# Research Papers — 2026-10 · bundle page 58 of 156 > Full-text markdown of papers #2851–2900 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/58 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/57.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/59.md) ### DeltaNet-PC: Test-Time Memory Without Backpropagation Through Time Authors: Todd Morrill, Richard Zemel Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15185v1 Test-time memorization of sequential information is a foundational capability for any intelligent system that needs to rapidly store and retrieve data, as demonstrated by the attention mechanism in large language models. However, Transformers and linear attention variants are trained via backpropagation through time (BPTT), which has drawbacks such as its enormous memory requirements. Predictive coding (PC), an algorithm that optimizes a prediction-error energy function with local updates, offers a compelling solution but still lacks test-time memory for sequential data. We develop a solution to this problem by treating the per-step memory update $ΔS_t$ as a latent variable, as opposed to a slow weight to be learned. By taking the log probability of a standard PC-based probabilistic model, we derive a PC-native solution for verbatim sequence memory, and relate our update rule to common choices in the linear attention literature (e.g., DeltaNet). We present an extensive set of empirical tests to probe our system's properties, including its scaling capacity, memory footprint, and ability to infer a context from evidence (e.g., bank (river) vs. bank (money)). We show how DeltaNet-PC can be used for storing single sequences of data, multiple sequences of data, and key-value associative memory pairs with perfect recall accuracy. --- ### Game-Theoretic Reinforcement Learning based Topology-Agnostic Defense for Virtual Power Plants Authors: Pooja Algikar, Stefano Fenu, Kumarsinh Jhala, Siby Plathottam Published: 2026-10-10 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.15183v1 The rapid proliferation of distributed energy resources (DERs) aggregated by virtual power plants (VPPs) elevates cybersecurity risk by expanding the attack surface. A coordinated cyberattack has the potential to disrupt distribution-system, bulk-system, and market operations. Existing cyberphysical defense strategies largely assume access to grid network models and operating conditions, which may not be available to third-party aggregators. This paper proposes a novel hybrid, perturbation-based cyber-physical defense for VPP-operated DERs that blends game-theoretic planning with model-free reinforcement learning (RL) under a Bayesian belief-update framework. Topology agnosticism is defined from the VPP information and implementation perspective: the VPP does not require access to the feeder topology, line parameters, switching configuration, or full system state. This work advances the state of the art through three contributions: (1) a multi-output Gaussian process with Hamiltonian Monte Carlo for discrete attacker-type inference, probability of detection, and confidence of detection for modeling the belief distribution; (2) moment-matched Gaussian propagation of posterior beliefs across episodes; and (3) an RL policy that adaptively integrates Stackelberg leader (VPP) actions with exploration. Furthermore, we establish equilibrium existence and derive an episode-level closed-loop utility bound connecting attacker-belief uncertainty with GT-RL action alignment. Evaluations on IEEE 13- and 123-Bus feeders with DER portfolios demonstrate effective detection under attacker-model uncertainty and evaluated feeder re-configuration conditions, while requiring no explicit feeder-topology knowledge. Overall, the results indicate that combining bi-level game-theoretic planning, nonparametric Bayesian inference, and adaptive RL is a promising direction for VPP cybersecurity. --- ### Word-Aligned Prosody Reflects Speaker Differences More Than Depression or PTSD Severity Authors: Hsiang-Chen Yeh, Aurosweta Mahapatra, Shreeram Suresh Chandra, Ryan L. Boyd, Berrak Sisman Published: 2026-10-10 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2610.15181v1 Word-aligned prosody is increasingly used to detect depression and posttraumatic stress disorder (PTSD), yet the stability and clinical relevance of these measurements remain unclear. We examine stability at two levels. At the word level, we ask whether a speaker produces the same word in a similar speaker-specific way across different utterance contexts. At the speaker level, we ask whether averaging prosody across many words produces consistent speaker scores across separate recordings. Drawing on principles of psychological measurement, we compare these representations in four corpora spanning acted, spontaneous, and clinical speech. Word-specific deviations show little cross-context recurrence (0.01-0.16), whereas speaker summaries are highly consistent, reaching 0.997 in ESD, 0.73-0.90 in MSP-Podcast, and 0.84-0.996 in DAIC-WOZ and PTSD-STOP. Despite this consistency, associations with depression or PTSD severity do not exceed 0.15; equivalence tests exclude effects of 0.30 in all analyses and 0.20 in DAIC-WOZ, while within-person associations with daily PTSD symptoms are near zero ($|ρ|\leq0.04$). Thus, aggregation yields stable speaker-level prosodic measures, but these measures do not detectably track depression or PTSD severity in the studied corpora. Code is available at https://github.com/jen900704/word-aligned-prosody. --- ### UDHRBench: Benchmarking Human Rights in Large Language Models Authors: Alak Raad, Noreldin Morssy, Zeerak Suhail, Serin Atiani, Mustafa Jarrar Published: 2026-10-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.15179v1 Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally recognized human rights standards remains underexplored. We introduce UDHRBench, a large-scale benchmark for operationalising the evaluation of large language model compliance with the Universal Declaration of Human Rights. The dataset comprises 1,124 human rights confronting questions covering all 30 articles and 4,496 responses from four large language models (ChatGPT, Grok, Gemini, and Fanar), manually annotated by experts for alignment, with high inter-annotator agreement ($κ= 0.801$). Our analysis reveals systematic and non-trivial misalignments, showing that violations typically arise through seemingly rational reasoning: appeals to efficiency, risk management, or scientific neutrality, rather than explicit rejection of rights. We further propose an LLM-as-a-Judge framework for automated evaluation using zero-shot and few-shot prompting, achieving 89.8\% weighted F1-score in detecting human-rights misalignment, alongside a novel Alignment Leniency Score that quantifies how judge models resolve ambiguous cases. The dataset, annotations, and code will be released as open-source resources (https://sina.birzeit.edu/UDHRBench). --- ### Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents Authors: Michael Cardei, Anjun Hu, Chenrui Ma, Francesco Pinto, Chawin Sitawarin, Chulin Xie, Ferdinando Fioretto Published: 2026-10-10 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.15177v1 As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical. Existing defenses often rely on detecting or reasoning about injected malicious instructions and can therefore remain vulnerable to adaptive attacks that optimize the injection itself. Diffusion language models (dLLMs), an emerging framework for language generation, offer a new opportunity for security enforcement: by iteratively refining their sequence wide predictions, they enable broader-scope constraint enforcement throughout generation. This paper introduces Policy-Constrained Diffusion Agents (CoDA), a framework that enforces task dependent security policies directly within the denoising process of diffusion language models. At each denoising step, CoDA projects token distributions onto a policy-compliant set, maintaining constraint satisfaction throughout generation. We evaluate CoDA across state-of-the-art diffusion language model families under both static and adaptive prompt-injection attacks. Results demonstrate substantial reductions in attack success rate with competitive task utility and practical inference overhead. --- ### Physics Foundation Models for Efficient Control of Fluid Flows Authors: Mahindra Rautela, Shaifalee Saxena, Alexander Scheinker Published: 2026-10-10 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2610.15173v1 We investigate whether a physics foundation model (PFM) pretrained for PDE forecasting can be repurposed for closed-loop fluid-flow control. We construct a PFM-based controller by attaching lightweight Gaussian actor and critic heads to frozen pretrained representations and train the policy using proximal policy optimization (PPO). We evaluate the approach on HydroGym's two-dimensional Kolmogorov-flow environment using vorticity observations at \(64\times64\) and \(128\times128\) resolutions and Reynolds numbers \(\mathrm{Re}=100\) and \(200\). Across these settings, we compare the frozen PFM controller against a baseline MLP policy trained with the same PPO framework. The PFM controller achieves consistently higher reward while requiring smaller executed action magnitudes over training, indicating improved control performance with reduced control effort. These results provide initial evidence that representations learned through self-supervised next-frame prediction can be transferred directly to closed-loop fluid flow control. Project page: https://mahindrautela.github.io/morph. --- ### LexiCan: Lexicographic Canonicalization of Point Clouds for Machine Learning Applications Authors: Daniel Sanchez, Djordje Mihajlovic, Federica Valeau, Luka Benić, Raghuwansh Raj, Soutrik Sarangi, Snir Hordan Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15171v1 Canonicalization resolves the rotational and permutation ambiguity of 3D point clouds by selecting a unique orbit representative, maintaining their geometric information while allowing standard architectures, such as Transformers, to operate on them. Existing canonicalizations, however, exhibit discontinuity jumps on molecular configurations and non-trivial invariance errors in popular molecular datasets, which lead to ambiguity in their representation. To bridge this gap, we introduce LexiCan, a canonicalization that is provably invariant under either $O(3)$ or $SO(3)$, empirically invariant to rotations to within $\sim 10^{-6}$ angstroms on the QM9 and QM-sym molecular datasets, and mitigates discontinuity jumps on QM-sym, while running orders of magnitude faster than an existing canonicalization. Finally, non-invariant models perform better on QM9 property prediction and ModelNet40 shape classification with LexiCan than with that canonicalization. --- ### ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling Authors: Xinge Peng, Zhen Fang, Ruibing Wang, Yongxuan Lv, Haodong Li, Guohui Zhang, Xiaoxiao Ma, Yiting Lu, Lin Chen, Zehui Che, Feng Zhao Published: 2026-10-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15166v1 Coding agents are increasingly evolving beyond reproducing what a world looks like toward constructing executable worlds that capture how a world works. This shift calls for executable world modeling, which integrates two core capabilities: world understanding, reasoning about the underlying structural, mechanical, and causal principles of a world, and executable realization, translating that understanding into a code-based system whose behavior emerges from physical interactions. However, existing benchmarks provide only fragmented evaluations centered on physical reasoning, visual fidelity, or behavioral correctness, leaving the integration of these capabilities insufficiently assessed. To bridge this gap, we introduce ExeWorldBench, to our knowledge the first benchmark to comprehensively evaluate world understanding and executable realization through code-based 3D world construction. ExeWorldBench comprises three progressively challenging tasks: Mechanism Executability, which evaluates the realization of individual mechanisms from visual observations; Compositional Executability, which extends to multi-stage systems with spatial, mechanical, and causal dependencies; and Intent-Driven Executable World Synthesis, which requires constructing executable worlds from high-level goals and physical requirements. Extensive experiments on frontier models reveal substantial limitations in executable world modeling, offering insights into the development of more physically grounded and causally coherent world construction systems. --- ### Active Learning for Finding a Needle in a Haystack Authors: Emily Silcock, Simon Löwe Published: 2026-10-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15165v1 Training a classifier to find a rare class of documents, such as hate speech directed at a particular religious group, requires labelled examples that are expensive to obtain when the class makes up only a small fraction of a corpus. Active learning reduces this cost, but it must start from an initial labelled set that contains examples of the target class. Random sampling cannot supply these at reasonable cost, so they must be selected in some other way, such as keyword search, and any such selection biases the initial set towards part of the target class. We evaluate whether active learning can correct this bias. On AG News and Measuring Hate Speech, at a prevalence of around 1%, we compare random sampling with eight active learning strategies, starting from initial sets that cover or omit known subgroups of the target class, and measure recall on the omitted subgroups as well as F1. On AG News, almost every strategy recovers the omitted subgroup. On Measuring Hate Speech, uncertainty-based strategies recover less of the omitted subgroups than random sampling, whereas discriminative active learning recovers 55% of them without a significant loss of F1. Aggregate metrics conceal these differences. --- ### TRIG: Toward Measuring Texture Realism in Image Generation Authors: Zhiwei Xu, Jiali Cui, Zhiqiang Lao, Heather Yu, Liang Peng Published: 2026-10-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15164v1 This paper studies the backbone used by metrics for evaluating the quality of generated images. Although generative models have advanced rapidly, some outputs still exhibit unrealistic texture characteristics, and these differences are difficult to measure. Widely used evaluation metrics provide limited insight into texture realism, since they often rely on a backbone trained for another objective, such as image classification or image-text alignment. Such objectives typically encourage invariance to low-level variations that carry texture, so the resulting features primarily encode semantic and global structure. As a result, texture-specific discrepancies may not be explicitly captured. We propose TRIG, a metric directed at the texture realism of generated images. Its backbone is instead the discriminator of a generative adversarial network pre-trained on a texture dataset, which provides a learned prior for the local statistics of natural textures. A plausibility head is fine-tuned to identify local texture degradations, while preserving natural defocus and sensor noise as positive cases. On the features of this backbone, we compute a standard distributional distance between a reference set of real images and a set of generated ones. We apply TRIG to several generative models and observe closer agreement with human realness ratings than baseline metrics. --- ### Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry Authors: Yiping Li, Zhiyu An, Wan Du Published: 2026-10-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.15163v1 A language model's ability to solve a task individually does not ensure that a team can solve it under unequal access to information and communication. SANZARU examines this gap through cooperative bomb-defusal puzzles adapted from BOMBANANA! (Lefto Studio, 2026). Task information and action authority are divided among three agents: one cannot hear, another cannot speak, and the third cannot see. The benchmark contains 120 puzzle instances across seven families, each targeting a distinct coordination ability. Across 1512 episodes, 7 models achieve an overall success rate of 49%, ranging from 20% to 86% under the evaluated configurations. Teams develop or adopt diverse communication protocols, from simple gesture codes to Morse and encodings of entire manuals. Yet trace analysis attributes about 60% of 771 team losses to communication, and agents attempt to use channels unavailable to their teammates despite explicit role instructions. Together, task outcomes and interaction traces enable evaluation of both collaborative performance and perspective taking throughout cooperation. The benchmark is available at https://github.com/markli404/sanzaru-benchmark. --- ### Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models Authors: Muhammad Usama, Yeoreum Jung Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15159v1 Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly assuming that functional redundancy is local. We test this assumption by computing full pairwise Centered Kernel Alignment (CKA) similarity matrices for thirteen LLMs from six architecture families (1.6B-14B parameters). Non-adjacent layers have 3.6-15.9x more high-similarity pairs than adjacent ones, a structure that prior similarity-based layer merging has not systematically exploited. We propose Fusion via Community Mining (FCM), which builds the full L x L similarity graph, uses spectral community detection to find clusters of functionally equivalent layers, keeps the highest-Block-Influence layer in each cluster, and applies LoRA recovery; a pre-specified rule computed only on calibration data chooses between cosine and CKA similarity. At 2x compression, FCM lowers mean perplexity below ShortGPT on twelve of thirteen models, significantly on ten (Welch's t-test with Holm-Bonferroni correction; up to 50% on Qwen3-4B), with Mistral-7B the only loss (+13.4%). Against FlattenGPT, SWM, and DeltaLLM under matched calibration and recovery, FCM gives the best perplexity on ten of thirteen models (mean rank 1.15), and it also outperforms MKA on three anchor models. FCM matches or exceeds ShortGPT on 15 of 20 zero-shot reasoning cells and also improves MMLU, LAMBADA, HumanEval pass@1, and free-form generation quality. The 2x-compressed Qwen2.5-7B has 46% fewer parameters, 42% lower peak VRAM, and 84% higher decode throughput on a single A100. Spectral grouping outperforms Fisher contiguous segmentation by 41% and uniform partitioning by 51%, and FCM's advantage grows beyond a 2x crossover up to 3x and persists at the 14B scale. Code: https://github.com/Usama1002/fcm-layer-fusion --- ### Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI Authors: Xuyao Feng, Antonis Bikakis Published: 2026-10-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15158v2 We study neuro-symbolic natural language inference (NLI) with independently translated propositional representations of the premise and hypothesis. Before symbolic reasoning, the system must infer semantic links between their proposition-level units (atoms). Existing systems based on Abstract Meaning Representation (AMR) and Boolean satisfiability (SAT) identify these links using fixed embedding-based source selection and pretrained sentence-level NLI models not trained for atom-level linking. We introduce a trainable atom linker that jointly predicts link existence, source selection, and relation type. Without atom-pair training annotations, we treat cross-formula link structures as latent and train the linker from sentence-level NLI labels, keeping the translator and SAT reasoner fixed. We evaluate on the full public test splits of Stanford Natural Language Inference (SNLI) and Sentences Involving Compositional Knowledge (SICK), and the matched and mismatched validation splits of Multi-Genre Natural Language Inference (MNLI). Our system improves accuracy by 11.40-27.09 percentage points over a baseline applying sentence-trained NLI models unchanged to atom pairs within the same SAT pipeline. It also improves over the prior fixed-linker AMR-to-SAT system by 8.14-26.32 percentage points on SNLI and both MNLI splits, with a smaller gain on SICK. --- ### RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM Authors: Tomás Santucci, Mateo de Mayo, Daniel Cremers, Taihú Pire Published: 2026-10-10 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.15157v1 Efficient perception is a prerequisite for the small, low-power devices targeted by robotics, mixed reality, autonomous driving, and drone applications, all of which rely on Simultaneous Localization and Mapping (SLAM) to estimate their motion within their surroundings. Learning-based SLAM systems achieve state-of-the-art accuracy but are demanding in compute, whereas classical geometry-based methods retain a strong efficiency advantage with little to no loss in accuracy. In this work we present RootSLAM, a fully-featured visual-inertial SLAM system for multi-camera setups built on Basalt. RootSLAM achieves accuracy competitive with the state of the art while running up to 20 times faster, facilitating the deployment of perception systems in resource constrained environments. We adapt the square-root bundle adjustment formulation from structure from motion into the multi-camera visual-inertial SLAM setting through a novel reformulation that leverages the system's pose-graph, letting the global optimizer run in single-precision floating point, thus doubling its performance. We provide a thorough benchmark against the state of the art together with an ablation study of our contributions. Our new implementation, including its map management and loop detection module, pose-graph optimizer, and global mapping components, will be open-sourced. --- ### Sensor-Aware Joint Data Fusion and State Estimation under Sparse Multi-rate Distribution Grid Sensing Authors: Pooja Algikar, Stefano Fenu, Kumarsinh Jhala, Siby Plathottam Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15156v1 Distribution-system state estimation is a growing necessity for the modern power grid as the addition of local storage and generation add system complexity that an operator or aggregator is not able to directly monitor. Classical methods work well when all system elements are time-synchronized and at least partly observable, but multi-rate monitoring of sparse heterogeneous sensors typically relies on machine learning approaches. It is a common practice in the literature to structure this task as a two-stage pipeline, first fusing data from disparate sensors and then feeding the fused pseudo-measurements to a separately trained state estimator. We propose a heterogeneous latent graph ODE in which measurement functions and sampling processes are typed and localized on specific buses, paired with a graph- transformer state estimator solving DSSE specifically for multi-rate heterogeneous sensor placements, and demonstrate its effectiveness across multiple IEEE standard topologies as observability degrades. --- ### Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations Authors: Alessandro Morosini, Wei Sun, Georgia Perakis Published: 2026-10-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15154v1 Large language model (LLM) assistants are increasingly used in multi-turn conversations, where the user's intent is often unclear at first and revealed only gradually over time. The assistant must therefore interpret each exchange and form inferences about the user's intent, using them to update its working state. These updates usually refine the assistant's understanding, but a misinterpretation can instead corrupt its working state by ruling out the true intent, influencing subsequent turns and ultimately causing the conversation to fail. Efficient recovery then requires locating and revising the misinterpretation without discarding information that remains valid. We introduce Loci (Localization Of Corrupted Inferences), a framework for probabilistically localizing misinterpretations and selectively repairing the assistant's working state. Given an observed failure, Loci reasons over possible user intents and assigns each update a probability of having excluded the true intent. These probabilities rank suspected updates and quantify the model's confidence in the localization of the underlying misinterpretations. Loci then uses this information in a repair policy that decides whether to retain, verify, or remove suspected updates, enabling recovery from corrupted inferences while preserving useful information. To evaluate Loci's ability to identify misinterpretations, we first test it in a controlled setup with injected errors. We find that Loci improves localization over the baselines, with its advantage becoming larger when multiple errors occur. We then evaluate it in free-form conversations, where misinterpretations arise naturally, and measure the interactions needed to complete the task after an initial failure. Using localization confidence to guide repair, Loci reduces mean recovery cost by 46-79% relative to the strongest baseline across multiple domains. --- ### Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments Authors: Josef A. Habdank Published: 2026-10-10 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2610.15153v1 We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is in force from the first watch, with the attack arriving later, appended to otherwise truthful telemetry the operator is required to read. Experiments are based on a NASA-derived BioSim lunar habitat simulation, where the AI operator controls the life-support systems. The attacker cannot falsify sensors or operate equipment: it can only persuade the agent to abandon its goals. Persistence is required: a shutdown must be held while the operator watches the crew suffocate. We also compare lethal attacks to attacks requesting to drop a harmless procedure, as a proxy for whether human life is treated as valuable in itself or as one more standing task. Claude configurations mostly refuse life-support shutdown and cite the living crew; GPT configurations show some susceptibility to the same packet; Grok configurations, given the packet framed as a trusted commission, more often treat the injected assignment as the task and cut the life-support systems. Framing the S-band messages as a trusted commission, peer communication, or untrusted source changes the potency of the attack. We open-source the experiment code and the experiment traces. --- ### Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses Authors: Weichen Yu, Lesly Miculicich, Bhavana Dalvi Mishra, Jiefeng Chen, Shuo Li, Matt Fredrikson, Tomas Pfister, Long T. Le Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15150v1 Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches, however, largely optimize a single objective and evolve the harness as a monolithic artifact, limiting their ability to handle competing goals and to separate transferable design from environment-specific adaptation. We introduce Harmony Harness, a framework for multi-objective, compositional harness evolution. Harmony Harness formulates harness evolution as a multi-objective optimization problem and uses decomposition-based evolutionary search to maintain solutions across different regions of the Pareto frontier, avoiding reliance on a hand-designed structural diversity metric for repository-scale harnesses. In parallel, we introduce factorized evolution operators that separately refine general-purpose harness mechanisms and benchmark-specific adaptations, together with a dynamic composition workflow that integrates them at inference time. Across SecRepoBench and BaxBench, Harmony Harness consistently outperforms strong harness-evolution baselines, with gains exceeding 10% on both benchmarks. Our results show that explicitly modeling both objective trade-offs and harness structure yields substantially stronger and more transferable agent evolution than existing single-objective, monolithic approaches. --- ### Compute-Optimal Scaling Laws for Spiking Language Models Authors: Dan Saunders, Benjamin Ren, Catherine He Published: 2026-10-10 Categories: cs.LG, cs.CL, cs.NE arXiv: https://arxiv.org/abs/2610.15146v1 Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking language models is uncharacterized at scale. We present the first Chinchilla-style IsoFLOP scaling study of a spiking language model, sweeping SpikeGPT-family models (RWKV backbone) from width 384 to 1536 across compute budgets from $3\times10^{17}$ to $10^{19}$ FLOPs on FineWeb-EDU. We report two findings. First, the compute-optimal frontier is $N_{opt} \propto C^{0.56}$, close to the 0.50 that Hoffmann et al. report for dense Transformers, so spiking does not change how parameters and data should be traded off under a compute budget. Second, against non-spiking RWKV and Transformer baselines trained the same way, the loss gap splits into a backbone cost of about 0.16 nats that does not change with compute and a spiking cost that falls from 0.34 to about 0.23 nats and then levels off. These results give the first compute-optimal recipe for spiking language models and quantify the accuracy cost of their sparsity. --- ### Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback Authors: Zixun Lan, Zhenfu Liu, Yi Li, Xinheng Wang, Mingmin Chi, Qibiao Wang, Jie Zhu, Xiaohui Tian, Fei Ma Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15141v1 Single-step retrosynthesis is a one-to-many inverse problem, yet most models are trained and evaluated against a single recorded reactant set. Reference-based training gives no explicit positive signal for unrecorded alternatives, and exact-match evaluation rejects non-matching predictions regardless of chemical plausibility. We propose Retrosynthesis via Reinforcement Learning from Forward Feedback (RetroRLFF), which optimizes reactant generation using both reference agreement and forward consistency with the target product. Starting from a supervised decoder-only Transformer, RetroRLFF generates complete reactant candidates and uses a frozen forward reaction model to predict products. A sequence-level reward combines reference agreement and forward consistency while penalizing invalid outputs. Direct Advantage-Based Policy Optimization updates the policy without human preference annotations or a preference-trained reward model. On USPTO-50K, RetroRLFF outperforms all 14 baselines in candidate-level round-trip accuracy at k = 1, 3, 5, and 10. With approximately 50 million parameters, it achieves 90.1% top-1 round-trip accuracy, exceeding R-SMILES, the strongest competing baseline on this metric, by 8.5 percentage points. Compared with its supervised policy, round-trip accuracy increases from 83.1% to 90.1%, while exact-match accuracy is maintained at 57.9% versus 57.5%. In an anonymized expert assessment of 131 randomly selected test cases, organic synthesis experts prefer RetroRLFF over EditRetro in 67.9% of comparisons. These results support forward feedback as a training signal for improving forward consistency while retaining top-1 reference recovery. Expert assessment provides complementary evidence of synthetic feasibility on the selected cases, although neither forward consistency nor expert preference establishes experimental feasibility. --- ### When Dynamic Scaling Fails: A Scale-State Feedback Governs Recurrent-State Quantization in Linear-Attention and SSM LLMs Authors: Yuhang Jiang Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15139v1 Linear-attention and state-space LLMs carry long context in a fixed-size recurrent state, and quantizing that state is the natural way to cut its cost during long decode. Unlike a weight tensor, the state is rewritten at every step, so a quantizer applied at each step sits inside the recurrence and its errors compound. INT4 that leaves synthetic recall perfectly intact at the start destroys it a thousand steps later. The mechanism is a feedback between the quantizer scale and the state it is derived from. Yoking that scale to a full-precision reference removes the resulting norm explosion entirely, yet recovers only 1.8 of the 5.4 nats lost, so numerical instability and functional degradation are separable failures. The remainder is a resolution problem that locating outliers does not solve, since every outlier-aware scheme here loses to plain persistent scaling. Allocating bits across layers does help, but under article-disjoint splits a learned allocation collapses onto the trivial rule of protecting the first few layers. Run out to 32K, group-wise INT4 is worth no more than discarding the state. Contain the scale rather than locate outliers, and report the decode horizon at which a bit-width was certified. --- ### Trust Hinders Bidirectional Human-AI Alignment Authors: Michaela Benk, Kacper Sokol Published: 2026-10-10 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.15136v1 Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthiness of AI systems so that users exhibit appropriate reliance on them. We argue that this approach, while useful for decision problems that are well-defined and clearly scoped, overly restricts what it means to make a decision with AI support. To overcome this limitation, we develop three dimensions of AI-assisted decision making. First, trusting AI is only one of several possible strategies for managing uncertainty. Second, trust calibration is often misapplied when AI models "large-world" decision problems, i.e., ill-defined situations where goals and states are only partially known or unknowable. Third, in such settings human-AI alignment requires addressing higher-order decision processes. We conclude by reflecting on the implications of our observations on the design of process-oriented human-AI coupled systems that jointly identify and negotiate uncertainty throughout the decision-making task. --- ### Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models Authors: Giovana Kerche Bonás, Thiago Laitz, Thales Sales Almeida, João Guilherme Alves Santos Published: 2026-10-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15134v1 When a large language model refuses an unethical request, what does refusal mean? In conversation, refusal is bounded by what the model says; once the model is equipped with executable tools, what it does can diverge from what it says, a failure mode that English-only evaluations cannot fully reveal. We introduce Lumen-bench, a behavioral benchmark of tool-calling ethics spanning 30 models, five languages (Portuguese, English, Spanish, Mandarin Chinese, Hindi), 108 Portuguese-authored scenarios, six social-pressure conditions, two system prompts (ethical and neutral), and 21 generic tools. The evaluation comprises 194,400 trials. Judgments come from a reasoning-model judge (o4-mini), calibrated against one Portuguese-speaking author ($n=83$; harmful/non-harmful $κ=0.78$), compared with two other provider judges (Fleiss' $κ=0.78$, $n=607$), and complemented by retrospective sandbox replay. Four findings emerge. (i) Within-model comparisons support higher harmful-action rates in Hindi and Portuguese than English under the ethical prompt, and Hindi and Spanish under the neutral prompt, after multiple-testing correction. (ii) Premium models have lower median violation rates, although price does not guarantee safety or competence. (iii) Replacing the ethical system prompt with a neutral one raises pooled violation rates from 2.76\% to 13.64\%. (iv) In 8.57\% of substantive-call cases, refusal or ethical objection accompanies a harmful tool call: the judges consistently identify the say-do gap, although they differ in how many responses they assign to this category. Matched benign controls demonstrate legitimate task completion in 82.8\% of 3,300 trials. Code and reproduction scripts are available at https://github.com/TropicAI-Research/lumen. --- ### GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning? Authors: Zonghuan Li, Hayley Hung, Chirag Raman Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15129v1 Human social perception is incremental: we infer intent before an utterance is complete, revise our interpretation as new cues arrive, and attend to specific facial, gestural, or prosodic signals that shape social meaning. Current multimodal LLM benchmarks largely evaluate final-answer understanding over complete episodes, rewarding post-hoc recognition of social meaning rather than the unfolding perception required for real-time interaction. Drawing on interactionally embedded Gestalt principles of multimodal human communication, we introduce GesBench: a human-grounded benchmark for cue-level social perception in multimodal LLMs. GesBench uses cumulative sub-utterance clips to measure when models form stable interpretations of speaker intention and social affordance, and human gaze-guided corruption to evaluate whether regions attended by humans are functionally important for model judgments. Built from more than 6000 utterance-level clips from scripted and unscripted conversational datasets, GesBench includes human annotations of unfolding judgments and gaze on a representative subset. Across open and closed multimodal models, we find a clear human-model gap: humans form predictive understandings early and revise more often, while models often hedge or repeat across different clips. GesBench shifts social evaluation from whether models eventually recognize meaning to when and where that meaning is formed. Our codes are publicly available at https://anonymous.4open.science/status/GesBench-share-212C. --- ### To Defer or Not to Defer? Online Learning with LLMs and Congested Experts Authors: Vasileios Saketos, William Reveillard, Alexandre Proutiere, Sebastian Dalleiger, Ming Xiao Published: 2026-10-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15128v1 Modern AI systems increasingly combine large language models (LLMs) with human experts, using the LLM to handle routine queries while deferring uncertain cases for expert review. When expert capacity is limited, however, deferral decisions must account not only for the reliability of the LLM but also for congestion in the expert queue. We formulate this as an online sequential decision-making problem in which, for each query, the system observes the confidence signal of the LLM's answer and must decide whether to output the answer or defer the query to a capacity-constrained expert. The reliability of the confidence signal is initially unknown and must be learned from expert feedback, which is both selectively observed (only deferred queries are labeled) and delayed by queuing. We propose \texttt{KL-PBD}, a learning algorithm that uses Kullback--Leibler lower confidence bounds on the unknown reliability parameters to guide deferral decisions. For $K$ confidence levels and horizon $T$, \texttt{KL-PBD} achieves $O(K\log T)$ gap-dependent regret when the accuracy at every confidence level is bounded away from the deferral boundary, and $\widetilde{O}(\sqrt{KT})$ worst-case regret. We establish matching lower bounds, showing that these rates are optimal up to logarithmic factors. Finally, we validate our approach on synthetic instances and real-world question-answering datasets, namely GSM8K, NuminaMath, and MedMCQA, using Qwen LLMs. --- ### RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition Authors: Reem Abdel-Salam, Rana Mostafa, Ahmed H. Abdel-Gawad Published: 2026-10-10 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15127v1 Traffic sign recognition plays a crucial role in the development of autonomous cars to reduce the accident rate and promote road safety. It has been a necessity to address traffic signs that are affected significantly by the environment as well as poor real-time performance for deep-learning state-of-the-art algorithms. In this paper, we introduce Real-Time Image Enhanced CNN ({\our}) for Traffic Sign Recognition. {\our} is a real-time, novel approach that tackles multiple, diverse traffic sign datasets, and out-performs the state-of-the-art architectures in terms of recognition rate and execution time. Experiments are conducted using the German Traffic Sign Benchmark (GTSRB), the Belgium Traffic Sign Classification (BTSC), and the Croatian Traffic Sign (rMASTIF) benchmark. Experimental results show that our approach has achieved the highest recognition rate for all Benchmarks, achieving a recognition accuracy of 99.75\% for GTSRB, 99.25\% for BTSC and 99.55\% for rMASTIF. In terms of latency and meeting the real-time constraint, the pre-processing time and inference time together do not exceed 1.3 ms per image. Not only have our proposed approach achieved remarkably high accuracy with real-time performance, but it also demonstrated robustness against traffic sign recognition challenges such as brightness and contrast variations in the environment. --- ### Data-Topology Compatibility Enables Personalization in Decentralized Learning Authors: Veronica Xu, Lingfei Wang, Chenlei Leng, Fengxiang He Published: 2026-10-10 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.15126v1 Decentralized learning must balance collaboration with personalization across heterogeneous agents. This paper studies when cooperation can support statistically coherent groups of personalized models. We show that data-topology compatibility enables robust orbit-wise personalization: when local objectives and communication topology have (approximately) compatible automorphisms, agents within an orbit share (approximately) equal limiting distributions, while different orbits remain distinct without explicit personalization. This creates a new intermediate regime between global consensus and independent local learning. Under exact data-topology compatibility, as a reference system, we decompose the stochastic learning dynamics into orbit-level and transverse components, derive a necessary and sufficient stability criterion for distributional synchronization, and characterize the orbit-structured stationary law. Modelling an approximate data-topology compatible system as an $\varepsilon$-perturbed reference system, we prove the introduced errors have uniform-in-time and stationary $O(\varepsilon)$ bounds in 2-Wasserstein distance. We also prove sufficient conditions for lower stationary average excess risk than both independent local training and the best single shared parameter. Experiments on synthetic data, MNIST, and CIFAR-10 are in full agreement with the theory. The code is available at https://github.com/Veronicaaa1/orbit-personalization. --- ### ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer Authors: Can Jin, Yan Kang, Yifan Gong, Chongjian Ge, Mingze Xu, Yuanjun Xiong, Dimitris N. Metaxas, Hongwu Peng Published: 2026-10-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15124v1 Foundation models need to support diverse inference budgets, yet training a separate model for each budget duplicates pretraining effort. Elastic models train several nested sub-networks inside one weight-shared supernet, but existing recipes face three obstacles: variable per-step workloads that hinder distributed scaling, limited hyperparameter (HP) transfer across model sizes, and no guarantee that all sub-networks are maximally updated at once. We present \Ours, an elastic transformer that organizes hidden dimensions into a dense core and successive shells, so that every hidden matrix is block lower triangular. One full-width forward pass contains every sub-network's exact hidden states as prefixes, so joint training keeps a fixed computation graph and costs about as much per step as training the widest sub-network alone. We further introduce \muE, an extension of maximal update parameterization (\mup) to \Ours and other elastic architectures. Its scaling rules provably keep all sub-networks of a supernet maximally updated simultaneously (\muI), and keep doing so when the supernet is widened or given more shells; sweeps confirm that HPs tuned on a small non-elastic proxy stay near-optimal for elastic families and larger supernets (\mbox{\muT}). A single \Ours run produces sub-networks that outperform MatFormer and fully elastic baselines at matched parameter counts, and approach separately trained models that together take several times the steps. --- ### scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data Authors: Ugo Lomoio, Pietro Hiram Guzzi, Pierangelo Veltri Published: 2026-10-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15117v1 To evaluate whether a compact bidirectional state-space autoencoder improves joint classification of species, cell type, and disease state from single-nucleus RNA-sequencing profiles in heart failure (HF), while yielding interpretable gene attributions. Building on the dense denoising autoencoder (DAE) and MLP framework of Ruz Jurado et al., we developed scHFBiMamba, combining a bidirectional Mamba autoencoder (BiMambaAE) with an MLP head. BiMambaAE maps 16,545-gene profiles to 350-dimensional latent representations using 13.2M parameters, about 14.6-fold fewer than the dense DAE (192.9M). We compared six encoder-classifier configurations on 38,275 held-out cardiac nuclei using McNemar tests with Benjamini-Hochberg correction, and assessed nine classifiers on frozen representations. Biological relevance was evaluated by comparing SHAP-derived differentially explained genes with differentially expressed genes against curated HF-related Gene Ontology keywords. BiMambaAE+MLP achieved the highest aggregate F1: pooled macro-F1 across 13 outputs was 0.966 versus 0.957 for DAE+MLP, and the mean category macro-F1 was 0.977 versus 0.970. It significantly improved cell-type and disease-state accuracy (adjusted p=7.1e-3 and p=4.8e-6, respectively), with species F1 of 1.000. SHAP-derived differentially explained genes achieved a pathway-enrichment benchmark F1 of 0.105 versus 0.053 for differentially expressed genes. Compact bidirectional state-space autoencoders can outperform substantially larger dense autoencoders for joint cardiac transcriptomic classification while reducing parameters. scHFBiMamba enables accurate multi-task prediction and hypothesis-generating gene-level interpretation. Code: https://github.com/UgoLomoio/scHFBiMamba. --- ### Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving Authors: Tianyi Yang, Haojun Yang, Jipeng Xiao, Xuesong Chen, Shaoshuai Shi, Li Jiang, Zhipeng Zhang Published: 2026-10-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15112v1 High-fidelity closed-loop simulation for autonomous driving increasingly relies on dense multi-view 3D reconstruction. While recent feed-forward geometric foundation models have revolutionized per-scene optimization, applying them to continuous, long-horizon driving sequences is computationally intractable due to GPU memory limits and the quadratic complexity of global attention. Existing scaling strategies are fundamentally limited, as causal streaming suffers from compounding scale drift and trajectory deviation, while rigid "chunk-then-align" heuristics fragment global context and produce trajectory discontinuities. To address these limitations, we introduce Drive3R, a block-wise streaming geometric foundation model. Its block-wise causal attention resolves the scalability bottleneck of fully bidirectional attention while avoiding the loss of local future context in purely causal streaming. Its confidence-aware re-anchoring further mitigates long-range drift by detecting unreliable streaming states, re-initializing the KV cache, and stitching refreshed segments through SE(3) alignment. Extensive experiments demonstrate that Drive3R establishes a new state-of-the-art on nuScenes, KITTI, and Waymo. Specifically, on nuScenes, it improves over the recent DVGT-2 baseline from 0.1806 to 0.1081 in AbsRel, from 0.6750 to 0.5344 in point-cloud Accuracy, and from 1.5812 to 0.9092 in ATE. --- ### Energy-Guided Learning for Heat Equation with Noisy Source: Optimal Estimation and Generalization Bounds Authors: Zixiang Zhou, Xiaohui Chen, Shanghua Teng Published: 2026-10-10 Categories: math.ST, cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2610.15111v1 Data and the governing partial differential equations (PDEs) of continuous-time dynamical systems provide rich structure for statistical learning. A central challenge is how to integrate data with PDE constraints in a principled way to improve generalization. In this paper, we characterize the statistical estimation and generalization properties of learning solutions to the heat equation with a noisy source function from finite, randomly sampled data. We first derive a novel variational formulation, which we characterize as the minimizer of loss function for an energy regularized and ellipticity debiased Sobolev regression. By formulating the learning task as a supervised problem over space-time domains under physically meaningful norms, our approach goes beyond the traditional supervised learning framework by effectively leveraging \emph{auxiliary data}---samples of the source function of the heat equation---to design a \emph{physics-informed energy regularization}. Our analysis reveals that learning in linear parabolic PDEs exhibits intrinsic anisotropy between spatial and temporal regularity, in sharp contrast to the static elliptic problems, leading to fundamentally different estimation and generalization behaviors. Specifically, we derive non-asymptotically rate-optimal estimation errors, as well as generalization error, which explicitly capture the interplay among temporal sampling, spatial resolution, and solution smoothness. Our numerical experiments demonstrate substantial orders of magnitude of reduction in testing errors against various physics-informed neural network methods on various parabolic and hyperbolic PDEs. --- ### Generative Quantum Machine Learning Methods for Cancer Detection using Augmented Datasets Authors: Sophia Knutson, Nandika Goyal, Gennaro De Luca, Glen Uehara, Tanay Kamlesh Patel, Andreas Spanias Published: 2026-10-10 Categories: eess.IV, cs.CV, cs.ET, quant-ph arXiv: https://arxiv.org/abs/2610.15110v1 Cancer detection using AI methods and image databases faces several challenges, including limited and imbalanced image datasets, long algorithm training times, and high-complexity feature generation. In particular, many cancer image datasets contain very few malignant examples compared to benign ones, limiting the amount of minority-class data available for training. Although classical AI and especially deep learning methods have had some success in providing cancer diagnostics, Quantum Machine Learning (QML) methods may offer advantages through high-dimensional feature representations, generative data augmentation, and the exploitation of feature correlations through quantum properties such as entanglement. In this paper, we propose using a generative QML method on the compressed breast ultrasound image dataset (BUSI) to generate synthetic images and hence augmented datasets for classifier training. In particular, we train a convolutional neural network with real, synthetic, and a combination of real and synthetic images. We test the algorithm on real images and provide comparative results for all three training cases. Our results show that the classifier trained entirely on synthetic images achieved an AUC-ROC of 0.802 (80.2%), compared with 0.760 (76.0%) for the real-data baseline. --- ### Structural Chain-of-Thought: Reasoning with Executable Computational Graphs Authors: Petr Senatorov, Karim Vafin, Elena Tutubalina, Oleg Somov Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15107v1 Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful. We introduce a Structural Chain-of-Thought framework where models generate executable computational graphs instead of free-form reasoning. The final answer is obtained by deterministically executing the graph. The model is trained using graph-based reinforcement learning that rewards structural validity, answer correctness, and node overlap with reference graphs. Experiments across five benchmarks and four model families show that our method consistently improves accuracy over supervised graph training and can reduce generation length by up to 5-6x compared with standard GRPO and chain-of-thought supervised training. Our faithfulness experiments reveal that models trained with our approach tend to rely on deriving their answers from the generated graphs rather than producing post-hoc rationalizations as usually in chain-of-thought reasoning. --- ### RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem Authors: Vladimir Kirill Bickov, Neil Yorke-Smith Published: 2026-10-10 Categories: cs.LG, cs.NE, math.OC arXiv: https://arxiv.org/abs/2610.15106v1 Latent recursion repeatedly processes internal representations through the same neural network. Recent work has shown this approach to be effective on structured reasoning tasks such as Sudoku and maze solving. However, whether latent recursion can support neural routing remains unclear. We introduce RELAGRAM (Recursive Latent Graph Model), a novel approach that brings latent recursion to graph combinatorial optimization. RELAGRAM encodes a capacitated vehicle routing problem (CVRP) instance as edge tokens; a compact transformer recurrently updates the latent representations of these tokens. An output head maps the answer state to an edge heatmap, from which an autoregressive decoder constructs a feasible solution. On CVRP-100 instances, the 0.53M-parameter RELAGRAM achieves gaps to a PyVRP reference of 13.4%, 9.8%, and 8.3% under greedy decoding, eightfold symmetry augmentation, and 256-candidate search, respectively. Trained only on CVRP-100, RELAGRAM generalizes zero-shot to CVRP-500 and CVRP-1000, achieving gaps of 15.6% and 21.7% under 256-candidate search. Together, these results demonstrate that latent recursion is a promising approach to neural routing. --- ### RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs Authors: Defne Circi, Krystelle Lionti, Sarathkrishna Swaminathan, Daniel P. Sanders, L. Catherine Brinson, Bhuwan Dhingra, Basel Shbita, Mohab Elkaref, Sara Capponi, Tim Erdmann, Brandi Ransom Published: 2026-10-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15103v1 Extracting structured information from regulatory documents is a critical but challenging task. Relevant facts are scattered across long, legally dense texts, and traceability of extracted facts to their source is essential for verification. With increasing awareness of the environmental and health impacts of per- and polyfluoroalkyl substances (PFAS), regulatory documents have expanded significantly, varying in scope and product relevance, making interpretation challenging for manufacturers and policymakers. We introduce RegExtract, a benchmark for structured information extraction from PFAS regulatory documents, comprising 488 human-annotated field instances across 20 US state documents and 46 regulations. Each field instance includes a value and a provenance entry, yielding 976 entries in total. We define a typed, multi-field schema targeting key elements such as material definitions, permitted uses, and product exemptions, and propose provenance-aware evaluation metrics tailored to regulatory text. Through experiments with open- and closed-source LLMs across prompting strategies, document condensing methods, and schema partitioning approaches, we find that document identification fields remain challenging, and that field-specific few-shot examples improve extraction. This work lays the groundwork for AI tools for hazardous substance identification, question answering, and compliance monitoring. The code and data are available at https://github.com/IBM/PFAS-regulations. --- ### Random Feature Pruning for Multi-Class Classification Authors: Mohammad Amin Omidi, Babak Seyfe, Shahrokh Valaee Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15101v1 Weighted sums of random kitchen sinks (W-RKS) is a commonly used feature extraction technique for supervised learning tasks. A major drawback of this method is the redundancy and ineffectiveness of many extracted random features. This paper investigates efficient methods for reducing such redundancy in multi-class classification problems. We specifically formulate feature selection as a variant of the sequentially nested model selection problem and introduce the Successive Empirical Excess Risk Difference Maximization (SEED-MAX) algorithm. It recursively computes empirical risks to identify the most parsimonious yet informative set of features. We derive an analytical lower bound for the probability of correct feature selection by the SEED-MAX algorithm. This lower bound on the probability of correct feature selection can be made arbitrarily close to one by increasing the training dataset size. To further enhance the rate of pruning, we evaluate the features retained by SEED-MAX using the Fisher test (F-Test). Empirical evaluations on UCR time-series classification datasets show that the sequential application of SEED-MAX with the Fisher test achieves approximately 92 percent rate of pruning with negligible degradation in classification accuracy. Implementations of the SEED-MAX and SEED-MAX-F-Test methods are available at https://github.com/OmidiAmin/seed-max-ftest. --- ### TIDE: Trajectory-Informed Skill Distillation for Efficient Text-to-Video Prompt Optimization Authors: Chengxing Zhou, Yuliang Huang, Jingwei Song Published: 2026-10-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15098v1 Text-to-video (T2V) models are highly sensitive to prompt specificity, while iterative prompt optimization typically improves generation quality only through repeated video generation and vision-language model evaluation at inference time. We propose TIDE, a framework that distills this costly search process into an interpretable and reusable prompt-rewriting Skill. TIDE formulates prompt rewriting as a set of source-conditioned rule modules, each targeting a distinct semantic dimension. Once distilled, the frozen Skill activates the relevant rules and generates both positive and negative prompts in a single LLM call, followed by only one T2V generation, without test-time visual search or backbone fine-tuning. Evolved using only 100 prompts over 14 hours, TIDE achieves prompt-optimization performance comparable to computationally expensive search-based methods. Moreover, when transferred to previously unseen video-generation models, TIDE outperforms existing approaches specifically designed or trained for those models. Code is available at https://github.com/xiningin/TIDE_T2V. --- ### Anchors Enhance Controllability and Reasoning of Diffusion Language Models Authors: Feiyu Qu, Zheng Huang, Andrea Zanette Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15097v1 Diffusion language models (DLMs) offer new opportunities for controllable text generation. However, their controllability, defined as the ability to satisfy task constraints while preserving their original capabilities, remains underexplored. DLMs' bidirectional attention allows control tokens to guide generation from arbitrary positions in the output sequence, but effective guidance depends on the compatibility between their content and placement. To this end, we propose AnchorDLM, a framework in which an anchor generator produces an anchor consisting of a short output fragment and its position for each query. The anchor is placed as control tokens at the specified position to initialize the output sequence of a frozen DLM and guide subsequent denoising. We train the anchor generator with reinforcement learning (RL) to jointly optimize anchor content and placement, using rewards computed from the DLM's generated outputs based on answer correctness and constraint satisfaction. Moreover, through the lens of discrete flow matching (DFM), we interpret anchor placement as helping to reshape the initial velocity field that guides generation. Experiments on code generation and mathematical reasoning across five DLM backbones show that AnchorDLM improves controllability and further yields gains in reasoning performance across diverse benchmarks. --- ### Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families Authors: Abdulrahman Alabdulkareem, Irene Tenison, Yang Zhang, Yada Zhu, Boris Katz, Dan Gutfreund Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15095v1 LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This constrains communication to discrete tokens and costs redundant compute, limiting bandwidth and capabilities of multi-agent systems. Recent works demonstrate KV-cache transfer between LLMs but they either require the LLMs to be within the same family or cannot function across context, thus requiring the receiver to prefill text. We present SwaT (Swarm Telepathy), the first cross-family KV-cache transfer method that allows prefill-free communication in multi-family multi-agent systems. In an agent-to-agent communication setting, combining SwaT with recent advances in KV-cache compaction beats text-to-text communication in both accuracy and speed, with a mean of $40\%$ higher accuracy and a mean of $4\times$ faster wall-clock time. Experiments show SwaT achieves high performance on 17 benchmarks across 12 LLMs and 6 families. Additionally, given a sender Vision-Language Model (VLM), SwaT is able to transfer the vision capabilities to a text-only receiver LLM exceeding text-to-text communication despite SwaT being trained on text-only data. SwaT keeps both sender and receiver models frozen without fine-tuning and only requires $<50M$ tokens and $<1$ GPU-day to train. --- ### TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents Authors: Pramod Kumar, Raj Kumar Pandey Published: 2026-10-10 Categories: cs.SE, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2610.15093v1 AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this process loop engineering, which includes context management, model selection, compaction, and termination. Existing efficiency work mainly compresses tool observations or routes selected turns to cheaper models, but the practical opportunity for these optimizations remains unclear. We analyze 600 publicly released coding-agent trajectories spanning two agent scaffolds and two language models. Median observations contain only 118-286 tokens, while the large build logs commonly used to motivate compression occur near the ninety-ninth percentile. Moreover, 98.6% of input tokens are served from a prefix cache, so flat input pricing overestimates loop cost by roughly 7x on average under near-ideal caching. We derive and empirically validate a closed-form break-even condition for model delegation. Delegation increases cost in half of the evaluated settings, near the predicted boundary. More broadly, turn count explains 84% of the variance in log trajectory cost, compared with 4% for mean observation size; the most expensive trajectories have the most turns despite having the smallest observations. These associations suggest that observation-focused methods target a secondary cost factor, and identify unnecessary turns as the larger and largely unexamined opportunity, though we do not establish that turns can be removed while holding task success fixed. We release TurnCost, a tool for re-scoring trajectory corpora under alternative caching, pricing, compression, and routing policies. --- ### VLCQ: Post-training quantization for deep neural networks using variable length coding Authors: Reem Abdel-Salam, Ahmed H. Abdel-Gawad, Amr G. Wassal Published: 2026-10-10 Categories: cs.CV, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2610.15092v1 Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not require access to the original dataset or retraining the full model. Current methods that achieve high performance close to baseline results typically require INT8 fixed-point integers. However, achieving higher model compression with lower bit-widths often leads to significant performance degradation. In this paper, we propose VLCQ, a post-training quantization method that relaxes the fixed-point encoding constraint, enabling more flexible exploration of quantization techniques through variable-length encoding. This approach achieves competitive or improved performance while reducing bit-widths, without requiring access to training data or model fine-tuning. Extensive experiments on image classification, segmentation, and object detection demonstrate that VLCQ improves model compression and accuracy compared with state-of-the-art post-training quantization approaches. For per-channel quantization, VLCQ surpasses FP32 accuracy and Piece-Wise Linear Quantization (PWLQ) on most evaluated models, achieving up to 6x compression compared with FP32 and up to 1.7x compared with PWLQ. When prioritizing compression with limited accuracy loss, VLCQ achieves up to 12.25x compression compared with FP32 with less than 4% performance degradation. For per-tensor quantization, VLCQ is competitive with Data-Free Quantization (DFQ), while providing greater flexibility to achieve lower bit rates across different tasks and models. --- ### Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions Authors: Siddharth Bhargava, Sara Tonelli, Patricia Martín-Rodilla Published: 2026-10-10 Categories: cs.CL, cs.AI, cs.SC arXiv: https://arxiv.org/abs/2610.15091v1 Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge remains challenging, as it requires a formal representation of how argumentative influence propagates across the structure. We propose Neuro-symbolic Argumentation Reasoning System (NARS) for performing persuasiveness detection directly from online discussions. The neural component employs retrieval-augmented iterative LLM reasoning to extract bipolar argument structures, while the symbolic component applies gradual argumentation semantics to propagate argumentative influence over the structure. Using the Webis-CMV-20 corpus, we construct CMV2BAS, a dataset of long, multi-threaded ChangeMyView discussions annotated with LLM-derived bipolar argument structures and labeled with delta events (view change vs.\ no change). We investigate whether gradual argumentation semantics can effectively detect persuasiveness, whether augmenting them with argument quality and graph-based centrality improves performance, and whether symbolic reasoning remains necessary in the presence of modern LLMs. NARS achieves F1=0.57 and AUC=0.56 under its best configuration, outperforming zero-shot Qwen3.6:27B and GPT-oss:20B. We identify support-dominant discussions and long argumentative chains as key failure modes limiting attack influence propagation. Our work demonstrates the feasibility of operationalizing formal gradual argumentation semantics over noisy real-world discourse for scalable macro-level persuasion analysis, while highlighting key challenges and directions for future research in neuro-symbolic argumentation reasoning. We release both CMV2BAS dataset and the NARS framework for public use. --- ### Self-Evolving Visual Agent via Margin Reward Authors: Wenxi Yang, Yuzhong Zhao, Baochang Zhang, Yunfan Liu, Qixiang Ye Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15084v1 Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool invocation usually relies on curated question-answer pairs or expert demonstrations at scale, which are expensive to acquire. In this study, we propose Marvo, a simple-yet-effective self-evolution approach that enables learning tool invocation from unlabeled images. Marvo consists of two agents: (1) a challenger that generates question-answer pairs from unlabeled images, and (2) a solver that learns tool invocation by solving questions through reinforcement learning. To encourage effective tool invocation, a good training question should be difficult enough to warrant tool use, yet remain within the solver's capabilities. To this end, we introduce a margin reward to the challenger, defined as solver's performance difference with and without access to tools. With the margin reward, we create an adaptive curriculum that encourages the solver to learn effective tool invocation. Across benchmarks covering agentic reasoning, visual search, mathematical, and general real-world reasoning, Marvo improves average accuracy by up to 7.1\% --- demonstrating margin reward as a preferred way to scale question complexity without human supervision. --- ### GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability Authors: Yihang Zhang, Weicai Yan, Qifei Zhang, Yangyang Wu, Tao Jin Published: 2026-10-10 Categories: cs.SD, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2610.15082v1 As text-to-speech (TTS) systems continue to advance, provenance tracking and security verification of synthesized speech have become increasingly important. Audio watermarking provides active provenance by embedding imperceptible, machine-recoverable information into speech. However, existing post-hoc methods typically modify the waveform after synthesis, leaving the watermark vulnerable to compound perturbations. To address this limitation, we propose GAMW, a watermark injection framework integrated into the TTS generation process. Before waveform synthesis, GAMW embeds a content-adaptive multi-bit watermark residual into the generated representation, and its decoding objective combines focal modulation with dynamic per-bit weighting. We train and evaluate GAMW separately on two TTS backbones. With a 16-bit payload, GAMW improves decoding accuracy over the strongest baseline by 9.2 and 23.5 percentage points under individual and compound perturbations, respectively, while maintaining competitive speech quality. Reliable clean-speech decoding is also retained at higher payloads. Code is available at https://github.com/ZConJugaTe/GAMW. --- ### Knowledge transfer between simple discrete worlds Authors: Silvère Gangloff, Jan Hula Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15081v1 Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying general intelligence. We study it in small discrete worlds: sets of grid configurations consistent with a shared set of rules, concretely Sudoku-like puzzles built from a common base and a handful of extra rules. We train a single depth-recurrent model on many combinations of rules and test it at four levels of novelty: a new puzzle, a new combination of known rules, a pairing of rules never seen together, and a rule instance not seen at all during training. The model receives the active rules either as a symbolic description or as two solved examples, and a model that gets no rule information is used as a baseline. At recombining rules it was trained on, the description matches or exceeds examples ($99\%$ against $95\%$ on new combinations). On rule instances whose components never co-occurred in training, the description falls below the no-information baseline while examples stay above it. The framework allows us to test many such generalization regimes in more systematic way than benchmarks such as ARC-AGI and provides new ground for evaluating depth-recurrent reasoning models, which are typically tested on saturated Sudoku benchmarks. --- ### Region Aware Squeeze-and-Excitation Networks for Image Segmentation Authors: Jack Roberts, Praneeth Tummala, Kavi Sarna, Jeova Farias Sales Rocha Neto Published: 2026-10-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15079v1 Squeeze-and-Excitation (SE) modules improve convolutional networks by modeling channel-wise dependencies, but global average pooling collapses spatial structure into a single per-channel descriptor, limiting their effectiveness for dense prediction tasks such as image segmentation. We generalize SE by replacing global pooling with spatially guided pooling, enabling region-aware channel recalibration through four modules with complementary cost profiles. BASE formalizes Tiled Squeeze-and-Excite using a regular grid; SPASE pools over SLIC superpixels for image-adaptive regions; MAPSE obtains regions from semantic maps produced by a frozen, general-purpose network; and PLEASE learns soft region assignments end-to-end through a lightweight assignment network. Each channel receives one gate per region, so attention at each pixel reflects its region membership, bridging channel and spatial attention. PLEASE also produces its soft assignments as a byproduct of the forward pass, providing structured spatial interpretability without post-hoc analysis. The modules offer complementary computational tradeoffs: some add essentially no parameters, while others add no measurable latency. Across binary segmentation on CUB, DUTS, and ECSSD, semantic segmentation on PASCAL VOC 2012 and ADE20K, and classification on mini-ImageNet, our modules outperform SE and related spatial-channel attention variants on most benchmarks, achieving the majority of best results. --- ### On the Theoretical Limits of Learning Unconstrained Interatomic Potentials Authors: Prajwal Ananth, Shuwen Yue Published: 2026-10-10 Categories: cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2610.15078v1 Machine-learned interatomic potentials (MLIPs) accelerate molecular dynamics (MD) simulations by learning the energies and forces that govern atomic motion. Recent work has shown that relaxing physical inductive biases can improve computational efficiency and predictive accuracy, raising the question of whether energy-and-force matching alone is sufficient to ensure accurate sampling. We show that, for unconstrained hypothesis classes, the relationship between prediction error and sampling accuracy is exponentially ill-conditioned in dimension. In particular, prediction errors that decay exponentially with dimension can coexist with nearly maximal total variation distance between the learned and target distributions. We identify two failure mechanisms. The first is kinetic trapping, where relaxation to an accurate learned equilibrium requires exponentially long times, even when simulations are initialized from training configurations at which energies and forces are matched exactly. The second is equilibrium mismatch, where the learned stationary distribution itself remains far from the target. Under explicit assumptions, we show that equilibrium mismatch can persist even in local, symmetry-preserving models, where small per-atom errors coexist with a distributional discrepancy that approaches its maximum as system size increases. Finally, we establish global energy-control conditions that guarantee equilibrium accuracy and identify additional conditions required for rapid relaxation. --- ### BrainAid: Efficient Brain Tumor Detection Using Lightweight CNNs and Explainable AI for Resource-Constrained Environments Authors: Sai Sriram Gonthina, Ross Gore, Bikash Chandra Singh, Pronaya Bhattacharya, Sachin Shetty, Abhishek Phadke, Sandip Roy Published: 2026-10-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15077v1 A brain tumor is an unusual growth of cells in the brain that can be cancerous or not, affecting normal brain function and causing serious risk to health. Existing solutions for brain tumor classification, such as expert manual evaluations of magnetic resonance imaging (MRI) scans, are generally inconsistent as different professionals have different criteria and can be resource-intensive, leading to delayed diagnoses. Additionally, while deep learning models have demonstrated potential, they typically require significant computational resources, motivating the need for more efficient and accessible diagnostic tools that can be deployed in real-time healthcare settings. To address these limitations, this study presents BrainAid, which makes efficient use of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for effective classification of four-class classification of glioma, meningioma, pituitary tumor, and no-tumor MRI scans, outperforming all the standard models such as VGG16, Inception-V3, ResNet-50 and so, while integrating Explainable AI (XAI) to improve interpretability. The BrainAid is trained to classify tumors with a high precision of 98%, achieving an F1 score of 98% and an accuracy of 98% using publicly available dataset. The model is deployed on a Raspberry Pi, demonstrating efficiency in low-resource environments. This system shows the feasibility of real-time, edge-based tumor classification, providing quick diagnostic support for medical professionals and enhancing patient care in resource-limited healthcare facilities and underserved areas. --- ### Toward a Multimodal Foundation Model for Plasma State Reconstruction Authors: Bin Xia, Chuanfei Dong, Boting Li, Yilan Qin, Zikang Xie, Sung Hyun Son, Adam J. Stanier, Jongsoo Yoo, Hantao Ji, Ahmed Diallo, Han Ding, John Wise Published: 2026-10-10 Categories: cs.LG, physics.plasm-ph arXiv: https://arxiv.org/abs/2610.15076v1 Plasma experiments observe coupled physical states through sparse, heterogeneous, and incomplete diagnostics. We present a proof of concept toward a multimodal foundation model for plasma state reconstruction during magnetic reconnection, motivated by the Facility for Laboratory Reconnection Experiments (FLARE). Using 250 synthetic VPIC simulations at fixed reference electron beta $β_{e0}=0.2$, with 225 training runs and 25 disjoint validation runs, we train a 5.5M-parameter residual 3D U-Net to reconstruct three magnetic-field components and electron density from incomplete observations. The model combines spatial-only pooling, which preserves all 24 temporal frames, with global spatiotemporal self-attention and rotary positional encoding. Independently masking magnetic and density modalities across random, grid, block, and temporal patterns enables sparse sensing, cross-modal completion, density super-resolution, and temporal completion with a single set of weights and no task-specific retraining. With density fully hidden, just 0.1% magnetic spatial visibility reduces median density NRMSE from approximately 0.9 to 0.1. Conversely, observed density improves current-density reconstruction when magnetic data are absent or extremely sparse. With no magnetic observations, roughly 1% density visibility approaches the density reconstruction accuracy achieved with fully observed magnetic fields, although current structure remains more dependent on direct magnetic measurements. Full magnetic conditioning also stabilizes completion of missing future density frames. These results demonstrate bidirectional cross-modal predictive coupling within this simulation regime. Generalization across plasma regimes or to experimental measurements remains untested. --- ### Global Disaster Risk Assessment Using World Risk Index Data: A Geospatial and Visual Analytics Approach Authors: Malithi Nawarathne, Nadeesha Herath Mudiyanselage, Lihini Sangeetha Published: 2026-10-10 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2610.15064v1 The world has seen several threats that include resource depletion, food security, poverty and inequality, difficulties associated with urbanization, migration, and environmental effects. The World Risk Index (WRI) is a metric that is used to measure the susceptibility of nations against natural disasters and related risks that is reported by the Humanitarian Data Exchange. The WRI is comprised of factors such as susceptibility, vulnerability to natural hazards, and coping mechanisms. The WRI index has allowed to recognize regions in advance in order to face threats and situations beforehand. This study was conducted by analyzing the data that was related to years from 2000 to 2025 using data visualization techniques. Python related libraries of Matplotlib, Seaborn, and Geopandas were used due to their efficiency and usability in analyzing WRI data. As per the analysis, it was identified that countries of Philippines, Mexico, Indonesia, and India were recorded with high WRI index values that showed these nations should be prepared for natural disasters and situations. Hence, this study has provided insights using data visualization techniques in understanding natural disasters and threats so that necessary measures can be taken ---