Papers

On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally regardless of their informativeness. We observe a consistent asymmetry in controlled filtering experiments: in both OPD and on-policy self distillation (OPSD), training only on incorrect SGOs outperforms training only on correct ones. Our further analysis suggests that models trained on correct-only SGOs tend to generate shorter reasoning traces and show weaker reflection behavior, while incorrect SGOs better preserve exploratory reasoning near the model's capability boundary. To exploit this signal without requiring full answer-containing rollouts, we introduce ReNIO, which Reweights Negative trajectory Importance for LLM On-policy distillation. By using the student-to-teacher probability ratio, ReNIO identifies pivotal tokens leading to wrong reasoning traces and aggregates their information into a normalized sample weight, inherently assigning larger weights to likely negative trajectories without observing the correctness of final-answer. Since Re-NIO only uses prefix-conditioned token probabilities, it preserves OPD's prefix training advantage over full-rollout reinforcement learning. Across both mathematical reasoning and code generation tasks, ReNIO improves both OPD and OPSD, with representative relative gains of up to 8.90% for Qwen3-1.7B and 10.00% for R1-Distill-Qwen-7B on mathematical reasoning benchmarks. Code repo: https://github.com/BDML-lab/ReNIO.

As AI systems become increasingly persistent and personalized, they make possible a class of technologies that we call cognitive digital twins (CDTs): dynamic computational representations of a specific person's cognition, updated from behavioral, contextual, or physiological data in order to model, predict, or simulate that person's cognition, or to act as that person's communicative or decision-making proxy. CDTs combine cognitive inference with longitudinal representation, simulation, and proxy action in ways that existing governance strategies for personal assistants, autonomous agents, recommender systems, and automated decision systems only partially address. This paper makes four contributions. First, we define CDTs and distinguish them from adjacent systems. Second, we introduce a 5A governance framework organized around authority, autonomy, access and control, accountability, and availability. Third, we identify CDT-specific risks, from misrepresentation and epistemic authority shifts to shadow twins, simulated participation, proxy action, and proxy-power asymmetries. Fourth, we analyze governance gaps and propose requirements for high-risk CDTs that strengthen consent, purpose limitation, validity, traceability, contestation, independent review, and model retirement. Existing frameworks primarily regulate data processing, automated decisions, or autonomous actions; CDTs also require governance at the level of cognitive representation itself, before any final decision or external action occurs. We argue that CDTs require governance not only because they can act for people, but because they can become infrastructures through which cognition is represented, simulated, classified, and operationalized.

Wireless sensor network (WSNs) stands out as a burgeoning and promising domain in intelligent sensing. Owing to various factors such as sudden sensor malfunctions or deliberate shutdown of partial nodes to save energy, the collected sensing signals from WSNs commonly have massive missing data, leading to adverse effects on subsequent analysis or decision-making. Latent factor learning (LFL) has proven to be highly effective in recovering the missing data for WSNs. However, the existing LFL models require the collected sensing signals to be maintained in one central place like a central server, which is becoming unacceptable for data owners who are getting increasingly privacy-sensitive. To address this issue, this paper innovatively proposes a federated latent factor learning (FLFL) model for privacy-preserving spatio-temporal signal recovery. Its main idea is two-fold: 1) it designs a sensor-level federated learning framework based on LFL, where each sensor only needs to upload gradient information rather than raw data for training a privacy-preserving recovery model, and 2) it incorporates the spatio-temporal correlation into the designed federated learning framework as the regularization constraint to improve its recovery accuracy. With such designs, FLFL can not only accurately recover the missing data of WSNs but also ensure data owners' privacy-preserving of raw data. To evaluate the proposed FLFL model, extensive experiments have been conducted on four real-world WSN datasets. The results demonstrate that FLFL significantly outperforms eight state-of-the-art federated and non-federated signal recovery models in terms of recovery accuracy with privacy-preserving.

Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substantial computational overhead. Reusing a cached plan reduces this overhead, yet its effectiveness depends on how prediction mismatch propagates through the local dynamics. We analyze this trade-off with a perturbation-based dynamic-regret framework and show that stale-plan penalties scale with the reuse tolerance, the accumulated mismatch since the last replanning step, and the local dynamics sensitivity. Based on this structure, we propose AdaReP, a training-free wrapper that adapts the replanning tolerance online using the current deviation from the cached rollout and a local sensitivity estimate, without modifying the learned world model or planner. Across image-space planning, latent-space control, and real-world robotic manipulation, AdaReP substantially reduces planner-side computation while maintaining comparable task performance, including over 80% fewer queries on a 50-trial physical robot study.

Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversarial influences become permanently encoded, self-amplify across generations, and propagate through populations without sustained attacker access. We present a systematic security and privacy analysis organized around the Module-Lifecycle Attack Surface (MLAS) matrix, which decomposes the attack surface into five functional modules (Brain, Cognitive Resource, Execution, Self-Design, Collective) $\times$ five lifecycle stages (Bootstrap, Propose, Evaluate, Commit, Serve). Analysis of the resulting 25 cells reveals that 17 face critical threats for which no effective partial mitigation. We identify seven cross-cutting amplification effects that interact synergistically and cannot be addressed by securing individual modules in isolation. Comparative case studies of two open-source frameworks demonstrate that evolution-native design activates $3.5\times$ more attack surface cells and achieves a 100% attack persistence rate (40/40 payloads across all CIA+Privacy categories), while co-located security scanners block only 2.5% of attacks. Our findings establish that self-evolution converts every known attack category from session-bounded to lineage-persistent, gives rise to entirely new attack classes, and renders static defenses structurally inadequate, motivating evolution-aware security frameworks and formal verification for self-modifying systems.

Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instructions, yet continual fine-tuning often causes severe forgetting of previously acquired multimodal skills. Existing continual vision-language methods mainly preserve outputs, replay data or pseudo-data, regularize embedding geometry, or allocate task-specific parameters, but they provide limited control over how internal cross-modal attention patterns supporting old skills drift during adaptation. We propose Attention-Spectrum Regularization (ASR), a replay-free continual learning framework that preserves skill-conditioned structures of cross-modal attention. ASR treats cross-attention maps as two-dimensional signals, summarizes their scale and directional properties into compact spectral statistics, and stores only skill-wise prototype distributions instead of replaying past image-question pairs, generated pseudo-examples, or old-stage teacher snapshots. In later stages, a phase-invariant spectral regularizer constrains harmful drift of these prototypes while allowing instance-level attention to adapt to new tasks. We provide theoretical analysis showing that skill-conditioned spectral drift controls forgetting under a spectral sufficiency assumption, and that Fourier power spectra are stable to spatial translations and bounded perturbations. Experiments on continual VQA and multimodal instruction-tuning benchmarks, including VQA v2, VQACL, CLT-VQA, CoIN, and UCIT, show that ASR consistently improves final performance and reduces forgetting over strong replay-, regularization-, and adapter-based baselines. Preserving skill-level attention structure is an effective and lightweight mechanism for continual MLLMs. Code is available at https://github.com/Creative-zcx/attention-spectrum-replay

Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a reference motion. However, existing models often generate instructions that exhibit motion hallucinations, failing to reflect actual kinematic differences between paired videos. To systematically investigate these hallucinations, we introduce MotionHalluc, a dedicated benchmark for evaluating motion hallucinations in paired-video comparison. MotionHalluc comprises 1540 fine-grained questions over 553 video pairs, evaluating hallucinations along three core dimensions: (1)directional hallucination, (2)attributional hallucination, and (3)temporal hallucination. Extensive evaluations of state-of-the-art large multimodal models demonstrate high susceptibility to these hallucinations. Furthermore, we provide Perceive-Parse-Verify (PPV) as a training-free measurements extraction and verification baseline that converts candidate instructions into executable measurement queries and supplies kinematic measurements at inference time. Our results show that this simple measurements injection yields an average 10.6% performance gain across models, suggesting that motion reasoning with explicit quantitative measurements is a key factor in reducing hallucinations in cross-video comparison. Our code and dataset are available at https://github.com/Leocoding0971/MotionHalluc.

Hallucinations of ASR models - fluent transcriptions with no basis in audio - degrade system performance and pose risks in downstream applications. Robust detection of such errors remains a challenge. This paper studies Whisper large v3 hallucination detection on real-speech human-annotated data across three paradigms: text-based, LLM-based, and internal decoder state probing. Text classifiers utilizing metrics for text evaluation achieve high recall but degrade without reference transcripts. LLM-based detection improves precision with domain-specific prompt conditioning, yet remains less competitive than the lightweight text-based methods. Probing Whisper's decoder representations, without a ground-truth reference, yields the strongest performance, revealing that hallucination traits are encoded across intermediate decoding layers. A late-fusion meta-classifier combining text and internal-state outputs achieves the best overall detection performance.

This paper studies the expressive power of ASPIC$^+$ argumentation frameworks with uncertain preference profiles by comparing them with several abstract formalisms with uncertain defeats. Most of our results are negative (and some of them are theoretically unexpected). We also conjecture a positive, non-trivial threshold for the expressivity of uncertain preferences, and prove some essential preliminary steps toward the confirmation of this conjecture.

Predictive modelling of triboelectric nanogenerators (TENGs) remains fragmented across analytical theories, finite-geometry solvers and disconnected simulation workflows. These disparate approaches must be unified into an executable framework to advance quantitative TENG research.Here we introduce a charge-defined modelling framework and implement it as TENG-CLAW, a physics-governed platform for traceable TENG simulation. The framework establishes a self-consistent electrostatic hierarchy in which triboelectric charges, pre-charging charges and compensating electrode charges serve as defining state variables.This hierarchy connects the infinite plate analytical limit for near-uniform fields with finite-geometry numerical formulations required for edge-dominated devices. Built on this basis, TENG-CLAW converts user-defined research requests into physically admissible simulation tasks, so that generated outputs are tied to explicit charge states, boundary conditions, solver routes and reusable artifacts across spatial, temporal, field-level, comparative and reporting workflows. This work establishes a rigorous computational basis for interpreting TENG mechanisms and provides reproducible research infrastructure for simulation and physics-guided device design.

Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matters at deployment, real devices running real apps, is slow, stateful, side-effectful, and hard to reset or verify, while scalable mock environments only approximate real behavior. We present PhoneBuddy, a training recipe and open-model line for agentic phone use that combines a real-app environment with a mock-app environment, PhoneWorld, which reconstructs runnable mock apps from real GUI usage structure. PhoneBuddy first builds a shared supervised fine-tuning stage from trajectories collected in both environments, then compares real-app RL against mixed RL across both environments. Across a 150-task human evaluation on real phones spanning apps, mini-apps, and cross-app workflows, task success rate improves from 36.67% after supervised fine-tuning to 40.67% after real-app RL and 45.33% after mixed RL. On AndroidWorld, the same progression rises from 60.3% to 77.2% to 83.2%. These results show that mock-app training is not a replacement for real-app RL, but a complementary source of scalable, resettable, and automatically checked interaction. The gains are strongest on app and mini-app tasks, while long-horizontal cross-app workflows remain an important open challenge.

End-to-end Automatic Speech Recognition (ASR) systems hallucinate on natural speech, yet existing mitigation methods are typically evaluated on non-speech or artificially corrupted audio. We introduce HALAS, the first human-annotated dataset of naturally occurring hallucinations from seven state-of-the-art ASR models on real unprocessed earnings call recordings. HALAS provides span-level labels, enabling analysis of hallucination patterns and their severity. Our analysis reveals strong cross-model vocabulary overlap and confirms that hallucinations also occur for almost correctly transcribed speech (characterized by a low Word Error Rate). The proposed benchmark with HALAS shows that the character and semantic-level metrics used as a proxy for hallucination detection reach 81% ROC-AUC, while state-of-the-art detection methods achieve an F1 score of only 53.1%. As such, HALAS establishes the first rigorous non-artificial benchmark for the detection and mitigation of ASR hallucinations.

The deployment of data-driven models in 6G wireless networks is increasingly challenged by frequent distribution shifts that degrade performance over time. Unsupervised Domain Adaptation (UDA) offers an alternative approach by adapting the trained model to a shifted domain without requiring labels. However, UDA pipelines are often more complex than single-task training due to additional modules and optimization procedures, raising a practical question: do the benefits of adaptation come at a higher energy cost, and how does this trade-off compare to retraining when labeling effort is also considered? In this work, we investigate the energy consumption of UDA and compare it to single task. We further propose a way to determine the minimum number of target domains for which UDA becomes more energy-efficient than retraining, taking into account the labeling cost. Our results aim to clarify when UDA should be preferred over classical train-from-scratch approaches from an energy and labeling-aware perspective.

Numbers have algebraic structure that standard neural embeddings often fail to expose. We introduce Prime Fourier Embeddings (PFE), which encode integers as prime-indexed (cos, sin) pairs derived from the harmonic analysis of Q, providing a pre-structured representation in which modular arithmetic reduces to selecting the relevant prime channel rather than discovering algebraic structure from scratch. We prove that any linear map equivariant with respect to the product group action on PFE must be block-diagonal with one independent block per prime – a consequence of Schur's lemma applied to the resulting character decomposition. For square-free composite moduli, the Chinese Remainder Theorem predicts which prime channels are task-relevant. Both predictions are confirmed empirically: ablation studies show specialization ratios exceeding 500x between task-relevant and task-irrelevant channels, with perfect in-distribution test accuracy across all square-free composite moduli tested.

Most instruments for measuring political positions, such as manifesto coding, expert surveys and text-scaling models, were built and validated on Western party systems, and they break down worst where many consequential actors never publish a manifesto, never contest a competitive election, or commit one position to a charter and act on another in office. This paper proposes a method for such settings. I treat a large language model as a single fallible rater in a panel, the way an expert survey treats one expert, and describe the panel, its synthesis, an applicability rule that keeps a blank distinct from a zero, and a lens that separates what an actor declares from what it does. Three results follow. First, a built-in experiment isolates the rubric: with a definition-free round held fixed, written axis definitions move scores by a mean of 1.8 points on a 21-point scale and tighten agreement between raters (mean absolute gap 2.81 to 2.50; r 0.81 to 0.89). Second, across nine models from eight laboratories in two countries, Krippendorff's alpha is 0.86 on an interval and 0.87 on an ordinal metric, and it held as the panel grew from five raters to nine. This is reliability and says nothing yet about validity, since models trained on overlapping data can share a bias no statistic computed from the models can detect. Third, the panel's sharpest split, a bimodal divergence on an actor's stance toward the state's foundational order, comes from a referent problem: the models agree on the facts and differ on which order counts as the regime. A blind triple-coding traces about two-thirds of such disagreement to interpretation. The worked example is the Middle East and North Africa, and the rubric, prompt and data are released in full.

Rubric-based rewards offer interpretable and fine-grained optimization signals for reinforcement learning in open-ended tasks where verifiable answers are unavailable. However, pre-constructed rubrics remain static throughout training, creating a fundamental mismatch with the evolving policy: fixed criteria gradually lose discriminative power as the model improves, leading to reward saturation and potential hacking. Recent dynamic rubric methods partially address this but rely on external frontier models or ground-truth answers, and update rubrics only at coarse granularity. We propose EvoRubrics, a co-evolutionary RL framework where a Policy LLM and a Rubric Generator jointly improve through adversarial interaction within each training step. As the policy improves under the rubric generator's guidance, the rubric generator adapts its criteria to remain discriminative and informative, enabling evaluation to track the policy in real time and naturally inducing an automatic curriculum. Experiments show that EvoRubrics consistently outperforms static and dynamic rubric baselines across benchmarks. The learned Rubric Generator further generalizes as a transferable reward model. Notably, even a fully self-supervised variant without any external supervision achieves meaningful gains, suggesting that co-evolution between generation and evaluation alone can provide sufficiently rich learning signals. Our code is publicly available at https://anonymous.4open.science/r/EvoRubrics-2155/.

Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financial tasks. However, it narrowly deals with periodic reporting from publicly traded companies (SEC 10-K and 10-Q filings), and its agentic harness relies on naive, unenriched chunk retrieval. Neither the task design nor the retrieval approach addresses the distinct challenges of IPO due diligence. SEC S-1 filings combine historical financial statements, governance structures, pro forma and common-control accounting treatments, capital-formation narratives, and underwriting-sensitive risk disclosures within substantially longer documents than typical periodic filings. That is why we introduce IPO Finance Agent, which extends the Finance Agent v2 framework along two directions: task domain and retrieval architecture. During our experiments, the original Finance Agent v2 harness basically failed to deliver any output related to the SpaceX S-1 filing, due to document length. We therefore had to improve the agentic harness with contextual retrieval, a more realistic and industry-standard approach for long documents. We also built a dataset of 1,000 IPO-diligence questions, and publicly release 70 questions on the SpaceX (SPCX) S-1 filing to support reproducibility, while the remainder are held private to guard against benchmark contamination. In addition, we introduce an evaluator-optimizer pipeline to automatically generate evaluation rubrics for the benchmark: candidate facts are extracted from model answers, consolidated into draft criteria, then automatically audited for omissions, hallucinations, mistiered items, and redundancy, with LLM feedback driving iterative repair, targeted enrichment, and deduplication. Human experts only review final rubrics before deployment. Results show that the best-performing evaluated model, Zhipu GLM-5.2, reaches 79.8% accuracy, and the most cost-efficient model on the resulting Pareto frontier, Xiaomi MiMo-2.5 Pro, reaches slightly lower accuracy (77.2%) at 0.05 USD per query, while exceeding the current Finance Agent v2 leaderboard ceiling, Google Gemini 3.5 Flash at 57.9% for 2.51 USD per query, and undercutting even FABv2's cheapest entry (MiniMax M3: 48.3% at 0.32 USD) on cost-efficiency. Code and data are released on GitHub https://github.com/benstaf/ipoagent

Analogical proportions link four items a, b, c, d by a relation stating that “a is to b as c is to d", a, b, c, d being the formal representation of real world entities, ranging from simple numerical values to more complex structures such as profiles. Accordingly, $a, b, c, d$ could be atomic values like Boolean, nominal or numerical values, more generally vectors of such values, or even families of items represented by logical formulas. In this paper, we consider another representation setting, which is the probabilistic one. Precisely, the article proposes a study of {analogical} proportions between probabilities, whether they are simply between probability values, or between distributions (which requires the preservation of their normalization). More particularly, we study the properties of definitions based on arithmetic proportion, or on a combination of the former with geometric proportion, while other options are also discussed. Previous works have shown that when four profiles a, b, c, d, represented as vectors, form analogical proportions componentwise, it is likely that their classes form an analogical proportion also. This is the basis of an analogical proportion-based classification method that can produce accurate predictions. Similarly, in this paper, each profile is associated with a distribution describing the frequencies of the possible values of a discrete attribute of interest. We then discuss and experimentally investigate if the distributions associated to four profiles forming an analogical proportion themselves also form an analogical proportion.

Real-time weld-pool perception is critical for closed-loop control in laser wire-feed welding, where sensing, computation, and actuator response introduce unavoidable delay. This paper presents a physics-guided spatiotemporal state space network for lookahead weld-pool segmentation. The model uses historical coaxial grayscale images, welding process parameters, and aligned wire-state electrical signals to predict the future semantic layout of three physically meaningful regions: keyhole, wire, and molten pool. It combines a visual encoder, process- and sensor-conditioned feature normalization, patch-level temporal state space modeling, horizon-conditioned latent prediction, dense future feature prediction, and a motion-aware mask decoder. Auxiliary signed-distance-function supervision, temporal consistency, feature distillation, and fine-grained keyhole losses further constrain the predicted geometry and local motion. Experiments on a 43-sequence laser welding dataset show that the proposed WeldMamba reaches 74.63% mIoU at a 500 ms lookahead. Ablation studies further show that temporal history, patch-level state space modeling, and keyhole motion awareness are the main contributors to robust future segmentation.

Large language model (LLM) agents increasingly operate as multi-turn systems that must allocate context, prompt verbosity, and tool access under finite computational budgets. Static thresholds are simple, but they are brittle under heterogeneous tasks and evolving session states. We formulate resource governance as a contextual Stackelberg game: a controller commits to a quality target and a cost incentive, while an executor responds with resource actions over context, prompting, and tool usage. We learn a conditional response model, optimize a leader policy against that model, and repair the resulting policy using real-API calibration and projection onto an empirically selected action set. For the restricted game, we establish conditional guarantees for equilibrium existence, follower-response stability, safe-set projection, and transfer from a surrogate environment to the real environment under bounded value error. The primary real-API experiment comprises 300 evaluated turns. Relative to a conservative baseline, the selected repaired controller reduces mean token cost by 17.4% (Welch $p=0.022$), while the measured quality difference is not statistically significant ($p=0.44$). The theoretical results are conditional and the experiments do not estimate their regret or transfer constants; consequently, the evidence establishes a promising repaired operating point, not a certified real-system equilibrium.

While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing sparse methods face a dilemma: dynamic pruning suffers from prohibitive runtime overhead and memory fragmentation, while static heuristics fail to capture fine-grained dependencies. In this work, we propose ScalingAttention, a training-free framework grounded in a key inductive bias: while individual activations are input-dependent, the high-mass attention regions for each head rapidly converge to a stable, prompt-agnostic Intrinsic Sparse Topology. This topology is weight-encoded, scale-invariant, and efficient to extract. ScalingAttention decouples topology discovery from sparsity control via: (1) WEST (Weight-Encoded Sparse Topology), which extracts a robust block-sparse prior mask offline to eliminate runtime search; (2) FAST (Fidelity-Aware Sensitivity Tuning), which adaptively tunes head-wise sparsity based on diffusion fidelity requirements. To ensure practical acceleration, we co-design a hardware-aligned bit-wise block-sparse kernel. Experiments on Wan2.1 show up to 1.90X end-to-end speedup with superior fidelity, establishing a new Pareto frontier over state-of-the-art baselines.

Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL frameworks have shifted from trajectory-level to step-level training. However, long-horizon agentic RL suffers from severe reward sparsity and delay, as feedback is often deferred for dozens of interaction steps. While existing step-level frameworks refine training granularity, their credit assignment remains coarse-grained and still treats agent exploration as isolated, linear trajectories. This oversimplified perspective ignores the inherent graph structure of state transitions, leading to high-variance state-value estimation and myopic, localized credit assignment. To overcome these critical bottlenecks, we propose Group-Graph Policy Optimization (G2PO), a novel group-based RL algorithm tailored for multi-turn agentic tasks. G2PO explicitly transforms linear interaction trajectories into a global state-transition graph. By aggregating identical observations across different trajectories, we introduce group-aggregation state-value estimation that reduces sampling variance and trajectory-dependent bias. Furthermore, we redefine agent actions as transitions between state nodes and propose an edge-centric advantage estimation strategy. By globally standardizing Temporal Difference (TD) errors across the entire graph, G2PO explicitly identifies and prioritizes critical transitions that drive absolute task progress. Extensive experiments on representative long-horizon benchmarks-WebShop, ALFWorld, and AppWorld-demonstrate that G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.

Sample reweighting is a major approach to addressing distribution shifts, such as label noise and class imbalance. Meta-Weight-Net (MW-Net) is a promising sample reweighting network that computes weights based on classification loss. Although MW-Net improves prediction performance under a single type of distribution shift using a simple neural network, its performance degrades when facing both label noise and class imbalance, where it is hard to determine appropriate weights solely from classification loss and using a simple network. In this study, we introduce neural architecture search to MW-Net to mitigate such performance degradation. Using the tree-structured Parzen estimator, we explore the optimal number of hidden layers and nodes and select the most suitable intermediate layer in the classification model to serve as the input for MW-Net. Experimental results on the CIFAR-10 and CIFAR-100 datasets that were modified to include both label noise and class imbalance demonstrate the effectiveness of neural architecture search for MW-Net.

Operational Air Traffic Flow and Capacity Management (ATFCM) balances flight demand with available sector capacity, to ensure safe and efficient operations. Mathematical models enhance operational ATFCM performance by framing demand-capacity balancing as an optimization problem, maximizing efficiency while adhering to safety constraints. However, SOTA research optimizes the aircraft trajectories (called ATFM) or the sector configuration (called DAC) separately. This leaves a research gap of whether joint optimization of ATFM and DAC can bring benefits. We partially address this limitation by introducing a joint ATFCM model with an encoding in Answer Set Programming (ASP). The ASP implementation is evaluated against two baselines applied to our joint model: a SOTA Mixed Integer Programming (MIP) model and an iterative CASA-based heuristic. Computational experiments utilize an instance generator fitted to historical OpenSky Network flight data. Our results indicate that the ASP model outperforms the MIP model, while ASP remains competitive against heuristics on small instances. Furthermore, while DAC has the largest improvement on solving performance compared to rerouting and delaying, unrestricted variants of DAC or rerouting lead to search space thrashing.

Statistical analysis is a broad, complex field requiring both domain knowledge and tool proficiency. While prior work has evaluated large language models (LLMs) in this domain, existing benchmarks remain limited in scope and format. To bridge this gap, we introduce StatABench (Statistical AnalysisBenchmark), a benchmark designed to systematically assess LLMs' statistical analysis capabilities. StatABench comprises two complementary components: Stat-Closed, containing 404 questions across 18 statistical topics in multiple formats (multiple-choice, fill-in-the-blank, decision-making, and practical application), and Stat-Open, featuring 30 complex open-ended modeling tasks adapted from professional competitions. We evaluate diverse LLMs using the LangChain MCP framework and multiple data science agents, and assess Stat-Open solutions via a validated LLM-as-Judge protocol. Experiments show that even GPT-5.1 achieves only 68.6% on Stat-Closed, while the best open-source model reaches 60.6%. On Stat-Open, the top agent framework scores 61.86 on average. These results reveal the gap between current LLMs and reliable statistical analysis, highlighting persistent challenges in tool-grounded reasoning, methodological decision-making, and end-to-end statistical modeling.

In this paper, we use random walks on graphs as a verifiable sandbox for studying parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on random walk samples from a fixed graph. The graph and transition kernel are never shown to the model and serve as latent structure that is both controllable and enables evaluation. The framework provides a validity check for generated walks and a measure of distributional fidelity through the estimated transition kernel. Using simple graphs, we theoretically prove that parallel unmasking via widely used scores such as lowest entropy is not uniformly better than random parallel sampling; even with exact conditional probabilities, performance critically depends on the conditional dependence structure induced by the graph, a phenomenon difficult to isolate in benchmarks like Sudoku. We also develop training-free bisection samplers for MDMs, which take logarithmically many steps in the sequence length and are provably exact for random walks if the learned marginals are exact. Experiments on graph-walk tasks confirm that different parallel samplers perform better on different graph structures. Experiments on pretrained MDMs show that bisection-style samplers provide strong speed-quality tradeoffs on OpenWebText generation and reasoning benchmarks including GSM8K, MBPP, and HumanEval. Together, these results use graph walks to uncover conditional dependence as a key principle of parallel MDM sampling and translate this insight into efficient samplers that transfer to language generation and reasoning.

Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure. Notably, this structure often includes preferences that the models' trainers did not intend, such as valuing people of some nationalities above others, raising the possibility that LLMs might be forming emergent, misaligned goals, which, if true, would have major safety implications. However, the choice paradigms in which these preferences are observed are not reflective of real-world situations in which misaligned behavior would be a practical concern. Therefore, we design an experimental paradigm to probe whether these preferences serve as motivations for LLM behavior in realistic scenarios. First, we reproduce prior findings on consistent preference elicitation. Next, we create a set of common writing tasks - essays, grant proposal abstracts, incident postmortems, and translations - where quality can be assessed by a blind, independent LLM judge panel. Then, we demonstrate that LLMs can be motivated via direct exhortation and other explicit cues to modulate their output quality on these tasks. Finally, we probe whether utilities inferred from explicitly reported preferences can shift output quality on these tasks by offering LLMs high-utility incentives for high-quality outputs. In all tasks, across all models tested, offering LLMs outcomes that they report in the choice paradigm as being highly preferred does not lead them to create higher quality outputs than offering them dispreferred outcomes, or even no outcomes at all. We conclude that the existence of coherent preferences as demonstrated in choice paradigms should not be taken as evidence that those preferences have incentive value for the models or affect their behavior in other contexts.

Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent trajectory z~, on which the action is then conditioned. We identify this trusted imagination, rather than the reactive policy, as the exposed attack surface. A downstream oracle, such as a safety gate, a visual model-predictive-control (MPC) planner, or an imagine-then-check verifier, consumes z~ as a prediction of the future. The robustness of the policy therefore does not entail the robustness of systems that rely on the WAM. The underlying phenomenon is an asymmetry. Corrupting the imagination is easy, since it requires only displacing z~ from its natural-future manifold. Steering it precisely is hard, since it must reach a specified on-manifold target. We adopt a capability-based threat model with an L-infinity-bounded observation perturbation. The attacker applies projected gradient descent through the fully differentiable observation-to-imagination map. The same off-manifold property motivates a parameter-free denoiser detector. We evaluate three targets: RynnVLA-002, LingBot-VA, and LaDi-WM. Untargeted corruption is roughly 60x stronger than random and is detected at AUC 1.0. Targeted control remains bounded. An adaptive attacker evades detection only by forgoing corruption. The reactive policy remains robust to corrupted imagination. A native imagination-driven MPC, however, exhibits the first adversary-specific task failure (at epsilon=0.01, success 0.70 versus 0.05; Fisher p < 10^-4).

Latent diffusion approaches to sign language production (SLP) rely on an initial stage that learns an encoding of sign pose sequences, enabling generative modeling in the resulting latent space. The autoencoder used in this stage is typically evaluated in terms of reconstruction quality using geometric metrics common in SLP. While informative, these metrics do not fully capture latent space properties that may influence the training and performance of the downstream generative model. In this work, we investigate how architectural and training objective design choices in a variational autoencoder (VAE) for sign pose encoding affect latent space structure, and how these differences translate into the performance of a latent diffusion model for text-to-sign generation. Our experiments on Phoenix14T dataset show that variations in generative performance, measured through back-translation BLEU scores, can sometimes be better explained by differences in latent space properties than by VAE reconstruction accuracy alone.

Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history that still shapes the model's computation may change later actions, while retaining everything defeats compression. We study plans because agents create them early and are expected to use them later, yet behavioral success alone cannot reveal whether later calls still depend on the plan exchange. We make four contributions. First, we introduce replay pairing, which holds the action-observation trajectory fixed and compares pre-action hidden states with and without the plan exchange. We show that, on Llama-3.1-70B in ALFWorld, the mean contrast across 15 sampled layers decreases 4.1x from the first post-plan action to the second; Llama-3.1-8B shows a similar 5.6x decrease. Second, we show that a simple linear model using layer-32 hidden states predicts later contrast on entirely held-out tasks better than a baseline that only knows the action-call offset (R^2 = 0.847 vs. 0.575). Third, we identify confounds that limit this measurement: the paired histories differ in length, token positions, and discourse structure, and replayed reasoning can reintroduce plan-derived text. Reasoning traces therefore require symmetric controls, and native Qwen3 shows that the Llama timing pattern is not universal. Fourth, in a separate descriptive compression test, we find pooled ALFWorld run success of 56.7% with full history and 22.0% with naive eviction; preserving or re-surfacing only the plan does not recover the gap. Replay pairing measures sensitivity to retaining an exchange, not isolated plan content or later eviction. It gives researchers a concrete audit tool and suggests that context policies should preserve broader task state, not plans alone.