. To do so we consider these neural network models for simulated systems of a harmonic one-dimensional, one-component oscillator with damping, as well as without damping for comparison. We find that both the Lagrangian and Hamiltonian approaches are able to predict the empirical physical behavior of the damped oscillator systems and to effectively ``learn'' to varying degrees the underlying Lagrangians and Hamiltonians, as has previously been shown to be the case with undamped oscillator systems. These investigations elucidate important properties of Lagrangian and Hamiltonian mechanics, including properties that are not manifest when considering systems without explicit time dependence. --- ### Does Vision-Language Pretraining Granularity Matter? A Controlled Evaluation of Vision-Language Objectives Across Chest X-Ray Interpretation Tasks Authors: Denis Musinguzi, Andrew Katumba, Prasenjit Mitra Published: 2026-09-25 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.31985v1 Vision-language pretraining objectives differ in the spatial granularity of their supervision, yet the implications of this distribution for chest X-ray interpretation remain underexplored. We present a controlled study that isolates the pretraining objective: holding the encoder and pretraining data fixed, we train nine objectives spanning global and local contrastive learning, captioning, and their combinations, and evaluate across five chest X-ray tasks of increasing spatial granularity. We find that (i) pretraining granularity aligns with task granularity at the extremes, with local objectives leading on abnormality detection and global objectives on classification; (ii) local objectives are surprisingly competitive on global-level generation and question answering tasks; (iii) the merits of captioning and contrastive learning reverse across granularity levels; and (iv) among combinations, mixing captioning and contrastive supervision is strongest on classification and in distribution generation, while pairing two captioning objectives generalizes best on zero-shot report generation. These results show that no single objective is universally optimal, and that the interaction of objective type, granularity, and task governs downstream performance. --- ### Understanding the Subspace Stabilization of the Hessian and Gradient Covariance Matrix Authors: Fangshuo Liao, Anastasios Kyrillidis Published: 2026-09-25 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.31983v1 The phenomenon of the top subspace stabilization of the Hessian matrix is an surprising and critical aspect in study of the second-order information of neural network training. Prior work argues that the top subspace of the Hessian stabilizes by measuring the overlap between the top subspaces of the step-wise Hessian, and explains this stabilization with diminishing parameter change in the late phase of training. In this paper, we define a new instability metric for the subspace evolution, and use it to detect subspace stabilization that is independent of the magnitude of parameter change. In the meantime, we observe that the gradient covariance matrix has a similar property of its top subspace to the Hessian. By using a between-class and within-class decomposition of the gradient covariance matrix, we identify an explicit form that gives a near-perfect approximation of the top-$(C-1)$ subspace of the Hessian and the gradient covariance matrix. In the gradient flow set-up, we show that the slow evolution of the idenfied approximation is due to the separation between the outlier and the bulk eigenvalues of the Hessian matrix, thus providing an explanation to the phenomenon of the top subspace stabilization of the Hessian matrix. --- ### Evasion Attacks on Cost-Utility-Based Adversarial Training for Online AutoML in IoT Networks Authors: Chukwunonso Henry Nwokoye, Wajiha Zaheer, Khalil El-Khatib, Li Yang Published: 2026-09-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.31981v1 As Internet of Things (IoT) networks increasingly depend on machine learning for anomaly, malware, intrusion detection, and network monitoring, such systems have become attractive targets for evasion attacks. Evasion attacks pose a major security risk because an adversary intentionally modifies input data to mislead a trained model into producing incorrect predictions while evading detection. This study evaluates the impact of black-box evasion attacks on a cost-utility-based adversarial training defense strategy in an Online AutoML context for IoT networks. Specifically, evasion attacks were applied to online learners, including Hoeffding Tree (HT), Leveraging Bagging (LB), Streaming Random Patches (SRP), Hoeffding Adaptive Tree (HAT), and Adaptive Random Forest (ARF). By developing naive and adversarially trained (AT) versions of these online learners, we generated clean and adversarial accuracies for each model. The results show that the AT versions of LB and SRP performed best, achieving the highest adversarial accuracy (0.985) and high clean accuracy (0.993) at the highest cost budget of 1.00, with a maximum accuracy reduction of only 0.8%. Finally, drift detection was conducted using the Early Drift Detection Method (EDDM). --- ### Goal-Persistent Coding Agents as Scientific Performance Engineers: A Fixed-Radius Nearest-Neighbor Case Study Authors: Xiangyang Ju Published: 2026-09-25 Categories: cs.AI, cs.PF, cs.SE arXiv: https://arxiv.org/abs/2609.31980v1 Coding agents can pursue persistent objectives across many tool-use turns, but evidence that general-purpose agents can conduct rigorous scientific performance engineering remains limited. We present a repository-scale case study in which off-the-shelf Codex and Claude Code agents optimize fixed-radius nearest-neighbor (FRNN) search for particle tracking. Starting from a PyTorch-dependent CUDA implementation, the agents follow an executable goal that specifies exact-correctness tests, profiling requirements, and acceptance criteria without prescribing code transformations. In the primary sequential trajectory, they autonomously remove the PyTorch dependency and conduct hypothesis-driven optimization experiments. The resulting standalone C++/CUDA library exactly reproduces the targeted reference result. Its synchronous NumPy interface achieved 1.6-fold speedup over the original GPU-resident PyTorch interface, despite including host transfers. Similar speedups were observed across different GPU architectures and software stacks. An independent optimization rerun followed a different sequence of hypotheses and reached even better performance on the target workload. These results show that goal-persistent coding agents can act as experimental performance engineers, and that executable scientific contracts are needed both to guide and to validate their optimization. --- ### Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows Authors: Louis Grenioux, RuiKang OuYang, Luhuan Wu Published: 2026-09-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.31978v1 Generating independent, equilibrium samples of molecular systems at scale remains a central obstacle in computational statistical mechanics. Boltzmann Generators address this by pairing a generative model with importance sampling to obtain consistent samples from the target distribution. We introduce Normalizing Flow Flow Maps (NF$^2$M), which combines the strengths of recent stochastic flow maps with the tractability of classic normalizing flows to build a Boltzmann Generator. Unlike most methods, which correct the generative model only at the end, NF$^2$M reweighs each denoising transition as generation proceeds, avoiding wasted compute on trajectories that are ultimately discarded. At each denoising step, a conditional normalizing flow proposes clean configurations given the current noisy state (a simpler task than sampling directly from the target) and its exact likelihood enables correcting each proposal toward the true denoising transition of the target Boltzmann distribution. This is in contrast to most existing methods, whose likelihoods are approximate or expensive to evaluate, undermining the statistical reliability of the correction. We establish consistency of the corrected transitions and bound how approximation errors propagate through the sampling chain. We evaluate NF$^2$M on peptide systems, demonstrating improved sampling efficiency and sample quality. --- ### Toward Embedding-Based Psychometrics: Structural Modeling of Assessment-Item Semantics With Contextual Scores Authors: Jinsong Chen, Shi-Ting Chen Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31976v1 Contextual scores represent assessment items through their similarities to reference words in an external corpus. We examine the semantic structure of scores for 40 TIMSS mathematics scored units using a partially specified two-step factor procedure. A search across factor counts identifies a persistent seven-group structure under the featured construction. Subsequent comparisons consistently favor a general dimension alongside group associations, although individual group memberships remain sensitive to some specification choices. Item examples distinguish recurring, cross-domain, sensitive, and imposed associations. Simpler and unrestricted references clarify the contribution and limits of the anchored representation: it improves on a single factor but does not achieve the lowest working Bayesian information criterion (BIC). A separate response benchmark compares three initial Q constructions and their Hull-PVAF revisions under higher-order and saturated attribute distributions. Among these diagnostic models, BIC favors the official content framework and the Akaike information criterion (AIC) favors its direct four-factor augmentation, but a matched unidimensional two-parameter logistic model has lower AIC and BIC than all twelve conditions. These findings support a conditional semantic representation while limiting direct diagnostic interpretation. We discuss learned text-assisted response calibration as a prospective application requiring a larger calibrated item bank and independent evaluation. --- ### Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs Authors: Maria Lomeli, Antoine Groudiev, Matthijs Douze, Loïc Cabannes, Pierre Emmanuel Mazaré, François Fleuret, Maximilian Beck, Gergely Szilvasy, Naila Murray, Hervé Jégou Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31975v1 This paper introduces model casting, a mid-training recipe that drastically sparsifies the activations within the Feed-Forward Network (FFN) layer. With this strategy, at inference time, we first compute the output of the gating matrix and, thanks to its high sparsity, we avoid computations with the two other matrices, reducing the FLOP count by up to 3x. While this theoretical speedup is an upper bound, model casting translates into significant speedups both on CPU and GPU. We then introduce LoPA Gating, a new FFN design that increases the maximum theoretical speedup. It is a low-FLOPs parameterization of the gating matrix that overcomes the 3x cap by allocating fewer FLOPs and parameters to the gating matrix, compared to the two other FFN matrices that are sparsely activated. We consider two cases: (i) we cast a pre-trained model with a sparsity inducing activation; (ii) we train with LoPA from scratch. In all settings, we significantly outperform existing pruning solutions and regular RELU-fication. For instance, at matched quality, we achieve a 3.2x FLOP speedup with LoPA Casting, against 1.6x at best for competing methods top-p and TEAL. Using dedicated kernels, we achieve an actual 3.31x speed-up on GPU at 90% sparsity, past the 3x ceiling of standard gating; RELU-fication, meanwhile, plateaus below 80% sparsity. --- ### Extraction of clinical findings from mammography and breast ultrasound reports: a comparison between specialists and Artificial Intelligence Authors: Lorenzo Farias, Hanna Reckziegel, Daniela Duarte da Silva Bagatini, Daniel Schulz, Gabriela de Andrade Monteiro, Letícia Zanatta, Ana Laura Brill Thum, Priscila Schmidt Lora, Débora Oliveira da Silva, Ana Paula Wernz da Cunha Müller, Cristiane Drebes Pedron Published: 2026-09-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.31974v1 Breast cancer is the leading cause of cancer-related death among women in Brazil, and the time between the request and the release of mammography reports directly influences adherence to screening, making the agility in processing these reports a critical factor for early diagnosis. In this context, this study compares the performance of a Large Language Model (LLM) with manual extraction performed by a team of health researchers in identifying clinical findings from mammography and breast ultrasound reports written in Brazilian Portuguese. Named Entity Recognition (NER) was applied through Prompt Engineering using a few-shot strategy, employing the Gemini 2.5 Flash model, selected from preliminary exploratory tests with four candidate models. The Gemini 2.5 Flash model demonstrated the best performance, achieving a Macro F1 of 0.91 and a Micro F1 of 0.98. The subjective validation, in which 29 exams of different formats were evaluated by health researchers using a Likert scale, yielded an agreement index of 93.1%. The model outperformed human extraction in overall Macro F1 (0.91 vs. 0.72), as in four reports the model correctly identified information that had been omitted or incorrectly recorded during manual extraction, demonstrating its potential as a complementary verification tool alongside specialists. The results confirm the hypothesis that LLMs, when instructed through Prompt Engineering, can achieve performance comparable to or superior to manual extraction by health professionals. --- ### Double-Edged Sword of Mediated Visibility: How Visual Framing Undermines Congresswomen's Perceived Competence Authors: Bryce J. Dietrich, Hyein Ko, Myriam Shiran Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31970v1 Women's presence in Congress has stalled below 30%. That institutional underrepresentation is mirrored by their limited visibility on televised news, where visual presentation can shape perceived competence and authority. Yet research tells us more about whether congresswomen appear than how they are visually framed. Facial recognition analysis of 695,464 image-text segments from CNN and Fox News (2011-2021) reveals that congresswomen appear disproportionately in split-screen rather than solo shots. Two pre-registered experiments with 6,220 participants show that, in static frames, split-screen framing reduces congresswomen's perceived political competence, but not congressmen's. In dynamic videos, the competence penalty disappears; instead, outraged language reduces a congresswoman's perceived warmth roughly three times as much as a congressman's. Suggestive evidence (p = .057) indicates that women viewers report greater external political efficacy after watching a congresswoman appear alone. We conclude that visual framing shapes both congresswomen's mediated visibility and their perceived capabilities. --- ### IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages Authors: Rajarshi Roy, Shobhit Banga, Jonathan Raiman, Supriya Paul, Bhaskar Singh, Manmeet Kaur, Sagar Jain, Hanuman Sidh, Pranav Sharma, Aditya Singh, Aaditya Pareek, Manas Dhir et al. Published: 2026-09-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31967v1 Full-duplex voice agents must handle pauses, take turns, backchannel, and respond to user interruptions in real time. Full-Duplex-Bench evaluates these behaviors, but its English-only corpus and reliance on word-timestamped ASR and an English-prompted LLM judge make it difficult to extend to Indian languages. We introduce IndicFDB, which extends it to ten languages spoken in India with 12,350 samples, nearly 17 times as many as the original. We address three challenges: finding conversational events in multilingual speech, evaluating their timing without reliable word-level alignment, and judging responses across languages. We mine pause handling, turn taking, and backchanneling samples from roughly 50,000 hours of channel-separated conversations using voice activity detection (VAD), and construct human-validated synthetic user interruption samples. Language-independent VAD heuristics evaluate timing, while an open-weight transcription and translation pipeline converts responses to English for LLM ratings of relevance and quality. Across seven voice agents, commercial APIs show unexpectedly consistent behavior across languages but are either fast or robust to pauses, never both, while monolingual open full-duplex models expose further tradeoffs among backchanneling, response quality, and latency. --- ### SNIP++: Fine-Grained Symbolic-Numerical Alignment for Symbolic Regression Authors: Benjamin Léger, Shubham Gupta, Samy Mammeri, Kazem Meidani, Cem Subakan, Christian Gagné Published: 2026-09-25 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31965v1 Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scientific discovery. Symbolic Regression (SR) relies on this connection directly: it searches for an expression that reproduces a given behavior. Recent multi-modal models learn this connection by embedding symbolic expressions and their numerical behavior in a shared representation space. We show that this embedding space is only globally aligned: complete expressions correspond to complete behaviors, but the contribution of individual parts of an expression is not represented. This granularity gap leaves the model unable to tell how a local edit to an expression changes its behavior, the central operation in SR. We introduce a compositional alignment method that closes this gap: a structural positional encoding exposes the substructure of an expression to the encoder, and a multi-granularity contrastive objective grounds each subexpression in the behavior it produces before propagating this grounding to the full expression. The resulting representations close much of the modality gap between symbolic and numerical embeddings, reliably distinguish the effects of local edits that the original alignment cannot, and transfer to external SR corpora. --- ### Symbolic Guidance for LLM Agents in Distributed Multiagent Coordination Authors: Ben Rachmut, Ning Zhang, Yevgeniy Vorobeychik, William Yeoh Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31963v1 Large language models (LLMs) are increasingly deployed as autonomous agents in multi-agent systems, yet their ability to reliably execute distributed coordination protocols remains poorly understood. While AgentsNet, a benchmark framework for distributed coordination among LLM agents, enables such coordination, granting full reasoning autonomy often leads to inconsistent or degraded performance in complex domains. We hypothesize that coordination can be improved by regulating agent autonomy through symbolic guidance derived from established algorithms. To investigate this, we introduce the \emph{Symbolic Guidance Taxonomy (SGT)}, which characterizes a spectrum of autonomy ranging from open-ended natural language reasoning to fully prescribed algorithmic execution, with intermediate levels providing partial pseudocode guidance. Our results show that intermediate autonomy levels consistently outperform both unguided agents and fully prescriptive specifications. These findings identify autonomy regulation as a key design principle for LLM-based distributed coordination. --- ### Improving Audiovisual Speech Recognition through Synthetic Visual Data Augmentation Authors: Pol Buitrago, Pol Gàlvez, Javier Hernando Published: 2026-09-25 Categories: eess.AS, cs.CL, cs.SD, eess.IV arXiv: https://arxiv.org/abs/2609.31961v1 Audiovisual Speech Recognition (AVSR) is a multimodal approach to speech recognition that incorporates visual information from lip movements to enhance model performance. Despite its advantages, its development remains constrained by the limited availability of labeled audiovisual (AV) datasets. This work explores the use of synthetic visual data as a solution, using an audio-driven talking-head pipeline to generate lip-synchronized visual content from existing audio data. We evaluate the effectiveness of synthetic visual data both as an augmentation strategy and as a standalone training resource, applying our approach to Spanish and Catalan. Our results show that augmenting real AV data with synthetic samples yields relative Word Error Rate (WER) reductions of up to 16.2%, demonstrating the potential of this approach. Moreover, we demonstrate that synthetic data alone can serve as a baseline for AVSR training in languages lacking AV datasets. These findings provide evidence that synthetic visual data can serve as a scalable solution to AVSR data scarcity, enabling broader language coverage. --- ### Model-Agnostic Online Certificate-Driven Calibration for Time Series Forecasting Under Distribution Shift Authors: Chenfeng Huang, Zixuan Ma, George Michailidis Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31960v1 Time series out-of-distribution generalization requires forecasters to remain reliable when deployment dynamics differ from training conditions due to covariate shift, concept shift, and temporal dependence. Probably Approximately Correct Bayesian domain adaptation provides computable certificates by decomposing target risk into a source risk term, a source-to-target mismatch term, and a complexity term, but standard analyses rely on independent sampling and distributional stability, assumptions that are violated in time series by serial dependence and nonstationary shift. We propose a model-agnostic online martingale Probably Approximately Correct Bayesian framework that yields finite-sample certificates under temporal dependence and distribution shift. The certificate replaces independent-sample concentration with martingale concentration that adapts to loss scale and predictable variation. We use the certificate as a surrogate regularizer for online calibration by training a gated residual Bayesian head on top of a fixed forecasting backbone, producing a corrective update that reverts to the backbone prediction when the gate is closed. Online calibration combines a source risk anchor, a posterior-shift penalty, and a time-adaptive mismatch term computed from target windows observed before forecasting. It follows a predict-then-update protocol in which outcomes become available only after forecasting and are used to update subsequent predictions. Experiments across convolutional, attention-based, and large language model-based forecasters show improved stability and accuracy under covariate and concept shift. --- ### CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs Authors: Zhenhao Zhang, Zhaoyu Fan, Haohan Ying, Jingwen Hu, Hancen Fan, Junhao Zhou, Zitian Chen, Linchao Zhu Published: 2026-09-25 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31957v1 Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and trajectory supervision. To address these gaps, we present CaptchaArena, the first large-scale, fine-grained training dataset for interactive CAPTCHA solving. It contains 50K puzzles across 20 CAPTCHA types and 5 interaction modes, with every solution verified through execution. CaptchaArena provides 50K screenshot-action trajectories, including 46K with step-by-step reasoning annotations. It also includes fine-grained pixel-mask annotations for irregular targets. Using CaptchaArena, we train CaptchaAgent, a single 9B policy for all 20 CAPTCHA types, with supervised fine-tuning followed by reinforcement learning. The environment verifier directly provides the RL reward. Supervised fine-tuning reaches 70.5 Pass@1, and reinforcement learning further improves it to 71.7, while also improving performance on two external benchmarks. These results demonstrate the value of large-scale, fine-grained computer-use supervision for training interactive CAPTCHA agents. We release CaptchaArena and CaptchaAgent at https://github.com/X0X0X00/CaptchaArena. --- ### Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction Authors: Olli Tuomi Published: 2026-09-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.31956v1 The corpus-mean direction of a transformer's residual stream is a component shared across all inputs, and is commonly removed by mean-centering before representational analysis. We present evidence that it is a functional component: the reference against which the MLP gate population sets its operating point. In Phi-2, an exact decomposition of resting gate pre-activations shows that at mid-stack layers the resting inhibition of >99.9% of gates is carried by the coupling $w \cdot b_L$ to the carried mean direction, at 48-56$\times$ the explicit bias parameter, and the coupling is direction-specific: a random direction at matched norm orders the population's firing rates at Spearman $ρ\leq 0.09$ where the reference reaches 0.95. (That 0.95 is near-tautological on its own; the paper derives its null.) Causally, removing the stream's projection on the reference multiplies above-threshold firing by about 9$\times$, dose-monotonically, at 23-59$\times$ a norm-matched control; a random-initialised twin is flat, and replacement tests show that the direction carries the function and the magnitude does not. A direction-matched control makes the same point: noise injected along the reference costs 8-42$\times$ the same energy along a random direction. The decomposition replicates on four further families spanning both gate types (GELU with an explicit gate bias, bias-free SwiGLU), and the dose-response on two of them. Across an eight-model scan the mechanism is present in every GELU and SiLU family and absent only in OPT, where an opposing LayerNorm bias cancels the carried reference. Gate thresholds are implemented as couplings to a constant the network builds for the distribution it is reading, with the bias parameters contributing little; how much of that constant is carried in the stream and how much in parameters depends on the architecture. --- ### On-Policy Attention Linearization Authors: Arian Raje, Anupam Nayak, Anthony Fei, Akaash Parthasarathy, Mohamed Abdelfattah, Gauri Joshi Published: 2026-09-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.31947v1 Hybrid transformer architectures that replace most softmax attention layers with linear attention offer transformer-level quality at a fraction of the memory cost. Rather than pretraining such models, a growing body of work distills them from already trained full-attention transformers. However, these distilled models often collapse on long-context retrieval and reasoning tasks, particularly when operating in thinking mode, where the efficiency gains of hybrid architectures matter most. Since linear attention layers must compress context into a fixed-size state, their errors compound over long sequences. As off-policy distillation never teaches the student model to recover from this drift, tasks that necessitate longer sequence lengths become especially challenging. We introduce On-Policy Attention Linearization (OPAL) in which the hybrid attention student samples its own long-context trajectories and receives dense supervision from the frozen full-attention teacher. Applying OPAL to Qwen3-4B and MiMo-7B-RL-0530, we recover $87$--$94\%$ of full-attention performance on commonsense reasoning, $100\%$ on needle-in-a-haystack (NIAH) retrieval, and $83$--$93\%$ on mathematical reasoning with only 3B training tokens. We achieve these results without supervised fine-tuning (SFT) or reinforcement learning with verifiable rewards (RLVR). Compared with the strongest prior linearization method, which recovers $68\%$ of its teacher's retrieval performance and $21.6\%$ absolute average mathematical reasoning accuracy, OPAL fully recovers retrieval and achieves $67.6$--$72.2\%$ on math reasoning. --- ### Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization Authors: Haris Moazam Sheikh Published: 2026-09-25 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.31940v1 Multi-objective Bayesian optimization (MOBO) is commonly approached through specialized acquisition functions or scalarization schemes designed to explicitly account for trade-offs among non-preferential objectives. In this work, we show that such complexity might be unnecessary. We propose a framework that extends standard single-objective acquisition functions directly to the multi-objective setting through a hypervolume-based transformation. We further extend hedge strategies for acquisition functions, which are typically used only in single-objective optimization, to the multi-objective regime. Our approach requires minimal modification to existing Bayesian optimization pipelines and avoids the need for bespoke multi-objective formulations. We demonstrate how a broad class of commonly used single-objective acquisition functions and hedge strategies can be adapted in a principled manner to handle multiple objectives, while preserving their intuitive interpretation and computational efficiency. Empirically, we evaluate the proposed methods across a range of synthetic and real-world multi-objective benchmarks. Despite their simplicity, our extensions consistently match or outperform more complex state-of-the-art MOBO methods in terms of optimization performance and sample efficiency. These results suggest that effective multi-objective Bayesian optimization can be achieved by reusing and carefully extending well-established single-objective acquisition strategies, offering a simpler and more flexible alternative to existing approaches. --- ### BioDyad: Synchronize Biomedical Discovery and Machine Learning Engineering Authors: Xingbo Du, Fadli Aulawi Al Ghiffari, Leonard Song, Loka Li, Duzhen Zhang, Zixiao Wang, Xiuying Chen, Le Song Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31939v1 Agentic biomedical machine learning (ML) draws on complementary advances in biomedical evidence acquisition and executable program search. Existing systems connect aspects of these capabilities, but coordinating them throughout program search remains challenging. New evidence must guide candidate construction, execution outcomes must inform subsequent discovery and reuse, and validation demands must fit the search budget. We introduce BioDyad, which couples biomedical discovery and ML engineering through two hierarchies within Monte Carlo graph search. Its scientific hierarchy combines prior biomedical guidance with iterative discovery, then links biomedical plans to execution outcomes in memory for reuse across candidates. Its engineering hierarchy moves candidate programs from smoke execution, through train/validation evaluation, to full-data retraining. We evaluate BioDyad on the 76-task BioXArena benchmark under a two-hour per-task budget with three matched LLM backends. It achieves the highest penalized all-task score and task success rate among four agent methods and a one-shot baseline under each backend. These results support coordinating biomedical discovery and ML engineering to integrate external knowledge into executable programs across heterogeneous biomedical tasks. --- ### Cache-Aware Conv3D Lowering Across Embedded World-Model Decoders Authors: Jiaming Zhang, Wu Yang, Shuai Tao, Wulong Liu Published: 2026-09-25 Categories: cs.LG, cs.PF arXiv: https://arxiv.org/abs/2609.31938v1 Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model but also on how the execution runtime represents its operations. We introduce a cache-aware lowering that expresses supported causal Conv3D calls as batched spatial Conv2D operations while preserving pretrained weights, temporal-cache semantics, convolution parameters, bias placement, and output layout. Across the complete Cosmos3-Edge image-to-video pipeline on a 64-GB NVIDIA Jetson AGX Orin, the proposed route accelerates VAE decoding by approximately $7\times$ and reduces complete-generation latency by more than $2\times$, while repeated decoder evaluations maintain complete fast-path coverage without fallbacks. The unchanged lowering also improves Cosmos3-Nano and transfers to LingBot-World's architecturally distinct Wan2.1 VAE. A clean-device comparison against fully specialized TensorRT shows that TensorRT provides a further $1.36\times$ steady-state improvement, but requires substantially greater per-module and per-runtime-state AOT specialization. Same-latent BF16 and FP32 evaluations characterize the finite-precision differences introduced by the alternative execution order. Together, these results position cache-aware lowering as a lightweight runtime optimization that recovers most of the available decoder acceleration without modifying the learned models themselves. --- ### Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core Authors: Ali Afoud, Jie JW Wu Published: 2026-09-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.31937v1 Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing each action, formatting it, and judging whether the result is adequate. Nothing outside the generative loop can reject its output, so an agent that cannot make progress does not report failure; it runs until an external budget stops it. We propose treating verification as an architectural layer by adapting the V-model from software engineering: specification levels descend from requirements to individual steps, each level is paired with a dedicated verifier, a deterministic controller enforces every verdict, and only verification outcomes write to memory, so a rejection localizes the level that introduced the fault and an agent halts by declining rather than by exhaustion. Each verifier separates a zero-cost deterministic \emph{gate} from an optional LLM \emph{judge}, so the contribution and cost of each can be measured independently. We report a pilot implementing the acceptance- and unit-level verifier pairs, comparing five configurations that share one executor, tool set, and scorer and differ only in verification, on the four-hop stratum of MuSiQue with an 8B-parameter backbone. Across 47 executions, the two unverified configurations answered none of ten questions, every run ending at a step cap or provider token limit; the verified configuration without a planner answered eight and abstained on the rest. Deterministic gates produced eight of the nine observed corrections at zero marginal cost, and planning degraded performance once verification was present. These results characterize termination behavior, not accuracy at scale; we outline a twelve-month plan to complete and evaluate the full architecture, including the integration-level pair the pilot omits. --- ### ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems Authors: Darshan Thaker, Lachlan Ewen MacDonald, René Vidal Published: 2026-09-25 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.31933v1 Native-latent guidance is a recent paradigm for solving inverse problems with latent diffusion models. It replaces repeated evaluations of the image-space forward model, each requiring a decoder pass, with efficient guidance computed using a learned latent-space surrogate. However, existing methods apply guidance uniformly across latent dimensions, ignoring that measurements are informative only along certain directions and that the reliability of model predictions varies across inputs and timesteps. We propose ANaLOG, a framework for efficient uncertainty-aware guidance with pretrained latent diffusion models. ANaLOG models uncertainty by learning an anisotropic, input- and time-dependent covariance that is integrated into the guidance mechanism to emphasize reliable directions and downweight uncertain ones. We theoretically analyze this framework in a linear model setting and prove that anisotropic, uncertainty-aware weighting is necessary for correct sampling, whereas isotropic guidance induces sampling errors. Experiments across five challenging inverse problems show that ANaLOG improves perceptual reconstruction quality over existing methods while preserving efficiency. --- ### Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations Authors: Mohamed Shaaban, Mohamed Elmahallawy, Marius Bernahrndt, Tobias Hecking Published: 2026-09-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.31932v1 Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental monitoring. However, conventional federated learning (FL) is ill-suited to onboard satellite learning, as it assumes computational, memory, and communication resources beyond the capabilities of resource-constrained LEO platforms, often necessitating the transmission of raw imagery to ground stations. We present COSMIC-FL, a resource-aware FL framework for efficient onboard learning in LEO satellite constellations. COSMIC-FL introduces two complementary Mixture-of-Experts (MoE) architectures: a Sliced design that shares backbone representations while activating task-specific channel subsets, and a Modular design that employs lightweight gating to route inputs to physically separated expert networks. A semantic class-to-expert mapping enables each satellite to train, update, and communicate only the expert paths relevant to its local data. To further improve efficiency, COSMIC-FL integrates staged optimization with three structured pruning strategies: server-side pruning, client-side fixed-ratio pruning with mean-vote aggregation, and adaptive client-side per-layer pruning based on aggregated importance and a MAD-based gap criterion. Combined with semantic expert routing, these techniques jointly adapt computation and model sparsity to both data semantics and layer importance, yielding a favourable accuracy--efficiency trade-off for heterogeneous space platforms. Experiments on six image classification benchmarks under highly non-i.i.d. settings show that COSMIC-FL maintains competitive accuracy while reducing communication, computation, and energy consumption by up to 80% over SOTA FL methods. We further validate COSMIC-FL on an NVIDIA Jetson AGX Orin, confirming its efficiency gains under realistic embedded deployment constraints. --- ### Artificial Neural Network Assisted Modelling of Tangent Galvanometer Measurements for the Determination of Horizontal Component of Earth's Magnetic Field Authors: Saralasrita Mohanty, Sudakshina Prusty, Anshuman Pal, Pradipta Kumar Mishra Published: 2026-09-25 Categories: physics.ed-ph, cs.LG arXiv: https://arxiv.org/abs/2609.31930v1 The Tangent Galvanometer (TG) is a standard undergraduate laboratory experiment for estimating the horizontal component of Earth's magnetic field (BH) by measuring the angle of deflection of a magnetic needle corresponding to the current flowing through a circular coil. In this study, an artificial neural network (ANN) is used as a complementary data-driven model to predict the value of BH. A dataset comprising 225 observations obtained using 50-turn and 500-turn coils was used for developing the ANN model. After quality control, 223 observations were retained and divided into training (70%), validation (15%), and testing (15%) subsets. The model was optimized using a feed-forward neural network with Tanh activation. Three different models (Models A, B, and C) with different input variables were compared for optimum performance. Model C used five input variables: current, deflection angle, tan(theta), magnetic field produced by the coil, and number of turns. The addition of tan(theta) produced a substantial improvement in prediction performance, which was further improved by including the magnetic field produced by the coil. Model C gave the best test performance, with R2 = 0.99053, RMSE = 0.54076 microT, and MAE = 0.32940 microT. The experimental and ANN-predicted values of BH were also compared with an adopted local geomagnetic reference value of 39.0 microT. The mean experimental and ANN-predicted values were 37.38898 microT and 37.32161 microT, respectively. The results demonstrate the usefulness of ANN as a complementary tool for analyzing experimental variability and nonlinear relationships in an undergraduate physics laboratory experiment. --- ### Recipe-Matching, Not Equivalence Authors: Ali Habibullah, Mohammad Alshiekh, Yazan Alshoibi, Salman Khan, Naeemullah Khan Published: 2026-09-25 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.31927v1 MathNet-Retrieve asks a retriever to find, for a math problem, a document stating the same problem. An LLM under one fixed prompt writes each gold document and its near-miss distractors; LLM judges filter them. We call this procedure the "recipe", training on pairs built the same way "recipe-matching", and ask how much score it buys beyond the ability the benchmark claims to test. Two models from one base, matched in rows and settings, differ only in the training file: pairs written under the benchmark's published prompt by another vendor's LLM and judge, or computer-algebra-verified pairs with no LLM anywhere. The first leads by 45 R@1 points on the easy tier. By a non-LLM paraphrase control, half to two thirds of that gap comes from the pairs being LLM-written at all: LLM rewrites under two unrelated prompts, with the verified model's negatives, recover 30 and 22 of the 45 points; back-translations with the same negatives recover almost none. The remaining 15 to 25 points appear only under the benchmark's own prompt and vanish on real duplicates no generator wrote, the same problem in two languages. The hard tier rewards the recipe's pair structure, a deep rewrite against a minimal-edit near-miss: LLM rewrites alone score zero on it, attaching negatives unlocks it, and every negative that does so costs cross-language points; the sets scoring highest on it separate near-misses no LLM wrote worse than LLM rewrites with verified negatives. MELD also moves when a model trains on pairs built its way, without losing retention; on SABER-Math the registered attack fails, and the one gain, from its LLM-written summaries, is small but holds at a matched budget. Only on MathNet-Retrieve could we pin an inversion, benchmark score up and real retention down, to one edit of a training file. We release the generator-free duplicate evaluations, the near-miss test and three trained models. --- ### Vibe Analysis: Exploring LLM Adoption by Data Visualization Practitioners Authors: Shani C Spivak, Aditi Krishna, Mahsan Nourani, Melanie Tory Published: 2026-09-25 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.31922v1 Large language models (LLMs) are enticing in their promise to support data visualization (Vis) through faster and simpler workflows for data prep, analysis, and visualization creation. Yet LLMs are notoriously error-prone and not built for data visualization tasks. Few studies have explored LLM adoption among Vis practitioners. To fill this gap, we conducted semi-structured interviews with members of the Data Visualization Society, a global community of data visualization designers. Our findings show that Vis designers actively use LLMs for both creative and technical aspects of the visualization process. A new visualization workflow is emerging, a process we call vibe analysis, analogous to vibe coding. Some key challenges raised by participants parallel those of vibe coding, while others are Vis-specific, like gaps in Vis knowledge and chart verification. This work opens up opportunities for research combining LLM-mediated work with Vis tools that incorporate data visualization guidance, constraints, and best practices. --- ### Overview of the TREC 2025 Million Large Language Models track Authors: Evangelos Kanoulas, Panagiotis Eustratiadis, Jamie Callan, Mark Sanderson, Yongkang Li, Jingfen Qiao, Gabrielle Poerwawinata, Vaishali Pal Published: 2026-09-25 Categories: cs.IR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.31921v1 Agentic AI envisions ecosystems of intelligent agents collaboratively solving complex tasks with minimal human intervention. In such ecosystems, each agent possesses specialized expertise, making effective expert selection central to overall system performance. While most current approaches assume a small number of well-documented models, real-world expertise is far more diverse and cannot be adequately captured through static metadata or hand-written descriptions. We anticipate a future with millions of specialized language models (LLMs), each excelling in different domains or problem types. Rather than relying on predefined capability statements, we propose a retrieval-based paradigm in which an assistant agent infers expertise dynamically by examining models' observable behavior. Upon receiving a user query, the assistant ranks candidate LLMs based on demonstrated competence, enabling efficient and adaptive expert selection. The TREC Million LLM Track operationalizes this paradigm by shifting the retrieval target from documents to expert LLMs. Participants are given a discovery set consisting of queries, answers, and log-probabilities from more than one thousand LLMs and are challenged to infer meaningful expertise representations for each model. Given an unseen test query, systems must then rank the LLMs according to their expected performance, providing the first large-scale benchmark for expertise retrieval in agentic AI. --- ### ROTE: Benchmarking Neural Memorization on Complexity-Controlled Symbolic Sequences Authors: Xinye Chen, Stefan Güttel, Mohammad Mozaffari Published: 2026-09-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.31918v1 We introduce ROTE (RollOut Testing of Exact memorization), a benchmarking protocol for evaluating symbolic memorization of neural architectures. We study memorization and the extension of symbolic rules in neural sequence models by using sequences whose complexity is regulated by Lempel--Ziv--Welch (LZW) compression. Under ROTE, each architecture is trained as the same finite-context conditional predictor and is evaluated using teacher-forced one-step prediction as well as closed-loop rollout on the withheld symbols. Following a shared prediction-and-rollout evaluation routine, the benchmark evaluates gated recurrent, minimal recurrent, attention-based, and hybrid recurrent-attention models with their native computational characteristics preserved. Beyond standard predictive metrics, the benchmark reports normalized string distances, training time, memory usage, and parameter count across an LZW-complexity sweep. The study establishes a connection between the complexity of algorithmic sequences and the memorization capacity of neural architectures, revealing the trade-offs involving memorization quality, rollout stability, and computational expense. Our software and reproducible experimental code can be obtained from https://github.com/nla-group/rote. --- ### Facial classification Using Hybrid Quantum Machine Learning Authors: Roshan Babu Bandlapalli, Srinivas V Katakam, Jitendra Chougala, Ravi Kumar Kappagantu, Jayasri Dontabhaktuni Published: 2026-09-25 Categories: cs.CV, quant-ph arXiv: https://arxiv.org/abs/2609.31915v1 Hybrid quantum methods have received limited study for resource-constrained facial biometrics. We present a hybrid quantum-classical facial recognition pipeline designed to run on standard computing hardware. Images undergo gamma correction, contrast enhancement, and principal component analysis before their features are encoded into an eight-qubit variational quantum classifier. Classical image matching then performs recognition. In experiments with 50,000 images, comprising 25,000 faces from CelebA and 25,000 non-face images from CIFAR-10, the method outperformed the reported CPU-trained FaceNet baseline in accuracy and training efficiency. The pipeline was also evaluated on GPU and quantum hardware. In an attendance monitoring deployment at Mahindra University in collaboration with Lloyds Technology Centre, CPU inference took 0.2 to 0.5 seconds per person, and the system remained robust to the use of spectacles. These findings support the feasibility of deploying hybrid quantum methods for facial recognition on existing CPU hardware. --- ### PredRA: Fast Medical Image Translation by Deterministic Component Extraction and Controlled Stochastic Refinement Authors: Jianhai Zhang, Pattarawut Charatpangoon, Donghao Zhang, Bijoy K. Menon, Wu Qiu, M. Ethan MacDonald, Aravind Ganesh Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31912v1 Strongly paired medical image translation contains a substantial component that can be predicted directly from the source. The current reality is that pure deterministic prediction can smooth away fine detail, while generative models can recover detail but may also introduce unnecessary or potentially harmful variation. We propose PredRA, a fast framework that uses the deterministic prediction as a stable reference and further extracts additional deterministic components from the residual during generative refinement, thereby improving fidelity while maintaining perceptual quality. The goal is simple: we view the entire residual-based generative process as an optimization problem and derive a practical solution that recovers useful residual detail through controlled refinement while keeping the prediction close to the paired target. Mechanism studies further show that useful residual information follows structured patterns, but its usefulness is difficult to estimate reliably at the voxel level. We therefore globally control how much of the residual refinement is added to the deterministic prediction, thereby reducing the accumulation of unnecessary uncertainty. PredRA therefore combines deterministic component extraction with controlled stochastic refinement for fast, fidelity-preserving, and perceptually strong medical image translation. We validate the approach across multiple real-world datasets, showing that controlled refinement improves fidelity to the paired target compared with full residual refinement while retaining much of the perceptual benefit of generative modeling. PredRA achieves competitive or superior performance to substantially larger state-of-the-art models with 1.4-11.9x fewer total parameters and 3.1-26.2x fewer trainable parameters, while its 32-step flow sampler requires 31.25x fewer sampling steps than the matched 1000-step DDPM. --- ### Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning Authors: Denis Musinguzi, Andrew Katumba, Prasenjit Mitra Published: 2026-09-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31911v1 Medical report generation has made significant progress with the rise of modern vision-language models and the growing availability of large-scale medical datasets. However, hallucinations remain a major challenge, largely due to the limitations of supervised fine-tuning (SFT), which prioritizes lexical similarity to reference reports rather than clinical correctness. While reinforcement learning has shown strong performance in domains with verifiable rewards such as mathematics and code generation, its application to open-ended medical tasks remains limited. Existing work focuses on evaluating final answers, overlooking the model's reasoning, despite evidence that flawed reasoning can degrade overall performance. In this study, we propose a framework that verifies the model's reasoning process by integrating anatomical regions, bounding boxes, and region-level textual descriptions. We design spatial and factual reward mechanisms to ensure that the model's reasoning is both visually grounded and factually accurate. Starting from Qwen3-VL-8B-Instruct as our base model, we adapt it to the medical domain using supervised fine-tuning, introduce reasoning capability through a cold-start SFT stage, and refine it with reinforcement learning. We find that RL provides performance gains beyond those achievable through SFT alone, and that jointly verifying both reasoning steps and final outputs yields larger improvements than verifying either in isolation. We further identify multiple modes of reward hacking in the RL stage. Finally, the model's structured think traces enhance interpretability, making its outputs easier to audit for clinical use. --- ### Improving Medical Calculation of LLMs with Embedded Coding Authors: Tianshi Ming, Yingying Zhang, Xian Wu Published: 2026-09-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.31908v1 Large Language Models (LLMs) perform well on medical examinations and question-answering benchmarks, but remain unreliable on medical calculation tasks that require exact numerical outputs. These calculations support high-stakes decisions such as medication dosing, organ-function assessment, and prognostic scoring, for which even small errors can have serious clinical consequences. We introduce MedCode, a framework that improves medical calculation by training LLMs to generate embedded executable code. Given a clinical context, the model identifies the relevant calculator, extracts its input variables, and produces a script that delegates arithmetic operations to a deterministic interpreter. Executing the script returns the calculated value together with an explanation and the appropriate unit. We construct supervised fine-tuning (SFT) and preference datasets from the MedCalc benchmark and additionally curate a dataset for calculation tasks in Intensive Care Unit (ICU) scenarios. We further propose weighted Direct Preference Optimization (wDPO), which adaptively emphasizes preference pairs that are difficult for the model to distinguish. Experiments with LLaMA3-8B, Qwen2.5-7B, and Mistral-7B show absolute accuracy gains of 20--30 percentage points, demonstrating the effectiveness of embedded code generation for medical calculation. --- ### EmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity Tasks Authors: Mukul Singh, Mansi Uniyal, Devin Devlin, Wen Xie, Big Thadawasin, Ritam Dutt, Vivian Lai, Hyeonsu B. Kang Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31906v1 Enterprise email agents must combine information retrieval, structured state changes, temporal reasoning, and multi-step coordination. Recent agent benchmarks include productivity tasks, but few center on typed email workflows in a self-contained environment. We introduce EmailBench, a benchmark of 206 email and productivity scenarios across 16 task categories. The benchmark couples a typed email API specification with provider-neutral naming, a deterministic synthetic Enron-inspired corpus, and a scenario suite whose topic selection was informed by aggregate task-intent telemetry from an interactive prototype. Its hybrid evaluation protocol combines 258 executable static assertions with 211 LLM rubrics. We evaluate eight LM configurations on a fixed single-user corpus. The best-performing configuration passes only 33.5% of scenarios despite 99.7% of its tool calls completing without an observed API failure, with pass rates varying substantially across task categories. This gap shows that valid tool execution is not equivalent to task completion. EmailBench provides a self-contained environment for end-to-end email-agent evaluation, with broader tool coverage, multi-persona testing, and repeated-run evaluation as future work areas. --- ### GT-VLA: Target-Conditioned Trace Guidance for Generalizable Robotic Manipulation Authors: Ninghan Zhong, Jing-Chen Peng, Sriram Vishwanath Published: 2026-09-25 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.31904v1 Vision-Language-Action (VLA) models have shown strong performance on robotic manipulation, but they often struggle to generalize to unseen tasks, configurations, and long-horizon settings. A key challenge is that VLAs overfit to training scenes and fail to follow novel language instructions. Off-the-shelf vision-language models (VLMs) often provide stronger generalization, but cannot directly control robot actions. To combine the common sense of VLMs with VLA control, we propose Guided Trace VLA (GT-VLA), a steerable framework that accepts guidance from an external generalist VLM through trace-conditioned action generation. GT-VLA uses a generalist model to identify semantic guidance for the current skill, converts this guidance into a 2D visual trace, and conditions its action policy on the resulting trace-rendered observation. This design separates semantic target acquisition, trace generation, and low-level action execution, allowing high-level guidance to propagate to robot actions. GT-VLA uses a Mixture-of-Experts architecture with skill-specific trace and action modules for robust execution. We evaluate GT-VLA on LIBERO and a physical robot platform, showing improved generalization over recent VLA baselines in both settings. The code and additional supplemental materials are available on our project website at https://ivaniz.github.io/gt-vla/. --- ### Choir: An Open Protocol for Distributed Multi-Agent Autoformalization Authors: Yidi Qi, Melanie Weber Published: 2026-09-25 Categories: cs.AI, cs.CL, cs.LO, cs.MA arXiv: https://arxiv.org/abs/2609.31903v1 AI agents can now formalize entire textbooks and major theorems in proof assistants such as Lean, but current efforts are typically centralized: a single team runs all agents and bears the full computational cost. We introduce Choir, an open protocol for distributed formalization. Choir decomposes a project into tasks that can be completed by independent contributors, each running their own agent with their own LLM subscription, while coordinating entirely through the project's GitHub repository. To support open participation, every contribution is checked by a deterministic gate before merge. Choir supports Lean 4, Isabelle, and Rocq, and is open source and modular, allowing projects to replace individual components or extend the protocol. --- ### Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training Authors: Emre Can Acikgoz, Yang Li, Zeyu Leo Liu, Srijan Bansal, Dilek Hakkani-Tür, Shafiq Joty, Semih Yavuz Published: 2026-09-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.31900v1 Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD) into multi-stage pipelines, yet these stages are typically designed and evaluated in isolation. We show that this composition is consequential: a stage that improves the current model can make the next stage less effective. Through controlled experiments with Qwen3 models on math and science reasoning, we first characterize OPD across nine student-teacher pairs spanning 2x to 53x parameter ratios and show that OPD effectiveness depends on student-teacher compatibility rather than teacher scale alone. The surrounding stages of OPD reshape this compatibility in three ways: (1) A brief SFT warm-up improves subsequent OPD, while an RLVR-strengthened student regresses under distillation from the same teacher. (2) Adapting the teacher with RLVR raises downstream OPD accuracy in proportion to the capability it adds. Following these two interventions, we find that combining teacher adaptation and student warm-up alone raise average OPD accuracy from 29.2\% to 43.8\% (50\% relative improvement) after the same number of distillation steps, with additional preparatory training. (3) At comparable accuracy, OPD leaves a stronger initialization for downstream RLVR than SFT, with a gap that widens as RL compute scales. Our results suggest that each post-training stage should be chosen not only for the capability it adds, but for the learning interface it creates for the next stage. --- ### MAESTRO: a Multimodal Auditory-attention Egocentric Speech-TRacking Open corpus Authors: K M Naimul Hassan, Ali Alavi, Donald S. Williamson Published: 2026-09-25 Categories: eess.AS, cs.HC, cs.LG, cs.SD, q-bio.NC arXiv: https://arxiv.org/abs/2609.31898v1 Humans rely on gaze, head movements, and visual cues to attend to speakers in noisy environments, yet auditory attention decoding (AAD) has been studied primarily using electroencephalography (EEG). We introduce the Multimodal Auditory-attention Egocentric Speech-TRacking Open (MAESTRO) corpus, the first AAD dataset to simultaneously record EEG, eye gaze, pupillometry, egocentric video, and head inertial measurement unit (IMU) data. MAESTRO includes four competing speakers and background noise across multiple signal-to-noise ratio (SNR) conditions, enabling attention decoding under realistic listening scenarios. Through a four-speaker attention decoding benchmark, we show that combining behavioral and physiological signals improves decoding performance over EEG-only approaches, enabling future advances in multimodal auditory attention decoding. These findings open the door to new applications, analyses, and methodological advances in multimodal AAD. The complete dataset is publicly available at https://huggingface.co/datasets/aspire-osu/maestro-eeg-dataset . The official code repository is available at https://github.com/ASPIRE-OSU/MAESTRO . --- ### Context-dependent agent evaluation with orthogonal equilibrium learning Authors: Haorui Ma, Zehua Zang, Jiangmeng Li, Yi Li, Fanjing Xu, Stefan Feuerriegel Published: 2026-09-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.31897v1 Many applications require to evaluate agents under contextual information (e.g., a prompt, task, or user group). We study how to perform such context-dependent agent evaluation from offline feedback. Existing score-based models for this purpose (e.g., Bradley-Terry) impose a transitive preference ordering, which fails to reflect collective preferences when human judgements are heterogeneous. Inspired by social choice theory, we frame evaluation as a contextual game between two players, each selecting a distribution over agents as the strategy to receive greater collective preference than the other. Then, the support of the Nash equilibrium defines a context-specific set of winners. However, learning context-specific equilibria from offline logs is difficult because each context reveals human feedback on only a subset of agents, and, hence, a naive plug-in estimator can therefore be biased. To address these challenges, we propose NashEval, a general framework for robust contextual equilibrium learning. NashEval first constructs debiased estimates of the contextual payoff matrix that characterizes the game. NashEval then learns the context-to-equilibrium mapping with a tailored orthogonal loss, which avoids the need to solve a separate game for each context. We show theoretically that errors in estimating the nuisance functions underlying the payoff matrix affect the risk of the learned equilibrium (i.e., exploitability) only through higher-order terms. Across various experiments, NashEval improves robustness of equilibrium learning and consistently identifies the set of top-performing agents across contexts. --- ### Auditing Quality Filters for Long-Tail Human Data Curation Authors: Rishav Agarwal, Nirshal Chandra Sekar, Anirudh Vemula Published: 2026-09-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31896v1 Robots on construction sites must detect workers who are kneeling or bending, which we call low poses. These workers can be lost from training datasets during automatic labeling. We study a pipeline that detects people, estimates their body joints using NLF, and groups similar poses. Low poses account for only about 2 percent of the retained examples. This low share may partly reflect the pipeline's quality filter, which rejects examples with low detection confidence or uncertain joint estimates. We examine this filtering using four alternative pose clues: bounding-box shape, vertical body span, pose grouping aligned to the scene's vertical direction, and image appearance. All four suggest that low poses are rejected by the filter more often. Separately, controlled simulated scenes show that a person detector fine-tuned on a public construction dataset misses more workers in these poses even when we correct their bounding box height is matched to that of standing workers. These findings suggest that low poses are scarce and hard to find, and we cannot rely on bounding boxes or poses for long-tail human data curation. --- ### CyberWorld: World Models for Sample-Efficient Autonomous Cyber Defense Authors: Ryozo Masukawa, Sanggeon Yun, Raheeb Hassan, Hyunwoo Oh, SungHeon Jeong, Mohsen Imani Published: 2026-09-25 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.31893v1 Deep reinforcement learning has become a prominent approach to autonomous cyber defense. Existing methods are predominantly model-free and consequently require extensive environment interaction. World models provide an alternative by learning predictive dynamics and optimizing policies through imagined trajectories, yielding substantial gains in sample efficiency in robotics and embodied control. Extending this paradigm to cybersecurity raises a fundamental question: what should constitute the "world" in a cyber world model? We introduce CyberWorld, a Dreamer-style world modeling framework that learns latent cyber dynamics from vector, graph, textual, and multimodal representations of the defended network. Across all four scoreable CyberWheel attack strategies, the graph-based CyberWorld variant exceeds a strategy-agnostic control after 3.6k-15.8k environment steps, compared with millions of steps required by model-free PPO. Across representation choices, graph structure provides greater robustness under topology-dependent attacks, while simpler representations remain competitive in overall performance. Among successful runs, the number of episodes required to reach the control remains approximately constant as network size increases from 15 to 100 hosts. These results establish learned cyber dynamics as a sample-efficient and scalable basis for autonomous defense, and identify world representation as a central design axis for robustness and scalability. --- ### NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech Authors: Qiaolin Wang, Pedro Sandoval-Segura, Anunaya Joshi, Edvardas Jurkonis, Jake Downie Published: 2026-09-25 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.31892v1 While modern text-to-speech (TTS) systems generate highly natural speech and support inline non-verbal vocalization (NVV) tags, accurate control over these events remains challenging. A key gap is the lack of established post-training methods for non-verbal control in continuous autoregressive flow-matching TTS. To this end, we present NVAlign, a direct-gradient post-training framework for NVV tag-following in this architecture. We first perform supervised fine-tuning (SFT) of TTS models and an NVV-aware automatic speech recognition (NV-ASR) model on NVV-annotated speech, then freeze the NV-ASR model to serve as the reward model for post-training. A two-step gradient surrogate enables efficient reward backpropagation through the flow-matching sampler to jointly update the autoregressive backbone and acoustic flow head. Fidelity penalties and reference-velocity regularization help preserve speaker similarity and speech quality. Results from NVV-SuperBench and human listening evaluations show that NVAlign improves tag-following accuracy over SFT and Flow-GRPO baselines. These findings demonstrate that direct reward-gradient optimization can improve non-verbal control in continuous autoregressive flow-matching TTS. Audio samples are available at https://nvalign.github.io/. --- ### FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization Authors: Arundeep Chinta, Lucas Vinh Tran, Jay Katukuri Published: 2026-09-25 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.31890v1 Content personalization systems in financial services must ensure fair exposure across diverse offerings-a requirement driven by contractual obligations and the need to prevent "rich-get-richer" dynamics where content with high click-through rate (CTR) dominates while other relevant products receive minimal visibility. Share of Voice (SOV) constraints, which guarantee each content category a target fraction of top-position exposure, address this by promoting product diversity and balanced user discovery. While re-ranking layers atop CTR models are common in practice, we propose two key novelties: (1) framing SOV-constrained ranking as a deep reinforcement learning problem analogous to constrained trade execution in algorithmic finance, and (2) explicitly incorporating CTR prediction uncertainty into the agent's state space and policy design-enabling larger ranking adjustments for high-uncertainty predictions where deviation from CTR-optimal ordering is less costly. We introduce FARE (Fair Ranking Executor), a modular uncertainty-aware execution layer that translates any black-box CTR model's predictions into SOV-fair rankings without retraining the underlying model. Our uncertainty-weighted proportional control policy (FARE-PC) and learned neural policies (FARE-ES, FARE-PPO) demonstrate that uncertainty-aware approaches can substantially reduce SOV deviation from fairness targets while minimizing engagement loss, with gradient-free evolution strategies outperforming policy gradient methods on synthetic data and the ordering reversing on KuaiRand-Pure. --- ### Knowledge-Driven XRD Phase Identification via Multi-View Retrieval and Explanation Authors: Doaa Mohamed, Markus Stricker Published: 2026-09-25 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2609.31888v1 X-ray diffraction (XRD) is a experimental technique for determining the phase composition and structure of crystalline materials. However, interpreting XRD patterns is challenging, particularly in high-throughput materials discovery, where many novel materials may need to be characterized and no reference patterns are available. Consequently, machine learning is increasingly used to accelerate and automate the analysis while reducing errors associated with human interpretation. We propose a multi-decision framework for XRD phase analysis that integrates representation learning, similarity-based retrieval, and explainable decision support within a unified reference database. A convolutional autoencoder learns compact latent representations of XRD patterns that preserve structural similarity while remaining robust to variations arising from experimental noise and measurement conditions. By integrating multiple decision pathways within a shared latent space, the framework moves beyond single-label prediction toward ranked and interpretable phase analysis that mirrors expert practice. During inference, complementary decision mechanisms are applied, including latent-space classification and retrieval, explanation-guided similarity using Integrated Gradients, and composition-based similarity search. These mechanisms generate ranked candidate phase lists that are aggregated into a final prediction with an associated confidence score. Experiments on synthetic datasets demonstrate strong predictive performance, achieving 98.85\,\% accuracy for crystal system classification and 95.82\,\% accuracy for space group prediction on the test set, while maintaining robustness under realistic perturbations. The framework supports reliable, analyst-friendly identification of crystal phases and structures in high-throughput and exploratory materials discovery settings. ---