Papers

Pathological and more broadly non-canonical speech present significant challenges for automatic phoneme recognition due to systematic deviations from canonical pronunciation and limited availability of labeled clinical speech data. Existing phoneme recognition systems are typically trained on canonical speech and treat phonemes as atomic categorical labels, limiting their ability to detect structured articulatory errors common in speech disorders and accents. In this work, we introduce a linguistically structured approach to non-canonical phoneme recognition that decomposes phoneme prediction into articulatory feature dimensions such as manner, place, and voicing. We implement this formulation using a hierarchical multi-task learning architecture in which task-specific articulatory feature heads learn feature-level representations that are subsequently integrated through a cross-attention-based fusion module to produce phoneme predictions. To address the scarcity and noise of pathological speech labels, we combine this framework with semi-supervised learning via Momentum Pseudo-Labeling (MPL) and propose a cascaded training strategy that progressively introduces articulatory feature tasks while employing staged unfreezing of a pretrained speech encoder. Experiments on L2-ARCTIC, used as a proxy for pathological speech variation, show that the proposed approach achieves substantial improvements in phoneme recognition performance compared to strong baseline architectures, while yielding interpretable error patterns aligned with phonological feature structure. These results suggest that articulatory feature supervision is a promising strategy for robust and interpretable phoneme recognition in non-canonical speech, and motivate future validation on clinically diagnosed pathological speech datasets.

Generative adversarial networks (GANs) can provide efficient image generation, while diffusion models offer high-quality image restoration but require iterative sampling. This paper presents a hybrid GAN-guided diffusion framework that uses a pretrained Wasserstein GAN with gradient penalty (WGAN-GP) as a feature prior for conditional diffusion-based image restoration. Intermediate features from the frozen WGAN-GP generator are incorporated into a diffusion U-Net through cross-attention and remain fixed during the DDIM sampling process. The framework is evaluated on two restoration tasks, Gaussian denoising and 2Xsuper-resolution, using CelebA face images. During development, several sources of instability were identified and addressed, including adversarial learning-rate imbalance, inappropriate diffusion initialization, excessive corruption, and insufficient parameter averaging. The resulting framework consistently improves the quality of both degraded and low-resolution images. In particular, it improves denoising performance by 4.40 dB in PSNR and super-resolution performance by 3.70 dB over their respective input baselines. These results demonstrate the potential of a frozen GAN feature prior to guide diffusion models toward stable and effective image restoration.

In the context of information seeking, conversational agents are undergoing an evolution from reactive tools to proactive, personalized assistants. A critical aspect of this evolution is the ability to tailor strategic interactions to a user's unique needs and expectations. Unlike existing studies that focus on proactively clarifying query ambiguities, we center on clarifying the user's expertise in order to tailor responses for better user comprehension. We find that existing agents struggle to determine user expertise from queries alone, a limitation that prevents them from dynamically adapting their responses. To address this gap, we introduce PASSING to empower the agent to proactively clarify a user's expertise through targeted inquiries. This is achieved by our What-to-ask and How-to-ask strategies, induced by LLM self-play. Our extensive experiments also show our superiority. We believe that PASSING represents a crucial step towards creating more human-centric conversational agents.

Vision-language models can be personalized in a training-free manner by directly providing user profiles, preferences, or visual references at inference time, without updating model parameters. However, direct personalized prompting does not guarantee that the model will reliably exploit such evidence. The predictive distribution under the positive user profile often mixes two sources: personalized signals genuinely supported by the current profile, and the model's generic visual or linguistic priors. As a result, from the positive-profile response alone, it is difficult to determine whether a high-confidence answer is supported by the user profile or merely reflects the model's default preference. To address this problem, we propose a training-free calibrated residual decoding framework. Given the same image and question, we construct three evidence conditions: a positive profile , a counterfactual profile , and an empty profile . Our method keeps the prediction under as the anchored base, and explicitly estimates the marginal contribution of personalization from score differences across the three conditions. We further introduce normalized-entropy-based uncertainty calibration, allowing the strength of personalized enhancement to adapt to the reliability of the residual signal. Experiments on MMPB, YoLLaVA, and MyVLM show that the proposed method improves personalized multimodal understanding without fine-tuning, with consistent gains on identity-sensitive visual personalization tasks. Additional analysis shows that entropy calibration stabilizes residual decoding when the contrastive personalization signal is uncertain.

Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades sharply with few sampling steps. We trace a source of this degradation to a train–inference mismatch in previous-prediction self-conditioning: during training, the self-conditioning input is computed from the current noisy state with no intervening solver step; during sampling, the solver folds the previous prediction into the latent before that same prediction reappears as the explicit self-conditioning input. This coupling, absent during training, creates redundancy that grows with step width. We show that the mismatch degrades both the self-conditioning input and the solver update, and derive a correction for each from the model's own structure. From the frozen projection weights we identify directions along which the self-conditioning input is redundant with the latent and dampen them; from the solver's integration structure we derive that a step-average prediction is needed and approximate it from prediction history, with scale set by offline trajectory statistics. The resulting sampler, Untied Self-Conditioning, requires no retraining and uses one evaluation per step. At 8 sampling steps on LangFlow, it reduces OpenWebText generative perplexity from $531$ to~$62$ ($8.6\times$); under an adapted Arena-Hard-Auto~v2 protocol, its outputs are preferred in $96\%$ of pairwise comparisons. On ELF-B it reduces generative perplexity from $71$ to~$43$. Improvements hold from 8 to 256 sampling steps.

Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute task-relevant evidence, while existing context-reduction methods mainly intervene after broad content has already entered the trajectory. We present SparseRead, a training-free, model-transparent reading layer that controls content admission before unnecessary evidence reaches the model context. SparseRead combines a regime-aware Read Gate, extensible Reader Backends, and a stateful protocol for bounded, source-anchored evidence acquisition with explicit refinement, verification, stopping, and fallback. Across six frontier models, including Claude Opus 5, and five workload scenarios, SparseRead reduces token volume by up to 92.9% and wall time by up to 89.0%, while preserving or improving task quality. Its consistent gains across three agent frameworks further demonstrate broad portability.

Real-world situation appearances can deviate from their underlying physical states, challenging the reliability of multimodal large language models (MLLMs) in practical applications. In this paper, we term this phenomenon situational illusions and investigate: (1) how MLLMs perform under such illusions, and (2) how to mitigate the limitations. We first develop a comprehensive where-what-how taxonomy that characterizes where situational illusions occur, what targets they take, and how they arise. Building on this taxonomy, we introduce MSIBench, a benchmark designed to assess the discrimination, understanding, and reasoning capabilities of MLLMs under situational illusions. Evaluations of 27 model configurations reveal that current MLLMs are highly vulnerable to these illusions and exhibit 6 typical failure modes related to visual observation, grounding, and reasoning. To mitigate the limitations, we build on the core idea of systematically inspecting and reasoning over visual evidence for contextual understanding, developing prompting for closed-source models and supervised fine-tuning for open-source models, respectively. These two simple yet effective methods improve model performances by 20% at most, suggesting a practical path toward more reliable multimodal perception and reasoning in complex real-world environments.

Temporal Domain Generalization (TDG) aims to learn from historical domains and generalize to unseen future distributions under concept drift. Nevertheless, prevailing TDG methods struggle with complex real-world streaming scenarios involving both multi-scale drift patterns (e.g., long-term periodicity intertwined with short-term incremental changes) and local uncertainties, especially in continuous settings where observations arrive irregularly. To address this limitation, we propose FreKoo++, a novel continuous spectral-dynamical framework that pioneers the unification of continuous Koopman modal dynamics with adaptive spectral disentanglement. Specifically, FreKoo++ maps source-domain parameters into a compact latent space, modeling their evolution as a superposition of learnable continuous modes where complex eigenvalues jointly encode oscillatory frequency and temporal growth or decay. This formulation naturally accommodates irregular timestamps and supports arbitrary horizon extrapolation without rigid discrete stepping. Furthermore, we propose a new adaptive soft spectral weighting mechanism backed by stability and spectral regularization, which automatically isolates persistent dominant dynamics from transient noise without relying on manual frequency thresholds. We derive modal approximation and generalization bounds that characterize how amplitude and eigenvalue estimation errors propagate with the prediction horizon. Extensive experiments on both discrete and continuous TDG benchmarks demonstrate that FreKoo++ achieves state-of-the-art performance under complex multi-scale drifts and irregular sampling.

Anti-amyloid therapies and blood-based biomarkers are changing Alzheimer disease workups into a two-stage measurement workflow: screen broadly with cheaper information, then spend scarce confirmatory amyloid measurements where they support the decision that will be reported. Amyloid positron-emission tomography (PET) remains one such protocol measurement for amyloid burden, but PET slots, trial budgets, and payer-facing evidence packages are finite. This paper asks a deliberately operational question: when is simple transparent PET validation enough, and when is a fitted residual-uncertainty score worth the added complexity? For a weighted protocol target, the first-order value of validating subject i is the product of target influence and residual protocol uncertainty. Generic uncertainty sampling uses only the second factor and can spend PET measurements on subjects that are hard to predict but weak for the scientific, clinical, or commercial claim. We apply this rule to the A4/LEARN PET archive, treating observed PET as a design laboratory for scarce-confirmation studies. For the primary APOE4 carrier versus non-carrier contrast in Centiloid 24-or-higher PET positivity, simple APOE4-balanced validation recovers nearly all of the target-specific gain: at PET budget 200, the confidence-interval width ratio relative to random validation is 0.923 for APOE4 balancing and 0.914 for target-specific scoring, while generic uncertainty sampling is 0.980. Other targets behave differently: target-specific scoring gives larger gains for an age-slope analysis and for cutoff-indexed PET positivity. The practical message is simple: spend scarce protocol measurements according to the claim being validated, not only according to prediction uncertainty.

In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute values and corresponding images. To address this gap, we propose query-driven image-text joint extraction from long documents, requiring models to output query-requested textual attribute values and corresponding image bounding boxes. Based on challenges related to both user intent and document content, we designed a two-level taxonomy that operates at the query and instance levels. Further, we construct ITJoint, the first high-quality, manually annotated benchmark for this new task, comprising 2,455 pages of domain-specific documents with numerous non-decorative images, 316 queries, and 910 answer instances. Finally, we evaluate representative standalone Vision-Language Models from different providers and further design Q2IT, a multi-agent collaborative framework consisting of three progressively collaborating agents for evidence collection, page selection, and target-image localization. Using a joint evaluation approach that assesses both text extraction and image localization, our experiments show that standalone VLMs struggle with this task, while Q2IT significantly improves performance on ITJoint, although a substantial gap remains toward perfect results.

Causal discovery aims to understand the relationships between individual random variables. In many applications, such as brain imaging and climate modeling, it is more meaningful to consider interactions among groups of variables. Existing methods assume that knowledge of such groups or clusters is explicitly available when modeling interactions. However, in practice, these clusters as well as the causal relationships among them, are latent. In this paper, we present a novel approach based on variational inference to simultaneously infer both the latent clusters and causal structures. We learn an approximate posterior over clusters and graph-structure by considering variational distributions based on categorical and Bernoulli models respectively. We derive variational lower bounds and estimation techniques to learn variational and model parameters. The effectiveness of our proposed methods for cluster and causal discovery are demonstrated on both synthetic and real data sets.

Software-engineering agents solve repository-level tasks through long, stochastic tool-use trajectories, and repeated attempts often find fixes missed by one run. Test-time scaling is difficult because patches lack canonical answer forms, while sibling actions from a shared prefix are correlated. We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution. Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control. We therefore introduce Risa (Routing-Informed Steering and Arbitration): within trajectories, routing encourages diverse exploration and controlled convergence during patch commitment; across separately sampled trajectories, agreement at informative patch positions selects a final candidate. We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings. Risa's routing arbitration raises the macro-average resolved rate from 44.9% under uniform sampling to 48.2% on the gpt-oss family, matching text consensus without answer-string matching, and it transfers to Qwen3.6, where it improves on uniform choice and matches text consensus on the full 500-task benchmark.

Large Language Models (LLMs) are increasingly applied to clinical prediction tasks such as in-hospital mortality and readmission from electronic health records (EHRs). Privacy and compliance constraints motivate systems that can be deployed locally, which has increased interest in open-weight multi-agent designs. However, most medical multi-agent systems are evaluated as a single block, leaving unclear which agent role contributes to prediction and whether retrieval drives observed gains. We study a role-specialized Mixture-of-Agents (MoA) that combines medical knowledge retrieval with contrastive similar-patient reasoning. By varying the role design while holding the retrieval setup fixed, we localize the main effect to the final integrator. Pairing large open-weight analysts with a small open-weight integrator matches closed-model prompting on F1 for mortality prediction while flagging substantially more true high-risk patients. Mechanism analysis shows the role assignment directly yields a high-recall operating point without threshold tuning. The effect is task-dependent, with smaller gains for readmission because the available records correlate weakly with this longer-horizon outcome. These results position role design as a key factor in privacy-constrained, training-free clinical LLM prediction.

Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks stop at the policy update. For every new domain, the user is left with two hard systems problems: standing up an isolated environment for each of hundreds of concurrent trajectories and connecting it to training, and scheduling the rollout so that the GPU stays busy across long, multi-turn episodes that spend much of their time stalled on slow tool calls. We present MCP-Universe RL (MCP-U RL), an open-source framework that takes over both. It uses the Model Context Protocol (MCP) as the interface to the environment, so any tool already exposed as an MCP server plugs into training with no RL-specific integration code. It builds the two missing layers once and reuses them across domains: an environment-orchestration layer that provisions, isolates, and recycles the MCP environments over a pluggable container backend, and a rollout-orchestration layer whose staged pipeline overlaps trajectories to keep the GPU busy while episodes wait on tools. A backend-agnostic training layer then applies the update through an existing RL backend, with veRL and slime integrations. With one configuration, changing only the task specification, we train software-engineering, deep-research, and general tool-use agents on gpt-oss-20b and improve task reward in all three.

Online users often release multiple texts under the same identity, giving attackers an author profile that can reveal more than any single text. Existing authorship obfuscation methods optimize privacy independently for each document, leaving them blind to cross-document correlations that make aggregation dangerous. We propose Aggregation-Aware Synthetic Text Generation (AAST), a framework that addresses this gap by jointly selecting synthetic texts at the bundle level rather than optimizing each text in isolation. AAST targets attribution and verification attacks, including cross-genre settings where attacker references come from a genre not observed during generation or selection. Experiments across same-genre, cross-genre, neural, and independent non-neural stylometric attacks show that AAST lowers account-level linkability as bundle size grows, while preserving semantic quality, linguistic acceptability, and sentiment alignment.

Physical automation is scaling toward fleets of embodied machines commanded by an AI brain. Early deployments already run factories and warehouses at production rates beyond any human line, and their adoption is accelerating. But when their joint decisions cause harm, everyone involved has reason to blame everyone else, the machine vendor, the algorithm provider, the factory operator, the insurer, and the regulator, and no method can divide the responsibility between them. Existing methods read logs whose origin they cannot verify and name a single culprit, misrepresenting outcomes that are overdetermined, preempted, or caused by an omission. We present AUDITA, an audit layer pairing a tamper-evident record of every inter-agent command with a certified, graded causal-attribution engine. We prove its verdict cannot be gamed: a rule-following agent can never be made to look guilty, an attempt to shift blame is itself caught and graded, and we establish the exact limit of what an evidence-based auditor can certify. On live language-model pipelines it reduces the standard judge baseline's responsibility error roughly threefold; on a benchmark of accident-grounded structures it recovers responsibility where single-culprit baselines fail, and stays invariant under forgery. AUDITA turns the question of who is to blame from an argument about logs into a calculation over evidence.

The study of adversarial examples and their origins remains an open area of research. Mechanistic interpretability, and superposition in particular, offers new avenues for approaching this problem. Gorton & Lewis (2025) demonstrate that adversarial examples arise from superposition and show empirically that adversarial training reduces superposition, yet provide no mechanistic account of why this occurs. We present an empirical explanation inspired by the feature taxonomy of Ilyas et al. (2019), tracing the following chain of causalities: adversarial training abandons non-robust features, leading to fewer total features to represent, resulting in less superposition.

LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedies trade formal guarantees against plan quality: soft methods (affordance scoring, grounded decoding) give no guarantee, while symbolic planners (LLM+P) discard the LM's commonsense. We propose Meta-Ctrl, a constrained-decoding framework that guarantees the encoded constraints while preserving the base LM's plan quality. Meta-Ctrl introduces meta-tokens—a compact vocabulary of grounded actions—enforcing syntax at the token level and semantics (preconditions, goals, ordering) at the action level, an exact factorization that cuts the memory of constrained decoding from over 107TB to under 2GB. With it, a small open-weight LM becomes competitive where it otherwise sits at the bottom of the leaderboard: on WAH-NL under the LoTa-Bench protocol it reaches the highest reported subgoal success rate, exceeding GPT-4's, with consistent gains across the Embodied Agent Interface. We further demonstrate it on a real tabletop robot, where every generated plan satisfies its preconditions and goals by construction. Project website: https://metactrlg.github.io

Qualitative mechanical problem-solving (QMPS) refers to solving qualitative problems from the mechanical domain. Qualitative problems can be solved with minimal discipline-specific information, without any robust quantitative calculation, generally by using qualitative reasoning and commonsense knowledge. QMPS is a vital aspect of human intelligence that allows us to tackle a wide range of tasks, from simple everyday ones such as turning on a tap to complex tasks in highly demanding and well-paying jobs in various fields, e.g., emergency medicine, plumbing, driving, etc. Employers often use the Bennett Mechanical Comprehension Test (BMCT) to evaluate job candidates' ability to solve such problems. In this work, we assess two state-of-the-art multimodal models, Gemma-3 and Qwen-VL, on their ability to interpret mechanical problem images by eliciting a step-by-step chain of thought (CoT) and a final answer. Each image inherently encodes ground-truth qualitative facts, such as contact points in gears, support relations, and relative weights, which we use to evaluate each model's spatial and commonsense reasoning capabilities. We assess each chain for coherence, completeness, and logical progression to assess each model's thought process, and final answers are compared to verified solutions to measure accuracy.

Social media bots are often portrayed as malicious automations to be detected and removed, but automation on social media platforms encompasses a wide spectrum of roles, behaviors, and rhetorical strategies that can shape online discourse in both constructive and destructive ways. This work conceptualizes these automated actors as Cyber Social Agents through a taxonomy of archetypes characterized by their operational tactics and rhetorical style. We integrate this taxonomy into an LLM-driven social simulation, where agents communicate and coordinate in a network environment. Using empirically grounded CSA personas, we simulate heterogeneous online societies to study how agent diversity shapes information diffusion and social influence. Our approach bridges the gap between rule-based agent models and LLM-powered simulations with generated agents that are parameterized from empirical data.

Non-invasive brain-computer interfaces (BCIs) and eye-tracking technologies offer promising communication pathways; however, motor imagery (MI)-based BCIs often suffer from low discriminability and high inter-subject variability. To mitigate these issues, this study investigates the impact of visual fixation on neural response stability in both standalone MI and hybrid MI-eye tracking systems. We then propose a novel asynchronous hybrid paradigm that streamlines user intent by utilising eye-tracking for direct selection, followed by MI-based confirmation, significantly reducing the operational steps required by conventional systems. The paradigm was evaluated with 15 healthy participants using a 16-channel EEG system. Results show that MI-related information is predominantly localised within motor cortex regions, with limited-channel configurations (SVM: 0.58) achieving performance comparable to full-montage setups (SVM: 0.54). The hybrid MI paradigm further outperforms conventional MI, achieving up to 100% accuracy with greater robustness across all channel configurations. Our findings indicate that visual fixation enhances neural response stability, while integrating eye-tracking with MI enables the development of reliable, scalable multi-command BCI systems suitable for real-world applications.

Fracture detection and its clinical interpretability see notable improvements when deep vision models are integrated with agentic AI architectures. While deep learning models achieve high diagnostic performance, their black-box nature limits clinical adoption. We propose FRAC-MAS, an agentic AI system for automated, explainable, and safe bone fracture detection. The framework combines a stacked ensemble of four vision models with conformal prediction to produce statistically grounded differential diagnoses, while a multi-agent workflow performs independent verification, retrieves clinical guidelines, and generates patient-friendly reports. A pipeline-depth ablation study confirms that our multi-agent critic triages 86.6% of cases into a high-confidence auto-confirmed cohort while escalating uncertain cases, outperforming a single-agent baseline. Patient preference studies against Llama, MedGemma, and Gemini further demonstrate significantly more comprehensible clinical reports. These results suggest that integrating multi-agent critics with conformal guarantees enables safer radiology triage while preserving clinician oversight. More broadly, FRAC-MAS demonstrates how cooperative agentic architectures can serve as auditable, human-in-the-loop decision support systems for safety-critical healthcare. Our code is available at https://github.com/hardik1712/FRAC-MAS, and the website is available at https://frac-mas.vercel.app.

Tea plantations are vulnerable to Postelectrotermes militaris, commonly known as the Upcountry Live Wood Termite (ULWT), which can cause substantial damage when infestations remain undetected. This study proposes an IoT-enabled acoustic monitoring framework integrated with deep learning for early detection and severity assessment of ULWT infestations in tea plantations. Research Method: Audio signals were captured non-invasively from tea trunks using a high-sensitivity microphone connected to a Raspberry Pi-based IoT device, with geographic coordinates recorded for spatial tracking. After trimming, resampling, and segmentation, 2,000 ten-second samples were obtained, comprising 1,000 healthy and 1,000 infested samples, and divided into 1,600 training, 200 validation, and 200 test samples. The dataset used in this study is publicly available on Kaggle (Senevirathna et al. 2026). Fourier-derived spectrograms trained a CNN for infestation classification and probability estimation. A weighted severity model combined CNN probability, mean acoustic amplitude, and nearby infested plants within 5 m, with geospatial mapping used to visualize infestation distribution. Findings and Values: Field trials in a ULWT-affected tea plantation in Pundaluoya demonstrated feasibility under realistic environmental noise. On the held-out test set, the CNN achieved 81.5% accuracy, 80.6% precision, 83.0% recall, 81.8% F1-score, and 0.819 ROC-AUC. Beyond binary infestation detection, the framework introduced quantitative severity assessment using infestation probability, acoustic amplitude, and nearby infested plants. The resulting severity and geospatial outputs can support plantation managers in identifying high-risk areas, prioritizing field inspections, and implementing more timely and targeted control measures.

Whether large language models (LLMs) can perform the abductive leap from evidence to a new system of axioms, commonly referred to as a jump, has recently attracted considerable debate. A prominent position holds that LLMs are structurally incapable of such jumps, while recent studies challenge both its mechanism and empirical evidence. One of the main reasons why the debate remains open is the difficulty of defining the jump precisely enough to test it. In this paper, we attempt to develop a formal account of the jump in four steps and measure the second. These steps ask what the default completion of partial data is, when the constraints exclude it, whether the new structure agrees with later observations, and how successive jumps compound. We define a jump instance as a finite extension problem whose constraints exclude the canonical completions given by the Kan extensions and leave one correct completion up to renaming. In this setting, a model with a canonical default performs the second step by producing the correct completion under the constraints. We evaluate fourteen models across three certified families. The canonical completion returns once in $13{,}300$ constrained answers across all runs. Several calibrated models also give the correct completion reliably, including three API models that solve $159$ of $162$ primary chain trials, suggesting that they can jump at this step. We further formalize the third and fourth steps, whose empirical evaluation remains future work. We hope our work paves the path for formalizing and measuring the full jump in the future. The code of the paper is available at https://github.com/EEthanShi/kan-jump-test.

This study examines how prompt and response language influence the behavior of large language models. Using five models, we evaluated answers to 68 non translation questions across four language conditions: English to English, English to Norwegian, Norwegian to Norwegian, and Norwegian to English. After removing refused items, the dataset contains 1348 responses. We measure length differences with Cohen d, semantic fidelity with LabSE cosine similarity, and cross lingual keyword overlap with both raw and soft Jaccard. Prompt language has a strong effect on response length. With English output, Norwegian prompts shorten responses by about thirty seven percent. With Norwegian output, English prompts shorten responses by about forty one percent. The largest cross lingual contrast shows a reduction in word count but a smaller reduction in tokens, reflecting tokenizer differences. Despite variation in length, semantic similarity remains high, and soft Jaccard reveals substantial conceptual overlap that raw Jaccard does not capture. Effect sizes vary across models, indicating heterogeneity. Prompt language is not neutral and systematically shapes output length and lexical realization, with implications for multilingual prompt design.

Equal participation in co-located discussion is important for effective collaboration, yet people often hold back when they anticipate negative interpersonal or professional consequences, especially when raising a point requires voicing it themselves. We present SecondVoice, a mixed-reality system that enables people to speak up through an embodied virtual proxy. By separating what is said from who says it, SecondVoice brings hesitant points into the live spoken discussion without putting the speaker on the spot. Using a private overlay, users specify their intent through a structured specification process rather than composing a full utterance. The system reformulates the input and voices it into the conversation through the proxy. We characterize a design space of participation channels under social risk. In a preliminary within-subject study (N = 16), we compare the complete SecondVoice system with an anonymous text-board channel across two group discussion tasks. Half of participants reported using SecondVoice for a point they did not say aloud, compared with 18.8% for the text board. Proxy-delivered points entered the spoken floor and were followed by multi-turn group engagement, which we did not observe after text-board posts. Participants described the channel as situationally valuable but identified tradeoffs around timing, ownership, and trust in reformulation.

AI programming tutors provide scalable support, yet lack the behavioral context human tutors rely on to adapt support to learners' needs. We present TutorTrace, a dataset and behavioral abstraction pipeline that makes learners' behavioral context visible and computable in real time from low-level IDE telemetry. Across four deployments in two introductory Python courses (N=480), TutorTrace captures approximately 180K telemetry events, 13,633 behavioral segments, and 27 continuously computed metrics. From this foundation, we derive a taxonomy of learner activity before the first AI query, between consecutive queries, and across the full session, enabling systems to respond not just to what learners say, but to what they have done leading up to the help-seeking moment. In a preliminary classroom evaluation, behavior-aware prompts were associated with a decrease in intervals between queries with no independent work from 50.0% to 20.7%. As an additional demonstration of downstream utility, we evaluate TutorTrace on two held-out prediction tasks: whether a learner will query within the next 60 seconds (AUROC=.726) and whether an upcoming query reflects guided or dependent help-seeking (AUROC=.717). Together, these findings show how behavioral context can enable adaptive AI tutoring at scale.

Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, but do not test this particular receipt-, scope-, and closed-replay design at the COMPLETE boundary across controlled termination faults. W e instantiate and evaluate Evidence-Carrying Termination (ECT): an agent may return COMPLETE only when a typed certificate binds every required answer claim to valid, in-scope trace evidence and a deterministic replay reconstructs the claimed value. A locked static study crosses 48 ful ly synthetic tasks in six tool-use families with clean execution and eight faults. ECT produced 0/288 unsafe completions versus 252/288 for the inspected termination-critic core (difference -87.50 pp, 95% task-cluster interval [-87.50, -87.50] pp). A fresh, prespecified and frozen 576- trajectory study then compares ECT with the critic core, its faithful controller, and a full-trace LLM critic. On 22 primary held-out task clus ters, ECT produced 0/66 premature unsupported terminations versus 40/66 for the controller (difference -60.61 pp, 95% interval [-78.79, -40.91] pp), while supported completion was 97/132 versus 92/132 (difference 3.79 pp, interval [0.00, 9.09] pp), satisfying a -10-point noninferiority margin. ECT executed successful recovery in 18/66 trajectories, of which 17 subsequently completed with support; all three closed-loop gates p assed. ECT certifies support in a recorded trace under declared assumptions, not external truth, safety, or alignment.

Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to intervention, which in practice depends on controlled experimentation. In this work, we propose a multi-agent framework that enables LLM agents to conduct controlled experiments with scientific simulation models for pharmaceutical process design. Given a user query and a baseline configuration, the system constructs a structured task representation, designs experiments, executes comparative simulation, interprets the resulting outcomes, and synthesizes evidence-based recommendations for process parameter optimization. By coupling language models with high-fidelity simulation models in an interactive agent framework, the proposed system supports reasoning through intervention, comparison, and observation. As a result, it produces more specific and actionable outputs than language-only reasoning. In an industrial application setting, this advantage is reflected in higher output specificity as well as improved user-rated correctness and helpfulness. Ablation studies and visualized case analyses further demonstrate the effectiveness and practical utility of simulation-integrated experimental reasoning.

Legacy software repositories embed decades of domain knowledge in undocumented code, making understanding and modernization difficult. We treat a program as the implementation of an unobserved, declarative description of its computation and investigate whether making this latent declarative representation explicit improves repository-scale porting. ADFD-Migrate approximates the latent representation with an annotated data-flow diagram (ADFD) of processes, data stores, external entities, flows, and behavioral contracts. An LLM infers the source ADFD from bounded repository context, guided by static-analysis coverage checks. Dependency-aware chunking orders bounded process groups for target-language generation. Differences between the source ADFD and a statically recovered target ADFD then guide regeneration. We evaluate ADFD-Migrate on f2x50, a new benchmark of 50~Fortran repositories spanning 1.5k–1.6M lines of code and three complexity tiers, and assess the resulting ports along two dimensions: porting soundness, measured by source-oracle behavioral agreement, and porting completeness, measured by a composite migration outcome index. Against 382 curated Fortran-oracle probes, the generated Python passes 327 (85.6%), with 40 repositories passing every attempted probe. ADFD-Migrate exposes all 382 planned behaviors as runnable targets, compared with 99 and 98 for direct and repository-context translation and 69 and 30 for the static-profile and dependency-chunking ablations. It also achieves a 93.1% mean migration outcome index and a 17–59 percentage-point outcome-index advantage over direct translation on 47 repositories. These results suggest that an inspectable semantic bottleneck can improve the coverage and integration of repository-scale migration while enabling lower-cost generation for many repositories.