Papers

As Digital Twin (DT) systems evolve beyond state synchronization toward task-oriented and knowledge-driven operation, Cognitive Digital Twins (CDTs) have emerged as an extension that incorporates cognitive capabilities into twin operation. Existing CDT studies often focus on specific enabling techniques, such as learning modules, knowledge graphs, and large language models, while providing limited insight into how cognition can be systematically integrated into DT architectures. To address this issue, this paper proposes a four-layer CDT architecture consisting of the physical layer, digital-twin layer, cognitive layer, and task layer. The proposed architecture establishes a self-evolving closed operational loop spanning these four layers, in which physical states are synchronized into digital representations, cognition constructs task-specific cognitive models through knowledge, memory, and attention, and task-level decisions are generated under practical constraints. Operational feedback further refines cognitive experience and updates relationships and annotations in the digital representation, enabling subsequent task interpretation, initiation, and reasoning to evolve with system operation. Based on this framework, two representative operation modes are characterized: user-request-driven cognition and self-driven cognition. We further discuss key enabling mechanisms and deployment challenges associated with semantic communication, knowledge querying, task orchestration, and closed-loop synchronization. A lightweight simulation study illustrates reliable closed-loop task feasibility under limited semantic information and improved operational efficiency through accumulated task experience. The proposed framework provides a structured foundation for the design and development of future CDT systems.

Neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS) encode a scene with complementary inductive biases, but existing cross-representation distillation typically fixes one representation as teacher for the entire scene. A globally fixed teacher can propagate local reconstruction errors. We present RouteBridge, a bidirectional framework that selects the teaching direction for each ray. Its reliability estimator combines photometric residuals with representation-specific geometric evidence and routes supervision from NeRF to 3DGS, from 3DGS to NeRF, or abstains. A renderer-independent interface transfers color, opacity, and normalized depth without shared features or point correspondence. On mip-NeRF 360, the NeRF and 3DGS exports reach 28.56 and 28.77 dB, respectively. The 3DGS export improves over 3DGS by 1.56 dB and over NeRF-GS by 0.45 dB while reducing LPIPS to 0.207. On static three-view DTU, RouteBridge obtains 21.12 dB. Ablations show that both adaptive routing and geometric ray targets contribute to the improvement.

On August 2, 2026, the obligations of Article 50 of the EU AI Act took effect, requiring generative AI providers to mark the content their systems produce and ensure it can be detected as AI-generated. Days later, Anthropic disclosed that every Claude model released after that date embeds a watermark based on SynthID-Text in all generated text, enabled by default with no user opt-out; Google has deployed SynthID-Text in Gemini since 2024. Users objected that the watermark degrades quality, particularly for code, that it secretly encodes identifying information, and, in mutual contradiction, that it is easily removable and inescapable; the vendor answered with assurances of unchanged quality, no identifying information, and robustness to light editing. In this work, we argue that neither the objections nor the assurances can currently be verified and that this unverifiability, rather than watermarking itself, is the substantive governance failure. We sort the contested assertions by what it would take to settle each and evaluate the open-source SynthID-Text implementation on two open-weight models, because no public tool can test the deployed systems. On prose, the measured effect of the watermark does not exceed that of changing the sampling seed. On code, the cost is three points of correctness on one model and below measurement on the other, while detection remains near chance, a limitation of detectability rather than quality. The remaining gaps trace to withheld access or missing institutions and we map each to a requirement: release of matched outputs, configuration disclosure, accredited audits, a shared evaluation protocol, and interoperable detection.

Accurate tactile forecasts need not improve force-constrained control. We study a 652,157-parameter action-conditioned visuotactile world model with matched behavior cloning, policy learning in imagination, independent reactive implicit Q-learning, and model-assisted force feedback. A fixed protocol executes 34 policies on 120 fresh MuJoCo environments spanning geometry and physical-parameter shifts, plus 324 independently replayed action branches on 12 additional ID environments. Visuotactile dynamics reduce force action-effect MAE from 0.413 N for persistence to 0.338 N. Model-assisted feedback raises ID force-budgeted success from 73.3% to 93.3%, with paired difference +20.0 [+6.7,+33.4] percentage points (95% CI), with the difference occurring during scripted lowering. Its pooled difference is +3.9 [-4.5,+11.7] points. Imagined RL achieves 11.9% pooled joint success versus 25.0% for reactive IQL. An empirical tactile-residual stress test adds 330 executions. The evidence concerns rigid-box lifting after a common approach, without physical-robot transfer or a closed-loop safety guarantee.

Teacher-student systems, in which a teacher neural network generates training labels so that a student neural network can learn to implement the same function, are widely used as an abstract setting to study learning. However, the structure of the teachers is often overlooked by assuming randomly-generated, normally-distributed parameters. This hides substantial variation in how learnable different teachers are. We formalize learnability as the success rate of converging to the global minimum, as a function of overparameterization, learning algorithm, student initialization distribution, and teacher geometry. We both identify an easy distribution that maximizes node dissimilarity and a hard distribution that minimizes it, and show that these two distributions induce markedly different success rates across a large range of settings and for different activation functions. To explain the gap, we study the loss landscape of small neural networks that contain two distinct kinds of suboptimal local minima, out-of-bounds (OOB) minima at the edge of the data distribution and interior minima within. Assuming infinite data and a fast readout layer, we analytically reduce the loss landscape of small networks to two dimensions, showing that the region of attraction of interior minima changes as a function of teacher structure. In larger networks, maximally dissimilar teachers induce more interior minima, while minimally dissimilar teachers induce more OOB minima. Motivated by these analyses, we show that differentially increasing the learning rate of the readout layer and decreasing the learning rate of the inner biases increases success rates. These findings provide an important step in narrowing the gap between the study of teacher-student networks and more structured functions that arise in practice.

Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence, where heterogeneous robots collaborate through low-latency connectivity, edge intelligence, and distributed sensing. Vision-language-action (VLA) models offer a foundation by integrating visual perception, language understanding, and action generation into a unified closed-loop policy. However, training and adapting VLA models to distributed robotic agents introduce challenges in privacy protection, communication efficiency, and model heterogeneity. Existing federated learning (FL) methods overlook the intrinsic differences among vision, language, and action pathways in parameter scale, privacy exposure, update dynamics, and tolerance to compression or perturbation. To address this issue, this article proposes FedMVLA, a modality-decoupled FL framework for privacy-preserving embodied intelligence in 6G networks. FedMVLA incorporates three mechanisms: modality-aware federated aggregation (MAFA), modality-aware privacy allocation (MAPA), and modality-aware communication compression (MACO), together with a modality-sliced transport design that routes the precision-critical action stream through a protected ultra-reliable low-latency slice. A case study on federated robotic manipulation over the Third Generation Partnership Project (3GPP)-based wireless substrate, covering fading, co-channel interference, and malicious jamming, shows that FedMVLA achieves an 84.8% task success rate, exceeds FedAvg by 22.2 percentage points, sustains a widening margin when scaling to 128 clients across eight cells, and reduces the schedule-averaged per-client uplink model-update payload by 95.6% (approximately 96%), while keeping the 95th percentile (p95) of the round-critical uplink completion time near 1.5s.

In the kernel regime, neural-network learning inherits its preferences from a frozen spectrum. During feature learning, this spectrum evolves, yet networks retain systematic biases toward simple, smooth directions. We develop a function-space statistical framework explaining the origin of these preferences, treating functions and their learning operators as macroscopic variables, with parameterization entering through the multiplicity of parameter configurations realizing each function. For mean-squared loss, error relaxes exactly under the evolving learning operator $M=JJ^\ast$. Training stochasticity induces a Gaussian weight over function-space states, while parameter multiplicity contributes an entropic operator $B$, defined by the curvature of its log multiplicity. A local Laplace expansion yields the fluctuation free energy $\Phi_{\mathrm{fluc}}(M;B)=\frac{\sigma_\xi^2}{2}\log\det(M^{-1}+B)+\mathrm{const}$, analogous to an Occam factor. Under mild statistical conditions, this free energy is rotationally stationary exactly when $[M,B]=0$, is minimized by pairing large eigenvalues of $M$ with small eigenvalues of $B$, and generates a local restoring force against mismatch. Learning is therefore biased toward faster relaxation along entropically cheaper directions. This preference strengthens with training noise and vanishes in the deterministic limit, beyond gradient-flow accounts of operator alignment. For ReLU networks, we relate entropic curvature to the minimal rearrangement of activation boundaries required for a functional change and bound this structural cost by directional smoothness. Consequently, smooth directions are preferentially learned faster, in a data-adaptive manner, even as the learning operator evolves.

Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical objectives such as cost and service quality. Existing optimization and reinforcement learning methods are effective for fixed formulations, but often depend on task-specific representations and constraint handling. We propose CityPlanner, a sandbox-agent framework for executable urban planning. CityPlanner introduces UrbanSandbox, a unified file-based environment where agents inspect task files, generate plans, run evaluators, and revise decisions based on executable feedback. To make learning tractable, we further propose atomic-task reinforcement learning, which decomposes long sandbox trajectories into BuildPlan for initial construction and ImprovePlan for feedback-based refinement. Experiments on a real-world benchmark show that CityPlanner consistently outperforms heuristic, task-specific RL, and general LLM-agent baselines. Ablations verify the contributions of UrbanSandbox, atomic-task RL, and iterative deployment. We release the code and dataset at https://anonymous.4open.science/r/co-agent-C1C8

Myocardial strain from echocardiography is a key biomarker for cardiac function. Recent deep learning methods show strong performance for myocardial motion tracking but often lack physiological constraints, leading to temporal drift across the cardiac cycle. Consequently, tracked points may not return to their relative initial positions at the end of each cardiac cycle, producing inaccurate strain estimates and even divergence in some cases. We propose a deep learning framework that compensates for drift during myocardial tracking. We extend a state-of-the-art echocardiographic tracking method (TAS-Net) with persistent memory tokens that share information across sliding windows over full cardiac cycles. A teacher-student fine-tuning strategy on real echocardiographic data then enforces physiologically consistent cyclic motion while preserving tracking accuracy. Experiments show reduced global and regional strain drift, improved agreement with clinical references, and better test-retest reproducibility, supporting more reliable myocardial strain estimation in clinical practice.

Synthetic data has become a promising way to scale model training beyond limited human-generated data but it may also induce strong model collapse (Dohmatob et al., 2024), where any fixed fraction of synthetic data prevents model performance from improving under data scaling, leaving a non-vanishing excess risk floor. In this paper, we study how synthetic data affects the generalization of one-pass SGD in high-dimensional linear regression with model shift. We establish finite-sample risk bounds for mixed and two-stage training, separating standard bias and variance from source-mismatch effects, namely fluctuation and persistent drift under mixing and filtered initialization bias under two-stage. These bounds reveal a sharp contrast: mixed training induces strong model collapse, while two-stage training avoids the floor by using synthetic data only in the first stage, showing that collapse is not inevitable under a simple data curriculum. Under a random sketch model, we further obtain scaling laws for both protocols, with tight results for mixed training in the optimization-saturated regime. These laws show that larger models may amplify synthetic-induced degradation under mixing, and quantify how high-quality synthetic pretraining may reduce bias in two-stage training. Finally, we establish an exact finite-sample necessary-and-sufficient condition for two-stage training to strictly outperform real-only training under the same real-data budget and identical real-stage updates. Overall, our results highlight that synthetic data is neither inherently harmful nor beneficial; its effect depends critically on both its quality and the training protocol used to incorporate it.

Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existing methods either employ a single agent or orchestrate multiple role-based agents to reason and learn over the entire graph, but both essentially rely on a shared reasoning policy across different graph regions, which can be suboptimal for graphs with heterogeneous structural and semantic patterns. Inspired by the progress of multi-agent collaboration on complex reasoning tasks, a natural remedy is to let multiple agents own different memory and collaborate; however, applying this paradigm to graphs directly faces two challenges. First, existing AGL methods typically verbalize graph structures into natural-language descriptions for LLM agents, making the reasoning process sensitive to the ordering of structural information and thereby breaking the permutation-invariant nature of graphs. Second, incorporating increasingly large sampled neighborhoods leads to rapidly growing contexts. To address these challenges, this paper introduces a multi-agent agentic graph learning (i.e., MAAGL) framework. MAAGL partitions the graph into communities and assigns an independent agent to each community for region-specific specialization. MAAGL represents structural and semantic evidence separately. Structural evidence is summarized by a dynamically updated structural signature that is permutation-invariant and fixed in size, while semantic evidence is filtered to the top-k nodes ranked by relevance. Based on historical trajectories with similar signatures, agents estimate their confidence and trigger debate-style collaboration when needed. Extensive experiments on four benchmark datasets show that MAAGL outperforms SOTA AGL methods.

This study evaluates Vibe Coding, an emerging AI-led conversational programming paradigm that enables developers to generate software through natural-language interaction with large language models. Using a mixed-methods design, the study assessed performance efficiency, cognitive implications, and responsible adoption in comparison with traditional and AI-assisted coding environments. Thirty participants, including professional developers and advanced computing students, completed equivalent programming tasks under three experimental conditions. Quantitative data were analyzed using descriptive statistics and repeated-measures ANOVA, while qualitative data were examined through thematic analysis. Results show that vibe coding significantly improved development efficiency, reducing task completion time by 27% compared with traditional coding and 12% compared with AI-assisted coding. However, these gains were accompanied by lower maintainability indices and higher security vulnerabilities, indicating trade-offs in software quality. Usability results yielded a good rating (SUS = 71.4), while cognitive workload remained moderate (NASA-TLX = 55.5), reflecting reduced syntactic effort but increased linguistic reasoning. Thematic analysis identified trust calibration, loss of control, cognitive adaptation, and prompt-engineering strategy as key constructs. Notably, perceived loss of control was associated with increased security risks due to reduced transparency and validation of AI-generated outputs. Based on these findings, the study proposes a three-pillar framework for responsible adoption: hybrid integration of human and AI capabilities, human oversight and transparent accountability, and context-aware deployment. Overall, vibe coding enhances productivity but requires critical oversight, reinforcing its role as a transformative yet transitional paradigm in software development.

Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear accessibility of simultaneously active features. By framing linear accessibility as a compressed sensing problem, we derive high-probability bounds for fixed supports under subgaussian noise, proving the sufficient dimension scales linearly ($d=O_{\varepsilon}(k \log m)$) rather than prior worst-case quadratic limits. We characterize the asymmetry between active and inactive interference and the trade-off between interference and observation-noise budgets. We then validate these bounds across system parameters through Gaussian-tail approximations. We also introduce IHT-SAE, which uses learned iterative refinement to improve feature recovery beyond the limits of linear availability. These results quantify the geometric constraints of the linear representation hypothesis, providing a framework for evaluating sparse autoencoders, compositional generalization, and neural interpretability.

Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypasses that allow an adversarial user to elicit unwanted or harmful outputs from models. Arbitrary cipher, or covert communication, attacks are one such type of jailbreak and have previously been demonstrated against the fine-tuning APIs of commercial models. In these attacks, target models are trained on a corpus of encrypted harmful questions and responses and subsequently respond to harmful requests through the learned encryption scheme. In this paper, we show that newer frontier models do not require fine-tuning to acquire cipher-based communication skills. Instead, they can learn these skills through prompting and, when necessary, through in-context learning. Furthermore, model alignment is significantly weakened or entirely bypassed when communication occurs through the learned cipher. To the best of our knowledge, this constitutes a novel attack vector against commercial black-box large language models. We demonstrate successful jailbreaks against frontier models developed by Anthropic, Google, and OpenAI. Our attack bypasses commercial harmfulness classifiers because harmful content is encrypted and therefore appears as nonsensical text or gibberish.

Sample size determination for machine learning (ML) prediction models is challenging because conventional power analysis typically requires the predictor-outcome relationship and effect structure to be specified a priori. Nonlinear ML models learn complex prediction surfaces that do not admit straightforward analytical power calculations. We propose a framework that approximates nonlinear ML models with localized linear representations and estimates sample size requirements by evaluating statistical power across these local regions.

Agent memory systems update state decisions from reports whose reliability may be unknown. Existing analyses of source estimation do not determine when a policy can be learned or its improvement certified without identifying the reporting channel. We study these three tasks using the same observed records. For a specified hidden Markov family with continuous source uncertainty, decision learning and powered certification have quadratic sample complexity, whereas fixed-precision source estimation has quartic complexity. We characterize a sharp identified interval for policy gain under an unknown shared-background channel and derive finite-sample certificates under bounded history dependence and conditional copying. Independently trained witness regions support general history spaces, and disagreement-conditioned auditing improves power for sparse revisions. For dependent histories, prediction-count-preserving batches cancel the unknown reporting background and admit conditional certificates. A MultiWOZ 2.4 evaluation uses text-processing policies on 1,000 human-written test dialogues with simulated audits. Balanced batches retain 2.26 percentage points of the full candidate's 7.34 percentage-point mean gain and obtain more positive certificates under weak audits. These results establish task-specific information requirements and provide an auditable policy-revision framework for Nous.

Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from new interactions. In open-ended environments, this motivates self-evolving agents that continually update reusable state-including model parameters, memories, tool definitions, skills, and workflows-from data, feedback, and accumulated experience. This shift changes the safety problem: once experience becomes reusable state, past events become future causes, and information harmless in one context may later influence decisions with greater persistence, authority, or scope. Self-evolving agent safety therefore asks not only whether a response is aligned or an action authorized, but whether safety properties survive the accumulation, generalization, and cross-context reuse of locally useful experience. We introduce SAVER, a transition-centered framework in which Substrate locates reusable influence, Adaptation captures how it changes, Violation identifies compromised safety attributes, Exposure marks where failures become observable, and Response assesses containment, repair, or revocation. Our survey reveals that failures need not originate from harmful information: legitimate state can become unsafe when adaptation expands its persistence, authority, or scope beyond the conditions under which it was valid. Existing work provides comparatively strong evidence for admission, retrieval, activation, exposure, and local containment, but much less for descendant repair and evaluation after adaptation resumes. We therefore argue for longitudinal evaluation that traces unsafe influence to its originating transition, verifies repair across descendants, and tests whether it can re-emerge under continued evolution.

Data agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of columns, so cost constraints may require choosing between table coverage and serialization detail well before the context window is full. We introduce BudgetSchemaBench, an execution-grounded diagnostic for this setting. Its construction derives relevance labels mechanically from gold SQL, without human- or LLM-authored ground truth. Using a pooled 80-database catalog, we sweep four schema-context budgets and compare three representations while keeping each retriever's table ranking fixed. A source-namespace check rejects queries that obtain the correct result from the wrong database. The evaluation covers three conditions: end-to-end retrieval; frozen-gold, in which the required tables are guaranteed; and a probe that removes those tables. For the primary solver with raw serialization, raising the budget from 2.5% to 50% of the catalog improves execution accuracy on 1,279 held-out questions by 18 percentage points under lexical retrieval but only 3 under dense retrieval; the dense retriever already finds most required tables at the smallest budget. When the required tables are removed, 94.6% of correct predictions name one of them exactly, consistent with reconstruction of absent schema from parametric knowledge. For the two main solvers in the frozen-gold condition, the three representations differ by at most 2 percentage points, and the widest paired 95% confidence interval bounds the difference within +/-4 points. We observe the same qualitative patterns with one reasoning model from a different family. When retrieval is coverage-limited, execution accuracy is more sensitive to the schema budget than to the tested serializations. The diagnostic and the code used to construct and evaluate it are publicly available.

AI-generated text detectors achieve high accuracy on standard benchmarks, yet the internal representations that drive these predictions remain poorly understood. We study which neurons in a frozen BERT-base-uncased encoder support AI-text detection, using the RAID benchmark across six generators spanning pure-base and instruction-tuned models. We apply the L1-to-L2 sparse-probing protocol of Gurnee et al. (2023) to all 9,216 CLS hidden-state dimensions (12 layers x 768), which we call neurons. The procedure recovers a stable set of under 1% of neurons per generator, consistent across folds and seeds; a probe restricted to that set retains most of the full-feature detection accuracy. Bidirectional activation patching confirms this set's causal relevance: in both directions it flips predictions an order of magnitude more often than size-matched random sets. Mean-ablating the same neurons leaves accuracy largely intact; the signal is therefore redundantly distributed. Cross-generator analysis reveals a bipartite structure: instruction-tuned generators concentrate 30-36% of stable neurons in BERT's final layer while both base generators fall below 14%, consistent with a layer-12 footprint of post-training alignment. Leave-one-family-out evaluation shows the selected neurons retain 86-94% of the full-feature ceiling on unseen generator families, so a detector can operate on a small fixed subspace without re-identifying neurons per generator.

Short-term forecasting of cloud-induced power ramps across a network of distributed photovoltaic (PV) or irradiance sensors is a recognised pain point for grid operators. A natural idea is to make the graph neural network (GNN) advection-aware: connect each site to the sites upwind of it, with edge time-lags set by the cloud-motion vector (CMV), so that a ramp is propagated forward before it physically arrives. Using a controlled synthetic testbed with a known wind field, we show that (i) with a realistic cross-correlation CMV estimate, an explicit advection graph does not beat a plain static or learned-adjacency spatiotemporal GNN; (ii) roughly half of the benefit available from a perfect CMV comes simply from providing an accurate motion vector as an input feature, not from graph structure; and (iii) advection helps only when the advective displacement over the forecast horizon, v*H, fits inside the sensor network. Motivated by (ii), we introduce a small self-supervised cloud-motion estimator – a position-aware encoder trained only on a multi-lag optical-flow reconstruction objective with an annealed kernel – that recovers the true wind vector to 2-4 degrees median angular error, 2-4x better than the classical cross-correlation method across every wind regime. Freezing this estimator and feeding its vector to the forecaster closes about 60% of the oracle-CMV RMSE gap at moderate wind (8-15% RMSE reduction over no advection), with no external wind data. We also report a negative result for a spatially-coherent probabilistic head. All claims are established on a single synthetic simulator; we discuss why real-network validation is the necessary next step and outline it.

Radar pulse de-interleaving is a foundational Electronic Support Measures (ESM) task that aims to separate chronologically interleaved pulse streams from multiple non-cooperative transmitters under unknown emitter cardinality in dense, contested electromagnetic environments. Classical histogram transforms and closed-world deep classifiers degrade under severe pulse loss, agile Pulse Repeti tion Interval (PRI) modulation, and spurious clutter. In this paper, we systematically characterise continuous temporal representations and physics-guided model selection in deep metric learning for open-world radar de-interleaving. Building on the transformer-based metric-learning framework for open-world deinterleaving introduced by Gunn et al. [1], we introduce a continuous Time-of-Arrival (ToA) sinusoidal positional encoding that directly models physical inter-pulse durations rather than ordinal token indices, a design choice that contrasts with [1], who found ordinal positional encodings provided no benefit and omitted them entirely. Neural network parameters are optimised solely via Supervised Contrastive (SupCon) learning, while scale-aware physical domain priors based on PRI Consistency and Angle-of-Arrival (AoA) continuity serve as physics-guided validation and checkpoint-selection criteria operating on unsupervised HDBSCAN cluster assignments.

We present a multimodal foundation model for lunar remote sensing, pretrained from scratch on SomBench, a geographically partitioned corpus of nearly two million co-registered tile bundles spanning 11 modalities at two spatial scales (1 m/pixel and 100 m/pixel). The model adapts the TerraMind masked-token architecture with two lunar-specific extensions: acquisition geometry is provided as explicit context, and meter- and hundred-meter-scale tiles are trained jointly so that a single set of weights covers both resolutions. FlexiViT patch embeddings allow adaptation to different patch sizes without retraining, while modality-wise inputs enable flexible multimodal fine-tuning. Qualitative generation experiments suggest the model learns meaningful cross-modal correspondences, including terrain derivatives from elevation and illumination-consistent reflectance from geometry. We evaluate on four benchmarks: crater detection at WAC and NAC scales, irregular mare patch (IMP) segmentation, and polar ice prospectivity regression. Across tasks, the pretrained model matches or outperforms ImageNet-pretrained baselines and an architecturally identical random-init control. On multimodal ice prospectivity regression, pretrained variants achieve the best results, while the random-init model outperforms most baselines, suggesting gains arise from both the architecture and pretraining. Label efficiency is notable for WAC crater detection, where the pretrained model trained on 50% of the data exceeds the strongest ImageNet baseline trained on the full dataset. Among adaptation strategies, LoRA matches or surpasses full fine-tuning on crater detection and IMP segmentation while using far fewer trainable parameters, whereas full fine-tuning performs best for ice prospectivity regression. We release the pretrained checkpoint, benchmark datasets, and fine-tuning code to support reproducible lunar AI research.

Generative artificial intelligence (AI) tools are increasingly accessible and have the potential to improve efficiency across clinical workflows. However, clinicians may also use non-institutional AI tools that are not provided, managed, or governed by their healthcare institutions, creating potential concerns related to privacy, security, accuracy, and clinician-AI interaction. Little is known about how clinicians currently use these tools for work-related tasks. We conducted a descriptive survey of clinicians recruited from the University of Arizona College of Medicine-Tucson and Banner University Medical Center-Tucson between May 20 and June 26, 2026. Participants reported their use of AI tool categories and the frequency with which they used AI for specific tasks across five workload categories: administrative work, clinical work, research, studying/continued education, and teaching. Forty-four respondents completed the survey. Forty-three respondents reported using AI for at least one work-related task during the preceding 6 months. Conversational AI and clinical decision support/diagnostic AI were the most used tool categories, each reported by 28 respondents. Administrative and clinical tasks demonstrated the most frequent use. AI was also used for higher-risk activities, including diagnostic assistance and clinical decision support. Non-institutional AI use was common among surveyed clinicians and extended across a broad range of work-related activities, including tasks with potential implications for clinical reasoning and patient care. Further research is needed to characterize how clinicians use these tools, how they evaluate AI-generated outputs, and how AI can be safely and effectively integrated into clinical workflows.

An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software engineer. Vendors ship harnesses tuned to their own models, and practitioners assume the vendor-native pairing solves more tasks. We measure that assumption with paired same-model contrasts on a private, contamination-controlled suite of 256 repository and post-cutoff contest tasks. The same 80 tasks ran under claude-agent-sdk and under deepagents on claude-opus-4-8, and under the openai-codex SDK and deepagents on gpt-5.5, with gemini-3.5-flash and deepseek-v3.2 as side cells. 792 of 800 planned runs were graded by an isolated oracle. Neither contrast resolves an average advantage for either harness: -1.25 pp for Opus 4.8 (48.8% vs 50.0%, task-bootstrap 95% CI [-10.0, +7.5]) and +1.25 pp for GPT-5.5 (55.6% vs 54.4%, CI [-4.4, +6.9]). The Opus average combines opposite strata: the native harness trails by 9.0 pp on the 61 repository tasks and leads by 23.7 pp on the 19 contest tasks (label-permutation p = 0.003). The partition was chosen after seeing the data and needs a designed replication. Correctness and completion also separate: 22 of 81 runs cancelled at the wall-clock ceiling had produced a passing patch. Re-priced from raw per-turn usage at frozen list prices, the neutral harness cost 1.3 to 1.6 times as much per solved task on Opus 4.8 and 1.2 times on GPT-5.5. These are observed-usage estimates. On the Anthropic account 58 runs left no usage record, and allocating that spend to either cell would move the Opus ratio between 0.7 and 2.3, so the billed ordering is unresolved. This revision corrects an August 2026 manuscript whose cost figures rested on a usage-semantics defect in our own telemetry (Section 5.1). We release the orchestrator, grading oracle, reanalysis code and derived aggregates. The tasks stay private.

Physical-layer authentication (PLA) in non-terrestrial networks (NTNs) is challenged by severe Doppler shifts, long delays, and fast channel variations, which cause distribution shifts and degrade conventional learning methods. Existing PLA schemes often rely on single features or generalize poorly to unseen environments. This paper proposes a secure adaptive framework for authentication in multi-zone networks (SAFA-MZ), a causal meta-learning framework for distributed PLA (DPLA) in NTNs. First, we design a multi-feature fingerprint that combines spatial, angular, combiner, subspace, and Doppler-delay features. The fingerprint is adaptive and distributed, as it fuses heterogeneous physical-layer features and measurements from multiple aerial nodes. Second, we formulate a structural causal model (SCM) to capture the relations among design choices, environmental factors, extracted features, and authentication outcomes. Third, we develop a model-agnostic meta-learning (MAML) strategy with invariant risk minimization (IRM) and causal consistency regularization for fast adaptation to unseen NTN environments with few labeled samples. Fourth, we propose a two-stage authentication scheme that performs local recognition and activates time-difference-of-arrival (TDOA) localization with a graph attention (GAT) network only when needed, which reduces backhaul overhead. Simulations show that SAFA-MZ achieves 92% accuracy and 96% AUC, outperforming centralized deep learning and single-feature baselines across diverse environments.

In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional Token (FT) or provide function schemas directly in the prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-Prompt (SIP) can generalize to unseen functions at the cost of longer prompts and higher inference overhead. We introduce a benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, and the highest Seen accuracy in our main grid occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with a higher inference cost, chiefly the latency of processing the schema prompt. Our theoretical analysis formalizes why only SIP can predict functions withheld as training targets and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.

Physical-layer authentication (PLA) in non-terrestrial networks (NTNs) has primarily been studied from a security perspective, while its system-level integration with communication remains less explored. We propose the secure adaptive framework for authentication in multi-zone networks (SAFA-MZ), a system-level formulation for the joint management of collaborative group-tag and private-data delivery in NTN, where high-altitude platform station (HAPS) placement, user association, and transmission powers are jointly selected under service and secrecy constraints. Group-level authentication tags and user data are collaboratively transmitted by multiple HAPSs, with artificial noise (AN) mitigating information leakage. We jointly optimize HAPS placement, user association, and power allocation to balance deployment regularity, tag distribution, and user-rate fairness under secrecy, quality-of-service (QoS), power, and coverage constraints. The problem is addressed using a repair-based cross-entropy method (RCEM) and a graph-aware advantage actor-critic (A2C) algorithm (GA2C). Under colluding and non-colluding eavesdropper models, GA2C improves average secrecy spectral efficiency (SSE) by 135–139% over its single-connect baseline and 21.1–23.2% over its baseline without AN. Across ten independent random seeds, GA2C achieves approximately 23.4% and 17.9% higher mean per-user SSE under non-colluding and colluding eavesdropping, respectively, and a 16.2% higher mean private-rate Jain's index than RCEM. These results quantify the gains of multi-node connectivity and AN within the proposed framework under the evaluated assumptions.

As LLM agents move from answering questions to carrying out procedures, failures can be unwarranted rather than visibly wrong: the final response looks acceptable even though the system skipped the check, branch, dependency, or invariant that made the answer justified. Output-only evaluation sees the answer, and trace-aware judging sees activity, but neither identifies which obligations were active for the query. We introduce CONTRACTEVAL, a diagnostic framework for making those active obligations explicit. It represents procedural instructions as query-active obligations and matches them against response or trace evidence, turning omissions, wrong branches, ordering errors, extra actions, invariant breaches, and output-contract violations into distinct conformance failures. On a controlled suite of audited procedural contracts, output-only and trace-aware LLM judges miss many injected structural failures; under gold expected and observed graphs, ContractEval detects and localizes all of them. LLM-backed extraction preserves much of this signal but remains calibration-sensitive. ContractEval is therefore not a compliance guarantee; it makes procedural conformance auditable rather than implicit in final-answer quality.

As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. In comparison to the traditional machine learning systems, agentic workflows have complex failure modes with planning, tool invocation and dynamic environment interactions. In this paper, we investigate whether model's internal representations provide stronger signals of eventual task success in multi-turn agentic setups. We introduce two complementary methods: Latent Trajectory Dynamics (LTD), which summarizes changes in residual-stream representations across an interaction trajectory, and the Action Representation Probe (ARP), which predicts success from representations formed at action decisions. Across three interactive benchmarks (Bash, SQL, Python) and three model families (Qwen14B, Qwen7B, DeepSeek6.7B), our methods consistently outperform surface level generation and sequence-based calibration baselines providing a zero-overhead reliability monitor that requires neither prompt alterations nor multi-sample rollouts.

Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N^2). We propose a leakage-free, block-based approach that shares NAS runs across subjects. On the BioVid Heat Pain dataset, our approach increased the mean accuracy from 82.79% to 83.39% while reducing the number of parameters by up to 99.2%.