arXiv:2510.10930v3 Announce Type: replace
Abstract: Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over 100 novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models.
Science Journals
arXiv:2605.16480v1 Announce Type: cross
Abstract: Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in which topology is implicit, forcing LLMs to reconstruct molecular structure before performing the requested chemical operation. Here we introduce MoleCode, an LLM-native, training-free, graph-explicit molecular language in which all molecular components are represented as typed entities with persistent identifiers and explicit relations. MoleCode makes molecular topology directly readable, editable and auditable within the language context, allowing an LLM to operate on structure rather than recover it from syntax. Across molecular reasoning, editing, generation and analysis tasks, this representational shift improves frontier LLMs most strongly when structural access is limiting: unfamiliar molecules, topology-sensitive operations, larger structures and repetitive polymers. It also changes how inference is allocated, replacing long reasoning traces devoted to implicit structural reconstruction with shorter, more chemically directed reasoning over explicit atoms and bonds. In molecular optimization, this enables localized, property-aligned edits that preserve structural similarity to the starting compounds. The same Subgraph--Node--Edge grammar extends beyond small molecules to polymers, Markush structures, mechanism-style transformations and interleaved scientific documents, including research articles and patent disclosures in which chemical information is distributed across text and images. These results suggest that the interface between scientific objects and LLMs should not treat structure as something to be decoded from text. When the object of reasoning is relational, the structure itself should be part of the language.
arXiv:2605.17334v1 Announce Type: cross
Abstract: Reliable early detection of lithium-ion battery degradation requires health indicators that are physically interpretable and computable from routine cycler telemetry without access to the degradation region. We introduce \textsc{CausalHealth}, a framework that applies causal graph discovery and $k$-nearest-neighbour transfer entropy to per-cycle voltage, current, temperature, and resistance time series, and organises twelve resulting anomaly scores into three signal-class bundles (Magnitude-shift, Predictive-residual, Complexity-entropy) -- with Isolation Forest reported separately as it falls below the bundle reliability threshold -- to characterise detection sensitivity across ten commissioning fractions (5--30\,\%). The Magnitude-shift class achieves 100\,\% detection across all seven tested cells spanning LFP (MIT--Stanford MATR) and LCO (NASA PCoE, CALCE CS2) chemistries, with a lead time of up to 402 cycles before conventional capacity-threshold failure on gradual-fade cells. A Reliability-Weighted Master Health Index (RWMHI) -- a cross-bundle fusion of five high-reliability detectors weighted by inverse coefficient of variation -- improves lead time by 15--52 cycles over the class median on long-lived cells while maintaining 100\,\% detection. Validation against electrochemical impedance spectroscopy on an NMC prismatic cell provides independent physical grounding: transfer entropy $\mathrm{TE}(R \!\to\! V)$ correlates with charge-transfer resistance $R_{\mathrm{ct}}$ (pooled $r = +0.990$; temperature-controlled partial $r = +0.898$), and an Arrhenius analysis of both quantities yields an activation energy consistent with published NMC charge-transfer kinetics. These results are evaluated on seven cells across three benchmark datasets.
arXiv:2605.14947v2 Announce Type: replace
Abstract: Stratospheric aerosol injection (SAI) is a solar radiation modification technique, proposed as an interim measure to offset warming while greenhouse gas (GHG) emissions are reduced. This paper discusses a possible SAI implementation route - an alternative to sulfate aerosols formed in situ - based on engineered solid particles having dedicated properties such as size, composition, surface chemistry, and traceable origin, supporting safety, controllability, and functionality needed for SAI systems. These engineered properties also open up options for any future multi-state coordination of SAI through two technical building blocks: (1) the SAI-induced radiative forcing (SRF) - the magnitude of the cooling effect attributable specifically to the SAI layer - as an operator-independent quantity, derivable from direct aerosol-layer measurements; and (2) particle traceability through identifying signatures embedded at production. Both could feed into a shared, publicly accessible monitoring database open to independent interrogation, addressing several governance challenges by anchoring compliance assessments in measurable parameters. Drawing on precedents from the Montreal Protocol, IAEA safeguards, and other regimes, we show that shared technical metrics have historically enabled multi-state cooperation, and we argue the same could apply to SAI. We describe a phased pathway in which the technical capabilities and coordination practices that would use them are developed and tested together, at scales orders of magnitude below operational deployment. To be clear - we regard SAI deployment as premature; the conditions under which it might be considered have not been met. The paper does not propose a governance framework; rather, it identifies technical infrastructure that could support a wide range of such frameworks.
arXiv:2605.17440v1 Announce Type: new
Abstract: Neutron multiplicity counting (NMC) underpins plutonium assay in nuclear safeguards, arms control, and disarmament verification, but existing simulation tools are essentially limited to MCNPX-PoliMi [1] (export-controlled, MCNP license required) and ONMS [2] (open-source but built on Geant4 with no scripting API); other codes (RMC, MCNP-PTA) are institute-internal. We present PyNMC, an open-source, Python-native NMC simulation framework that couples OpenMC for transport with FREYA for event-by-event correlated prompt-neutron emission and ALPHANSO for native ($\alpha$, n)-source estimates, together with collision-level time-tagged event recording and a Python shift-register post-processor cross-validated against ONMS. The framework is validated against the ESARDA Neutron Multiplicity Benchmark on bare $^{252}$Cf (c2-10, c2-100), the low-multiplication Pu metal case c3s (M = 1.12 from an independent k-eigenvalue calculation; ESARDA spec M = 1.08), and a 10 g PuO2 sample with an ($\alpha$, n)-source term (c4s); an internal stress-test extension to a $\approx 100$ g Pu metal sample at M = 1.29 is reported alongside but lies beyond the ESARDA participant range. For c4s, ALPHANSO gives $\alpha$ = 0.78 with modern cross-section data; the reported benchmark comparison rescales the ($\alpha$,n) rate to the ESARDA value $\alpha$ = 0.853. Simulated rates agree with point-model predictions for all cases, and with the published ESARDA participant-code scatter where participant results exist. The framework is shipped as a Docker container under the MIT license and is openly available on GitHub at github.com/cfichtlscherer/nmc.
arXiv:2605.17449v1 Announce Type: new
Abstract: Whole-slide MIL models are often called context-aware once graphs, Transform ers, or state-space modules are placed above patch embeddings. We show that this label can be deceptive. On pathology tasks where tissue architecture is part of the diagnostic signal, several strong MIL baselines retain nearly unchanged slide level AUC after patch coordinates are permuted. Their predictions are accurate, but largely compositional. We refer to this failure mode as spatial blindness. Our explanation is optimization-based: dense appearance statistics are learned early under slide-level supervision, leaving weak gradients for sparse spatial relations. ResTopoMIL addresses the issue by first fitting a permutation-invariant prototype histogram and then freezing it while a lightweight graph branch learns the residual under a coordinate-shuffling constraint. The architecture is simple by design; the intervention is in how the spatial branch is trained. Across 9 public WSI bench marks, ResTopoMIL improves classification and survival prediction with 1.15M parameters, restores sensitivity to coordinate perturbation, and gives stronger lo calization evidence on CAMELYON-16.
arXiv:2605.17454v1 Announce Type: new
Abstract: Multi-party multi-objective optimization problems (MPMOPs) require consensus among autonomous decision makers and therefore differ from flattened many-objective formulations. Existing runtime theory for multi-objective evolutionary algorithms is largely tailored to single-party Pareto-front approximation and does not directly explain common-solution search in MPMOPs. We investigate cross-party recombination in two representative settings. On MP-JCG, a pseudo-Boolean benchmark with an explicit gap region, we prove that a payoff-guided mutation baseline faces a gap-crossing bottleneck requiring \(\Theta(n^2)\) expected fitness evaluations. In contrast, an analytical CPR-NSGA-II variant discovers both common Pareto-optimal solutions in \(O(n\log n)\) expected evaluations by directly assembling complementary prefix and suffix templates distributed across party populations. Comparing this with the flattened four-objective formulation F-JCG, our full-front coverage analysis illustrates the additional coverage burden introduced by flattening. For BPBOMST, the bi-party, two-objective-per-party specialization of the multi-party multi-objective minimum spanning tree problem, we develop a layered support-cover analysis. For each common Pareto objective vector, the symmetric average projection induces an auxiliary bi-objective MST instance, and suitable support representatives yield a \(2\lambda\)-common approximation cover with \(\lambda\in[1,2]\). We further derive an instance-parameterized expected runtime bound for a representative-pool CPR-NSGA-II variant using edge-union recombination and uniform repair. This bound separates the effects of local auxiliary-front filling, cross-party recombination shortcuts, and edge-union repair ambiguity.
arXiv:2605.17465v1 Announce Type: new
Abstract: Learning causal relations from observational data is challenging because the graph search space grows super-exponentially with the number of variables. Ordering-based methods reduce this space by first identifying the topological ordering, whereas continuous optimization methods explore most likely regions of the space by casting DAG learning as a differentiable objective with an acyclicity constraint. Despite their conceptual appeal, both paradigms face significant scalability limitations in high-dimensional settings, restricting their practical applicability. In this work, we introduce a new formulation for linear causal discovery that tightly integrates these two paradigms to achieve substantial gains in scalability without sacrificing accuracy. Our approach, TriOpt, decomposes the problem into two efficient stages. First, it recovers the topological ordering by exploiting the Sherman-Morrison rank-1 downdate together with the additive structure of linear kernels, enabling fast and scalable ordering estimation. Second, given this ordering, we reformulate structure learning as a convex continuous optimization problem that entirely avoids the need for enforcing costly acyclicity constraints. We theoretically show that, under the true ordering, TriOpt exactly recovers the underlying linear DAG. Empirically, across synthetic, semi-synthetic, and real-world datasets, TriOpt achieves orders-of-magnitude speedups over state-of-the-art linear causal discovery methods in high-dimensional regimes, while maintaining comparable or superior accuracy.
arXiv:2605.17467v1 Announce Type: new
Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such as direct prediction of agent-error pairs and agent-first failure attribution, rely on local logs of agents and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-grained attribution. To address these challenges, we propose VerifyMAS, a hypothesis verification framework for agent failure attribution. Instead of directly predicting faulty agents and error types, VerifyMAS formulates and verifies failure hypotheses against full trajectories. This verification-based approach decomposes attribution into trajectory-level error validation and fine-grained agent localization, providing an error-first attribution approach that captures global failure patterns while substantially reducing the search space. We further introduce a hypothesis-based data construction strategy grounded in a structured error taxonomy and fine-tune a specialized LLM verifier model for trajectory-level failure verification and agent attribution. Experiments on Aegis-Bench and Who&When show that VerifyMAS consistently improves diverse backbone models, including open-source Qwen and API-based GPT models, outperforming prior methods without sacrificing inference efficiency for long multi-agent trajectories.
arXiv:2605.17471v1 Announce Type: new
Abstract: Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau, particularly below 4-bit-widths. While this problem has been observed in prior work, its precise cause remains unclear. In this paper, we analyze the convergence of QAT by estimating the spectrum of the loss-surface Hessians. We find that the weights converge to flat regions around saddle points, where a large fraction of the Hessian eigenvalues are both positive and negative. During training, an increasing fraction of Hessian eigenvalues concentrates around zero, whose magnitude decreases. At lower bit-widths, the magnitude of eigenvalues in the Hessian spectrum is significantly smaller. To mitigate these issues, we propose an algorithm called WinQ to accelerate QAT, which involves: (1) periodically resetting weights to the linear interpolation of full-precision and quantized weights, reducing the distance to the quantization grid and increasing eigenvalue magnitude, and (2) computing gradients of noise-injected weights to regularize the Hessian. Extensive experiments show that WinQ accelerates QAT by up to 4 times across various quantization methods and models. Under the same training cost, WinQ improves state-of-the-art sub-4-bit quantization by up to 8.8%. These results are consistent across 16 settings with different language models, quantization methods, and bit widths.
arXiv:2605.17489v1 Announce Type: new
Abstract: Face Image Quality Assessment (FIQA) is a crucial control step in biometric pipelines. It ensures only reliable samples are processed to maintain system accuracy. State-of-the-art FIQA methods achieve high utility but typically operate as "black boxes." They produce scalar scores without human-interpretable justifications. This lack of transparency limits their effectiveness in human-in-the-loop scenarios, such as automated border control, where actionable feedback is essential. In this paper, we investigate the potential of off-the-shelf Vision-Language Models (VLMs) to bridge this gap by performing FIQA in a zero-shot setting. We present a comprehensive evaluation framework for assessing VLM performance. This involves benchmarking traditional FIQA methods through error-versus-reject curves. Additionally, using a diverse set of datasets, ranging from surveillance-oriented to synthetically generated, we analyzed their interpretability, consistency, and robustness to prompt changes. Our results show biometric utility performance depends significantly on architecture, not merely on parameter count. Most VLMs' outputs align with those of traditional methods. We also find that VLM ranking performance and the generated scores may vary across prompts. Our synthetic ablation study shows that while increasing the parameter count can improve internal consistency, it yields worse degradation-detection performance than smaller models. These findings suggest that zero-shot FIQA score estimation using VLMs is promising and could effectively complement conventional FIQA pipelines as an interpretability module. The codes are available at https://github.com/ThEnded32/VLM4FIQA.git.
arXiv:2605.18227v1 Announce Type: new
Abstract: Pseudo-random number generators (PRNGs) are widely used in modern computing and are expected to exhibit excellent statistical performance and repeatability. This study evaluates and compares modern PRNGs used in high performance computing and artificial intelligence. Our selections comes from different families, including Xoshiro, Philox, PCG, and MRG32k3a. We systematically assess the quality of these generators; instead of testing a single stream for each generator, we test more than 10 3 streams with the BigCrush battery form the TestU01 library. The results, involving more than 4.5 years of cumulative computing time, are analyzed against the claims made by the generators' creators. The highest success rate is 72%, and all tests have been failed by almost every generator, the failed tests are documented. To ensure fairness, all tests are conducted under consistent conditions and are designed to closely simulate real-world usage. The results of each test are available, usable and reproducible with a git repository.
arXiv:2605.18257v1 Announce Type: new
Abstract: Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment spaces that overlook modality-unique features. We propose CodeBind, a framework that optimizes multimodal representation spaces through a modality-shared-specific codebook design. By incrementally aligning target and bridging modalities, CodeBind bypasses the need for fully paired data. Unlike traditional hard alignment, CodeBind decomposes features into shared components for semantic consistency and specific components for modality-unique details. This design utilizes a compositional vector quantization scheme, where a shared codebook bridges modality gaps and modality-specific codebooks mitigate representation bias by preventing dominant modalities from overshadowing others. Validated across nine modalities (text, image, video, audio, depth, thermal, tactile, 3D point cloud, EEG), CodeBind achieves state-of-the-art performance in multimodal classification and retrieval tasks.
arXiv:2605.18430v1 Announce Type: new
Abstract: Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prototyping and intuitive design workflows. However, existing benchmarks focus on basic primitives and simple sketch-extrude sequences, lacking advanced features essential for real-world applications and covering only traditional mechanical parts. We introduce Text2CAD-Bench, the first benchmark systematically evaluating text-to-CAD across geometric complexity and application diversity. Our benchmark comprises 600 human-curated examples spanning four levels: L1-L2 cover fundamental geometry with standard features, L3 introduces complex topology and freeform surfaces, and L4 extends to real-world domains beyond mechanical parts. Each example pairs dual-style prompts -- geometric descriptions mimicking non-expert users, and procedural sequences aligned with expert-level conventions. Evaluating mainstream general LLMs and domain-specific models, we find that current models perform reasonably on basic geometry but degrade substantially on complex topology and advanced features. We release our benchmark to drive progress in text-to-CAD research.
arXiv:2605.17526v1 Announce Type: new
Abstract: As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end-to-end software development. Although existing benchmarks have recently evolved from localized code editing to from-scratch project generation, they remain confined to structurally simplified, single-stack applications. Consequently, they fail to capture the heterogeneous environments, full-stack orchestration, and system-level complexity of real enterprise Software as a Service (SaaS) systems, leaving a critical gap in assessing agents under realistic engineering constraints. To fill this gap, we introduce SaaSBench, the first benchmark designed to explore the boundaries of AI agents in enterprise SaaS engineering. Spanning 30 complex tasks across 6 SaaS domains with 5,370 validation nodes, it incorporates 8 programming languages, 6 databases, and 13 frameworks to meticulously mirror real-world software heterogeneity. Furthermore, we design a dependency-aware hybrid evaluation paradigm tailored for complex systems with long horizons and multi-component coupling, enabling fine-grained, reproducible assessment. Crucially, our extensive experiments reveal a striking insight: the primary bottleneck for state-of-the-art agents is not generating isolated code logic, but successfully configuring and integrating a multi-component system. Over 95\% of task failures occur before agents even reach deep business logic, with models often falling victim to overconfidence and prematurely halting during foundational system setup, or getting trapped in ineffective debugging loops. We hope SaaSBench serves as a practical and challenging testbed to drive the evolution of reliable, system-level coding agents. The code is available at \url{https://github.com/ShadeCloak/SaaSbench}.
arXiv:2605.18554v1 Announce Type: new
Abstract: Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification of either component can severely degrade accuracy and calibration. Motivated by the rapid progress of predictive models such as large language models, the martingale posterior, also known as predictive Bayes, replaces the prior--likelihood pair with a predictive distribution and recovers parameter uncertainty by repeatedly drawing predictive samples and refitting the model. A direct federated implementation, however, would require clients to share the local data sets. This letter proposes {federated martingale posterior} (FMP) sampling, a one-shot embarrassingly parallel protocol in which each client uploads a small set of trainable data embeddings and the server runs the predictive sampler centrally. Experiments on MNIST, CIFAR-10, and CIFAR-100 show that FMP closely matches the centralized counterpart and significantly improves calibration over consensus-style baselines.
arXiv:2605.18556v1 Announce Type: new
Abstract: Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, current vision-language-action policies and world-action models often couple linguistic knowledge with visual computation in a shared backbone or conditioning pathway, leading to modality competition and making knowledge extension dependent on backbone updates. In this paper, we introduce Key-Gram, a conditional-memory framework that separates language-derived world knowledge from visual-state reasoning for embodied control. At its core is a memory module that decomposes an instruction into task-specific key-grams, retrieves static linguistic priors through deterministic hashed lookup, and injects the retrieved entries into selected hidden layers through context-aware gating and lightweight convolutional fusion. This design allows the backbone to devote its main capacity to visual reasoning and action inference, while reusable instruction knowledge is stored in an extensible external memory. The logical memory table can be conveniently partitioned during training and, due to its $O(1)$ lookup pattern, efficiently placed on host memory during inference. Across RoboTwin2.0, LIBERO/LIBERO-Plus, and real-world dual-arm manipulation, Key-Gram consistently improves both $\pi_{0}$ and $\pi_{0.5}$ backbones, with average relative gains of $29.5\%/9.9\%$ on RoboTwin2.0, $35.8\%/4.5\%$ on LIBERO-Plus transfer without target-domain fine-tuning, and $15.4\%/8.1\%$ on real-world long-horizon tasks. These results demonstrate that externalized linguistic memory provides an effective and extensible mechanism for improving compositional grounding, transfer, and real-world manipulation.
arXiv:2605.17530v1 Announce Type: new
Abstract: Network intrusion detection systems play a vital role in protecting networks by detecting malicious network traffic which can then be investigated by a cybersecurity operations centre. State-of-the-art approaches utilise supervised machine learning methods to train a classification model to recognise known cyberattacks; however, these models require a large labelled dataset to train and show poor performance when trained on smaller datasets. In an attempt to address this shortcoming, anomaly detection models learn the distribution of benign traffic and flag non-conforming traffic as malicious. While these methods do not require malicious examples to train, they suffer from high false-positive rates rendering them impractical. As a result, networks may be particularly vulnerable when there are insufficient labelled instances of a specific attack class to train an effective classifier. This often occurs in newly established networks or when previously unseen types of attacks emerge. To address this challenge, this work proposes the use of a triplet network, utilising online triplet mining and a KNN classifier, which is able to perform few-shot classification, enabling effective intrusion detection after being trained on a limited number of malicious examples. Various online triplet mining algorithms were explored and model design choices, such as the inference algorithm and optimised distance metrics, were compared and evaluated through a series of ablation studies. The final model was compared against other state-of-the-art approaches in few-shot binary and multiclass classification, where the proposed approach was found to be competitive with existing methods when trained on as little as 10 malicious samples of each class.
arXiv:2605.17533v1 Announce Type: new
Abstract: This letter proposes a distributed 3D leader-follower formation (3D-LFF) control framework for multi-UAV systems that achieves formation tracking while enforcing perception safety constraints. Maintaining safe, vision-based 3D-LFF is challenging because onboard cameras impose strict Field-of-View (FOV) limitations, and demanding formation commands can drive the leader outside the follower's camera frustum, resulting in loss of visibility. To address this issue, we develop a perception-aware safe control architecture that guarantees visibility by construction. First, we derive a relative kinematic model in a line-of-sight coordinate representation and design a distributed 3D-LFF tracking controller using only locally available relative states. Next, we embed the nominal formation controller within a Control Barrier Function-based Quadratic Program (CBF-QP) safety filter that minimally modifies the commanded velocities to maintain the leader inside the follower's camera frustum while preserving formation tracking whenever feasible. Gazebo simulations and Crazyflie hardware experiments validate the proposed approach, demonstrating accurate formation tracking and effective FOV enforcement, including scenarios in which the nominal desired formation conflicts with visibility constraints.
arXiv:2605.17535v1 Announce Type: new
Abstract: Legacy modernization breaks business logic. Most tools and LLM-based approaches treat modernization as syntax translation, losing implicit rules, edge-case handling, and cross-module constraints. We present AgentModernize, a multi-agent framework that treats modernization as a behavioral preservation problem. Four specialized agents handle extraction, specification, code generation, and validation. The key intermediate artifact -- a Behavioral Specification Graph (BSG) -- forces extracted business logic to be explicit and inspectable before any code is generated. We evaluated on LegacyModernize-8, eight scenarios spanning telecom and banking, using three models (GPT-4o-mini, GPT-4o, GPT-5.3-codex) under a fair protocol: same gold-standard tests, 3 trials, temperature 0.0. Full AgentModernize with feedback was the only configuration with non-zero mean BER under every backbone. SP-LLM and CoT-LLM scored 0.0% on every scenario, on every backbone. AgentModernize without feedback scored 0.0% mean BER with GPT-4o-mini and GPT-5.3-codex; under GPT-4o it achieved non-zero BER only on S1 (44.4%; 5.6% mean over scenarios). Mean BER for full AgentModernize was 9.4% (mini), 8.1% (GPT-4o), and 19.4% (codex). The BSG captures 91.2% of gold-standard rules, confirming that the bottleneck is code generation, not extraction.
arXiv:2605.17538v1 Announce Type: new
Abstract: This letter investigates the problem of output synchronisation in heterogeneous dynamical networks with nonlinear diffusive couplings in the presence of disturbances on the coupling links. By exploiting relative dissipativity properties between adjacent agents, distributed conditions are established to guarantee output synchronisation. Specifically, these conditions can be verified using only local information associated with neighbouring agents and coupling links. As an illustration, a heterogeneous network of Goodwin oscillators is considered, where the relative dissipativity properties between neighbouring oscillators are characterised and used to analyse synchronisation.
arXiv:2605.17541v1 Announce Type: new
Abstract: We present a semi-analytical model to analyze multi-tile metasurface antennas consisting of a set of metasurface tiles and a practical power-dividing network that excites the tiles. The metasurface tiles consist of arrays of rectangular waveguides with subwavelength metamaterial radiators etched into their top walls, each of which can be accurately modeled as polarizable dipoles. The feed structure for the arrays comprises a slotted waveguide attached to their bottom wall, with coupling slots inserted into the common wall that are likewise modeled as polarizable dipoles. The proposed semi-analytical model employs a coupled-dipole framework that accurately captures dipolar interactions among constituent elements within the metasurface tiles, along with a multi-port network analysis technique that accounts for electromagnetic interactions between the tiles and the power divider, thereby forming a self-consistent formulation. The proposed model enables the prediction of key performance metrics, including overall S-parameters, radiation patterns, and gain, and is validated through full-wave numerical simulations. By significantly reducing the computational complexity associated with electrically large apertures, the proposed framework enables rapid and efficient modeling of the overall structure, thereby facilitating iterative optimization. The proposed model has potential applications as an efficient forward model for the design of wireless systems requiring large-aperture metasurface antennas, including remote sensing and next-generation wireless communication networks.
arXiv:2605.17542v1 Announce Type: new
Abstract: This paper proposes a systematic and explicit quantum circuit framework for solving advection-diffusion equations with boundary conditions, based on the Linear Combination of Hamiltonian Simulations (LCHS) method. By employing the Finite Volume Method (FVM) combined with various flux construction schemes, we elaborate the design of quantum circuits tailored explicitly for Robin boundary conditions (including Dirichlet and Neumann boundary conditions as special cases) and periodic boundary conditions. In contrast to prior works on quantum simulation of advection-diffusion equations, we present a detailed error analysis for the linear combination of unitaries (LCU) induced by the constructed quantum circuits. A comprehensive gate complexity analysis demonstrates the quantum advantages over classical computing in high-dimensional scenarios. We simulate the proposed circuits on a fault-tolerant emulator, and numerical results validate the effectiveness of the proposed framework across homogeneous, inhomogeneous, and high-dimensional cases. The proposed framework is compatible with numerous spatial discretization methods and numerical schemes, extends naturally to other linear PDEs, and establishes a practical foundation for solving large-scale PDE problems on future fault-tolerant quantum computers.
arXiv:2605.17562v1 Announce Type: new
Abstract: EEG foundation models (EEG-FMs) have been evaluated predominantly on clean, in-distribution accuracy, leaving their robustness, interpretability and representational quality largely unexamined. This study addresses these gaps by benchmarking six EEG-FMs against a baseline deep learning model across eight datasets. Beyond clean accuracy, we conduct three layers of analysis: (i) Robustness: we apply test-time perturbations including additive noise, random and region-based channel dropout and region-specific noise injection. Our analyses show that no single model dominates all failure modes. The most noise-robust model is among the most fragile under channel dropout and much of the dropout fragility disappears when channels are removed rather than zero-padded. (ii) Interpretability: we present the first application of Attention-Aware Layer-Wise Relevance Propagation (AttnLRP) to EEG-FMs and show that models broadly concentrate relevance on task-appropriate brain regions consistent with known neurophysiology. However, attribution maps remain spatially stable under perturbation while predictions degrade, suggesting that the models attend to the correct brain regions but decode corrupted content. (iii) Expressiveness: With block-wise probing we show that late blocks are repurposed during fine-tuning, while early blocks already hold task-related information. Furthermore, we demonstrate that the poor head-only performance previously attributed to low-quality pre-trained representations is largely explained by pooling and that EEG-FMs possess sufficient representational capacity when their token-level embeddings are preserved. Together, these findings provide the first systematic assessment of robustness, interpretability and expressiveness for EEG-FMs and highlight critical considerations for their development.
arXiv:2605.18613v1 Announce Type: new
Abstract: Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music autoEncoder), an autoencoder for stereo music and general audio that reaches a 4096$\times$ temporal compression ratio while maintaining reconstruction quality and downstream generative performance. We achieve this by combining a tranformer-based backbone with set of semantic regularisation approaches, phase-aware reconstruction losses and improved discriminator designs. The architecture delivers substantial computational cost benefits, through both its high compression ratio and its reliance on well-optimised transformer primitives. Two variants (a large SAME-L and a CPU-deployable SAME-S) are released in open-weights form.