Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
medRxiv (Medicine) 2026-06-12

Design, Implementation, and Evaluation of a Shadowing Program for Medical Students in the Basic Sciences Phase

Introduction Shadowing, as an educational method based on active observation, can foster a realistic understanding of professional roles and enhance the communication skills of medical students. This study aimed to design, implement, and evaluate a shadowing program for basic sciences medical students. Methods This development study was conducted based on the ADDIE model in five phases. The study population consisted of 799 medical students in semesters 2 to 5. The stages included Analysis (determining needs through literature review and expert panels), Design (specifying learning environments and evaluation methods), Development (preparing guides and educational tools), Implementation (within the Medical Ethics course), and Evaluation (using questionnaires and reflection forms). Findings This study aimed to design and evaluate an educational shadowing program based on the ADDIE model. In the Analysis phase, the profiles of 799 students and learning objectives were determined. In the Design phase, a structured program for four types of shadowing was designed. In the Development phase, all guides and educational tools were prepared. In the Implementation phase, the program was carried out with complete coverage and adherence to ethical considerations. Finally, the program evaluation showed that "Motivation to become a good physician" (3.75-3.95) and "Enhancing empathy" (3.50-3.94) received the highest scores, while "Increasing understanding of the basic science-clinical connection" (2.53-2.89) and "Willingness to attend on holidays" (1.87-2.31) received the lowest scores. Conclusion The findings indicate that implementing the shadowing program is an effective method for strengthening the professional attitudes and academic motivation of medical students. However, the program did not significantly improve students perception of the basic science-clinical connection, indicating a need for curricular refinement. The continuation and extension of this program to other levels and fields of medical sciences are recommended.

02.
medRxiv (Medicine) 2026-06-15

Comparative Analysis of Machine Learning Models vs. Traditional Clinical Calculators for Cardiovascular Risk Prediction

Background: Cardiovascular diseases (CVD) remain the leading global cause of mortality, responsible for approximately 31% of all deaths worldwide in 2021. Traditional risk calculators, including Framingham, ASCVD, SCORE, and SCORE2, have long constituted the cornerstone of primary prevention strategies; however, they were derived predominantly from high-income European and North American populations, thereby limiting their predictive accuracy in diverse epidemiological contexts, particularly among Hispanic/Latino communities. Machine learning (ML) offers an alternative to capture the non-linear interactions inherent in biomedical data. Objective: The present study develops and validates ML-based models for cardiovascular mortality prediction using the National Health and Nutrition Examination Survey (NHANES) 1999-2018 dataset, and systematically compares their discriminative performance against eleven conventional clinical CVD risk calculators. Materials and Methods: A dedicated software platform, "CardioPrediQ," was designed to integrate multiple CVD calculators with ML-based risk assessment. A cohort of 12,847 participants with 16 predictor variables was derived from NHANES. Six algorithms (Logistic Regression, Cox Proportional Hazards, Gradient Boosting, AdaBoost, Random Forest, and Extra Trees) were trained in combination with six class-balancing strategies, yielding 36 model configurations. All models were trained on a stratified 70/30 split and calibrated using the Saerens prior probability adjustment method. Performance was evaluated using AUC-ROC, sensitivity, specificity, F1-score, and a weighted composite score. DeLong's test was employed to assess the statistical significance of AUC differences between the best-performing ML model and each conventional calculator. Results: Gradient Boosting with 2:1 oversampling and Saerens calibration achieved the best overall performance (AUC = 0.8934; composite score = 0.7904), outperforming all traditional calculators in composite ranking. The top six positions were occupied exclusively by ML and statistical models. The mean age of cardiovascular decedents was 67.43 years compared with 47.74 years among survivors. DeLong's test confirmed statistical superiority over six traditional CVD calculators (p < 0.05), whereas the difference against the top-performing calculators (ASCVD, HEARTS Caribbean, ASCVD Colombia, SCORE2, HEARTS North America) did not reach statistical significance. Age dominated feature importance at 41.2% relative weight, followed by systolic blood pressure (18.7%). Saerens calibration reduced the Brier score from 0.1286 to 0.1158, substantially improving probability calibration. Conclusions: ML models demonstrated superior composite performance over traditional calculators. The statistical equivalence with the highest-performing conventional calculators in the NHANES cohort is context-dependent and validates the methodological pipeline. The CardioPrediQ platform addresses the critical need for integrated, scalable CVD risk assessment tools, which is particularly relevant for Latin American populations where calculator validation remains limited. These findings support the integration of calibrated ML-based risk prediction into clinical practice while underscoring the importance of probability calibration for informed clinical decision-making.

03.
arXiv (CS.CV) 2026-06-12

Learning Task-Aware Sampling with Shared Saliency through Density-Equalizing Mappings

In image and surface-based learning tasks, convolutional features are typically extracted using receptive fields that are sampled uniformly across the entire domain. However, informative structures are rarely distributed uniformly in practice and are often concentrated in localized regions. Such phenomena are particularly common in medical imaging, where pathological changes are spatially confined. Consequently, uniform convolution allocates equal computational effort to both informative and uninformative regions, resulting in inefficient feature extraction and suboptimal utilization of model capacity. To address this issue, we propose a framework for task-adaptive sampling that dynamically redistributes computational attention according to the spatial importance of the data. Specifically, we introduce the Density-Equalizing Convolutional Neural Network (DECNN), which employs density-equalizing mappings to guide convolution through a learned density function. The density function encodes the relative importance of different regions and induces a transformation that enlarges informative areas while compressing less relevant ones. As a result, convolutional receptive fields are redistributed non-uniformly over the domain, enabling denser sampling in task-relevant regions. By coupling this importance-driven transformation with convolution, DECNN performs adaptive feature extraction that focuses computational resources on informative structures. This leads to more efficient use of model capacity, yielding a lightweight yet expressive architecture while simultaneously producing an interpretable saliency map. Experiments on image classification and craniofacial surface analysis demonstrate that DECNN achieves competitive or superior performance with fewer parameters, accurately identifies task-relevant regions, and remains robust under complex geometric variations.

04.
arXiv (CS.CV) 2026-06-16

RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos

Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale. Editable 3D Gaussian Splatting (3DGS) simulation offers a promising alternative by reconstructing real driving scenes and supporting controllable scene editing. However, edited 3DGS-rendered videos still suffer from a significant Sim-to-Real gap, including rendering artifacts, degraded foreground assets, inconsistent illumination, and temporal flickering. Existing restoration and video generation methods are insufficient for this task, as they often fail to jointly repair 3DGS-specific artifacts, improve visual realism, and ensure temporal consistency. To fill this gap, we propose RealityBridge, a structure-preserving and asset-aware Sim-to-Real framework for edited 3DGS driving videos. RealityBridge uses multimodal controls, including rendered videos, foreground masks, edge maps, and semantic masks, together with a lightweight GateNet for adaptive condition allocation across backbone layers. We further construct targeted training data and introduce autoregressive long-video training with reward-guided post-training to improve restoration quality, temporal stability, and hallucination suppression. Extensive experiments on internal and public driving datasets show that RealityBridge outperforms existing methods in artifact removal, illumination harmonization, and long-sequence temporal consistency.

05.
arXiv (CS.AI) 2026-06-16

ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing

arXiv:2606.15315v1 Announce Type: new Abstract: Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing algorithms. This paper presents ChatPlanner, a novel framework that leverages Large Language Models (LLMs) to enable preference aware public transit routing. Our approach employs fine-tuned LLMs with Retrieval-Augmented Generation (RAG) to extract routing parameters and interpret nuanced user preferences from natural language queries, subsequently integrating these preferences into the objective function of a public transit routing algorithm. This study designs preference aware datasets incorporating eight personas and five contexts to establish scoring standards for both fine-tuning and RAG. This work conducted three experiments to validate the solutions' feasibility, extraction of routing information and preferences, and solution set quality and completeness. Results demonstrate that ChatPlanner generates feasible solutions reliably. Fine-tuning enforces the required output structure and learns general preference patterns, while RAG provides query-specific context to resolve imprecise or conversational expressions and calibrate continuous scores. The combination of both achieves the highest accuracy in routing information extraction and user preference interpretation. Results based on selected case studies show that by capturing user preferences, ChatPlanner identifies valuable solutions across different dimensions that existing route planners overlook, generating more valuable route alternatives. This research establishes a new paradigm for integrating natural language understanding into transportation optimization.

06.
arXiv (CS.AI) 2026-06-16

Agentomics: Economic Foundations for the Valuation, Attribution, and Pricing of AI Agents in Human-AI Workflows

作者:

arXiv:2606.14769v1 Announce Type: cross Abstract: Agentic AI systems are increasingly being deployed as productive resources in organizational workflows, yet existing evaluation methods primarily measure isolated technical performance rather than economic contribution. This paper introduces Agentomics, a workflow-based framework for valuing, attributing, and pricing human and artificial agents. The framework models a workflow as a configuration of heterogeneous agents whose collective performance determines gross value, deployment cost, reliability, and expected failure loss. Workflow value is treated as a team-level quantity that may include complementarities, substitution effects, bottlenecks, and nonlinear production; additive stage-level value is only a special case. Building on this workflow model, the paper formulates AI deployment as a coalition-formation problem and defines coalition value as the incremental net surplus generated relative to a benchmark human workflow. The Shapley value is then used to attribute economic surplus among participating AI agents, yielding a principled connection among valuation, accountability, and market pricing. The resulting Shapley pricing equilibrium provides a normative benchmark for assessing whether agent prices reflect expected marginal contribution. A security-operations case study illustrates how the framework accounts for productivity gains, deployment costs, reliability losses, and coalition-level complementarities in hybrid human–AI workflows.

07.
arXiv (CS.AI) 2026-06-19

Emergent Alignment

arXiv:2606.19527v1 Announce Type: new Abstract: Can Large Language Models (LLMs) discern when their own outputs are misaligned with human ethics? And can they self-correct? We endow an LLM with a conscience step that reviews its own reasoning and outputs, and we extend the training loss with an alignment component using Direct Preference Optimization (DPO) to steer the model away from non-ethical outputs. The result is an online technique to align models in a wide range of applications: training, fine-tuning, adversarial prompting, and zero-shot learning. It does not require a weaker or stronger judge, relying instead on a frozen copy of itself. In previous work, the Emergent Misalignment scenario showed a range of emergent unethical behaviors from fine-tuning the model to hack code. Instead, we empirically show how to achieve Emergent Alignment: a single high-level introspective question steers training toward an ethical model under the same code hacking scenario.

08.
arXiv (CS.CL) 2026-06-12

Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention

Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this gap is not a uniform cognitive deficit. Evaluating two architecturally diverse SLLMs, we show speech-to-text (S2T) matches or exceeds text-to-text (T2T) on spatial, syntactic, and factual tasks. Yet on logical tasks requiring entity tracking, S2T accuracy collapses to chance. We diagnose this as an entity binding failure: continuous speech features blur precise entity-property associations during implicit reasoning. To validate this diagnosis, we introduce Entity-Aware Chain-of-Thought (EA-CoT), a lightweight inference-time intervention forcing SLLMs to enumerate entities and bind them to claims before reasoning. EA-CoT bridges the gap, even when spoken names are misrecognized, yielding up to a 24.4 percentage-point accuracy gain. Ablations confirm the gains stem from explicit semantic binding, reframing the gap as an elicitation failure rather than a missing capability.

09.
arXiv (CS.AI) 2026-06-12

Automated reproducibility assessments in the social and behavioral sciences using large language models

arXiv:2606.13670v1 Announce Type: new Abstract: Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze the original data to assess whether the published findings can be recovered. However, such approaches are resource-intensive and difficult to scale. Here, we show that large language models (LLMs) can automate reproducibility assessments. Using N=76 published studies with predefined claims from the behavioral and social sciences, we compare LLM-generated analysis with the original findings and human reanalysis. For 7 studies, the LLM could not produce a viable effect size estimate. For the remaining studies, our LLM pipeline recovered the original effect sizes in 41% of studies using a +/-0.05 tolerance in Cohen's d. Further, our LLM pipeline reached the same qualitative conclusion as the original study in 96% of cases, where conclusions indicate whether the reanalysis supports the original claim. For comparison, human reanalysts recovered the original effect sizes in 34% of studies and reached the same qualitative conclusion in 74% of cases. Together, these results show that LLMs can serve as a scalable tool for automated reproducibility assessment and provide a foundation for systematic auditing of empirical results in the social and behavioral sciences.

10.
arXiv (CS.LG) 2026-06-12

One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data

arXiv:2606.10678v2 Announce Type: replace Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies. Despite their success, these single-stage forecasting architectures exhibit persistent systematic residual biases arising from structural discrepancies, unmodeled stochastic components, or inadequate multi-scale temporal representations. This limitation persists when residuals are treated as irreducible noise, precluding adaptive correction of structured error patterns. To address this limitation, we introduce a two-stage, model-agnostic framework that explicitly decouples forecasting and residual learning into distinct stages of representation learning. A base transformer first generates the initial predictions. Subsequently, a dedicated meta-corrector dynamically models structured error patterns across multivariate channels, preserves cross-variable dependencies, and iteratively refines the residual bias of the base transformer. By formalizing this pipeline as a hypothesis space expansion, our framework addresses approximation limitations inherent in single-stage architectures, removes reliance on restrictive assumptions, and enables end-to-end learning of complex error dynamics. Evaluated on eight popular benchmark datasets using established protocols, our approach achieves state-of-the-art performance, with significant improvements in standard metrics (MSE, MAE). The results demonstrate the framework's ability to mitigate systematic biases and enhance robustness to complex temporal dynamics, advancing the practical applicability of transformer-based forecasting models.

11.
arXiv (CS.CL) 2026-06-11

Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains

Speech foundation models often struggle in low-resource domains due to domain mismatch and data scarcity. We propose Gumbel-BEARD, a domain adaptation framework that automates Whisper encoder layer selection via an end-to-end trainable hard Gumbel-Softmax selector. It enables self-supervised adaptation with a BEST-RQ objective that dynamically adapts to target acoustic characteristics without manual tuning. Experiments on the MyST child speech corpus demonstrate efficiency and scalability: with 10 h of labeled data for fine-tuning, our method matches a fully supervised baseline trained on the complete 133 h labeled set. We establish new state-of-the-art word error rates (WERs) of 8.21% using Whisper-medium on MyST and 11.06% using Whisper-small on the OGI Spontaneous dataset. Evaluation on CORAAL further confirms robustness to adult dialectal domain shifts, with up to 6% relative WER reduction, highlighting the generalizability of our approach to diverse low-resource conditions.

12.
arXiv (CS.CV) 2026-06-16

Pathway-Structured Privileged Distillation for Deployable Computational Pathology

Integrating transcriptomics and histopathology can improve cancer risk modelling, yet practical use is constrained by the limited availability of RNA profiling in routine settings. Here we introduce Mixture of Pathway Experts (MoPE), a knowledge-distillation framework that reframes multimodal learning as privileged distillation for histology-only inference. MoPE is motivated by the partial observability between RNA profiles and whole-slide images: histology can capture morphology-linked consequences of certain molecular programmes, but cannot be expected to reconstruct the full transcriptomic state. MoPE encodes RNA-derived pathways and transfers the molecular supervision to pathway-indexed pathology experts through memory-usage alignment. Across diverse public benchmarks and two independent breast cancer cohorts, MoPE consistently improved WSI-only inference performance relative to baseline methods. Pathway-usage analyses and human-audited visual inspection provide bounded inspection of model behaviour and candidate morphology-linked readouts. These results support pathway-structured privileged distillation as a promising route to using molecular information during training while preserving RNA-free inference.

13.
arXiv (CS.CL) 2026-06-11

AI Coding Agents Can Reproduce Social Science Findings

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

14.
arXiv (quant-ph) 2026-06-16

Quantifying Coherence-to-Entanglement Conversion Efficiency under Noisy Operations

arXiv:2606.16916v1 Announce Type: new Abstract: We investigate the noise-limited conversion of local quantum coherence into bipartite entanglement in a minimal two-qubit protocol comprising a coherent single-qubit input, an incoherent ancilla, an ideal CNOT operation, and subsequent environmental noise. Employing the $l_1$-norm of coherence and the entanglement negativity as resource quantifiers, we establish an exact closed-form correspondence between local single-qubit input coherence and the two-qubit entanglement generated in the noiseless limit, showing that the output negativity is precisely one half of the initial $l_1$-coherence. We then derive analytic expressions for the surviving entanglement and the associated coherence-to-entanglement conversion efficiency under two representative noise mechanisms: independent phase damping and global two-qubit depolarizing noise. The two channels exhibit qualitatively distinct degradation behavior. Phase damping induces a universal multiplicative suppression of the generated entanglement, yielding a coherence-independent conversion efficiency and no finite-noise entanglement sudden death. In contrast, global depolarization introduces an isotropic mixing contribution that shifts the partial-transpose spectrum, producing coherence-dependent degradation and a finite sudden-death threshold. We show that maximally coherent inputs not only maximize the entanglement generated by the CNOT protocol but also optimize its robustness against depolarizing noise. Direct density-matrix simulations validate the analytic results to numerical precision. These findings provide a compact analytic benchmark for assessing how different noise mechanisms constrain coherence-to-entanglement conversion in elementary quantum-information protocols and near-term quantum devices.

15.
arXiv (CS.LG) 2026-06-11

Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds

arXiv:2606.12050v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) combine machine learning with physical laws to solve differential equations. While existing results provide rigorous a posteriori upper bounds for PINN prediction errors, complete certification also requires complementary lower information in order to obtain computable two-sided error enclosures. In this paper, we derive computable a posteriori lower bounds for PINN errors in ordinary differential equations on suitable certified state-space domains under a localized strong monotonicity condition. We combine these estimates with complementary localized upper bounds under a one-sided Lipschitz condition, which is weaker than the global Lipschitz assumption used in previous work and can yield sharper upper error bands. The resulting bounds depend only on the neural-network approximation, the ODE residual, and local monotonicity and growth constants, and therefore do not require access to the exact solution. For linear time-invariant and time-varying systems, we further derive explicit formulas in terms of the minimal and maximal eigenvalues of the symmetric part of the system matrix. We also discuss the distinction between soft and hard enforcement of initial conditions in PINNs and explain why exact enforcement can make the scalar lower certificate uninformative. To recover nontrivial lower information in the linear setting, we use a signed-residual finite-probe certificate based on coordinate unit vectors. We also formulate a certificate-informed training strategy in which the propagated upper certificate is used as an auxiliary regularizer, while lower certificates remain post-training diagnostics. Altogether, the proposed framework provides rigorous and practically computable error certificates for PINN approximations of ODEs, while making explicit the domains and model classes for which the assumptions can be verified.

16.
arXiv (CS.LG) 2026-06-16

SSNAPS: Audio-Visual Separation of Speech and Background Noise with Diffusion Inverse Sampling

arXiv:2602.01394v2 Announce Type: replace-cross Abstract: This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on generative inverse sampling, where we model clean speech and ambient noise with dedicated diffusion priors and jointly leverage them to recover all underlying sources. To achieve this, reformulate a recent inverse sampler to match our setting. We evaluate on mixtures of 1, 2, and 3 speakers with noise and show that, despite being entirely unsupervised, our method consistently outperforms leading supervised baselines in WER across all conditions. We further extend our framework to handle off-screen speaker separation. Moreover, the high fidelity of the separated noise component makes it suitable for downstream detection of the acoustic scene. Code and pretrained models will become available upon acceptance. Demo page: https://ssnaps2026.github.io/ssnaps2026/

17.
arXiv (CS.LG) 2026-06-11

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

arXiv:2606.12054v1 Announce Type: new Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet, despite the breadth of existing approaches, it remains unclear which design choices truly matter in practice. In this work, we investigate parameter noise injection for stochastic gradient descent, focusing on two key questions: how to efficiently pair each training example with its own perturbation in mini-batch training, and whether sophisticated noise parameterizations or multi-sample gradient averaging yield meaningful gains over simpler alternatives. To address the first question, we leverage a distributional identity for linear layers that allows per-example noise injection without breaking batched computation. To address the second, we systematically compare several diagonal Gaussian parameterizations against an isotropic baseline across varying noise levels on CIFAR100. Our results consistently show that simple, lightweight strategies, isotropic noise with a single perturbed forward pass per update step, recover most of the benefit of more complex schemes. These findings suggest that simplicity suffices for parameter noise injection, and that practitioners need not resort to elaborate perturbation designs to reap the optimization and generalization benefits of noisy SGD.

18.
arXiv (CS.AI) 2026-06-18

Domain-Shift Aware Neural Networks for Unbalance Characterization in Rotating Systems

arXiv:2606.18882v1 Announce Type: cross Abstract: This work investigates the application of a domain-shift aware neural network for regression tasks aimed at estimating unbalance masses in rotating shafts under varying operating conditions. Experimental data were collected from a test rig in which a primary shaft, equipped with a flange carrying unbalanced masses, was driven at different rotational speeds, while a secondary shaft could be optionally activated to introduce domain discrepancy. The unbalance masses were positioned at a fixed radial distance, and the dynamic response of the system was recorded using triaxial accelerometers. The inverse problem of mass estimation is formulated within a domain adaptation framework, where the network is trained with a maximum mean discrepancy strategy to align feature representations across source and target distributions. The results demonstrate the effectiveness of explicitly addressing domain shift in improving prediction accuracy, especially when the system's physical behavior and sources of domain discrepancy are not fully known and fall outside the training conditions. These findings highlight the potential of domain-shift aware models for regression tasks in Structural Health Monitoring.

19.
arXiv (CS.LG) 2026-06-11

Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents

arXiv:2606.11998v1 Announce Type: new Abstract: Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and untrusted models may render trusted models unreliable monitors. We introduce bootstrapped monitoring, a protocol that addresses this by inserting a stronger, intermediate untrusted model with transparent chain-of-thought reasoning into the oversight chain. The untrusted monitor ($U_m$) evaluates the agent's actions, while a weaker trusted model ($T$) oversees $U_m$'s reasoning to detect collusion. We evaluate bootstrapped monitoring on multi-turn software engineering tasks (BashArena) across multiple agents and monitors. Bootstrapped monitoring substantially improves catch rates over trusted-only monitoring, even when the untrusted monitor actively colludes with the agent, provided we have access to its raw chain-of-thought. Our results suggest that bootstrapped monitoring can extend the useful lifetime of trusted models in control as AI capabilities advance.

20.
arXiv (CS.CL) 2026-06-16

Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents

Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume test-time tokens, a cost rarely reported alongside the actor's inference cost. We study online augmentation, where this overhead is paid on every task, and re-evaluate its benefits under a fixed total inference budget. We compare AWM, ASI, and ReasoningBank with a token-matched vanilla baseline that uses the same budget for additional actor steps. Across three WebArena domains and three models, Gemini 3 Flash, GPT-5.4-mini, and Qwen 3.6-27B, the vanilla baseline matches or surpasses all three augmentation methods in aggregate success rate while often using fewer total tokens. We observe a similar trend on WorkArena-L1 with Qwen 3.6-27B, indicating that the effect extends to enterprise knowledge-work tasks. Our results suggest that skills and workflow memory can be useful in specific domains, but their apparent gains often vanish against a budget-matched actor. We further show that run-to-run variance materially affects outcomes and should be reported as a core evaluation criterion for online web agents.

21.
arXiv (CS.CL) 2026-06-17

LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI

AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment. We present LegalHalluLens, an auditing framework with three components: typed hallucination profiles across four legally-motivated claim categories (numeric, temporal, obligation/entitlement, factual) over CUAD (Hendrycks et al., 2021); a Risk Direction Index (RDI) that reduces omission-versus-invention bias to a single deployment-comparable scalar; and a typed debate pipeline calibrated to both magnitudes and directions. Across 510 contracts and 249,252 clause-level instances we measure a within-model gap of approximately 38-40 pp between obligation/numeric and temporal claims that aggregate reporting hides, and show that two systems with matched 52% rates can carry opposite RDIs. The debate pipeline reduces fabricated detections by 45% with per-category gains tracking the diagnosis, matching commercial APIs with a substantially smaller backbone (4B active parameters). Typed profiles and RDI surface failure modes that aggregate metrics hide; we further show these diagnostics serve as calibration inputs for multi-agent debate pipelines, where Skeptic challenges and asymmetric gates targeted at measured failure modes outperform generically-tuned debate. The framework supports direction-aware procurement, accountability, and agent design for legal AI deployed in the wild.

22.
arXiv (CS.LG) 2026-06-15

SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines

arXiv:2606.14361v1 Announce Type: new Abstract: Machine learning (ML) pipelines require extensive data preparation, feature engineering, and integration across heterogeneous sources, making them tedious and error-prone to develop. While large language models (LLMs) have recently shown promise for assisting programming tasks, chat-based interfaces provide limited control over pipeline behavior and often produce code that is difficult to optimize or integrate into production systems. We demonstrate SemPipes, a novel programming model that extends ML pipelines with declarative, LLM-powered semantic data operators. SemPipes allows developers to specify high-level natural language instructions for data-centric operations, while seamlessly combining these operators with arbitrary Python code from standard data science libraries. For the semantic operators, it synthesizes specialized implementations at pipeline training time, conditioned on dataset characteristics and pipeline context, enabling the flexible yet controlled integration of LLM capabilities. We demonstrate SemPipes through SemPiper, an interactive interface that visualizes computational graphs of the pipelines, synthesized operator implementations, and optimization trajectories produced by an evolutionary search procedure. Attendees can explore three end-to-end scenarios, modify pipelines, inspect generated code, and observe how semantic operators are synthesized and iteratively optimized. The demonstration highlights how declarative semantic operators enable controllable, optimizable, and practical integration of LLMs into ML pipeline development.

23.
arXiv (CS.CV) 2026-06-11

Continual Learning with Support Boundary Experience Blending

Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified decision boundaries. We address this limitation by introducing Support Boundary Data (SBD), generated via differential-privacy-inspired noise into latent features to create boundary-adjacent representations that implicitly regularize decision boundaries. Building on this idea, we propose Experience Blending (EB), a framework that jointly trains on exemplars and SBD through a dual-model aggregation strategy. EB has two components: (1) latent-space noise injection to generate support boundary data, and (2) end-to-end training that jointly leverages exemplars and SBD. Unlike standard experience replay, SBD enriches the feature space near decision boundaries, leading to more stable and robust continual learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet1K demonstrate consistent accuracy improvements of 10%, 6%, 13%, 2%, respectively.

25.
arXiv (CS.AI) 2026-06-15

Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

arXiv:2606.07157v2 Announce Type: replace Abstract: Many efforts to ensure frontier AI models are safe rely on monitoring their chain-of-thought (CoT) reasoning. If models become able to perform sufficiently complex reasoning internally, without explicit thinking tokens, this would undermine such oversight. We measure how well frontier models reason without CoT across a suite of over 30,000 questions spanning 43 benchmarks in domains including math, coding, puzzles, causality, theory-of-mind, and strategic reasoning. To compare models against humans, we estimate the $50\%$-task-completion time horizon (TH): the human time required for tasks a model completes with $50\%$ success rate. We complement this with a $50\%$ reasoning token horizon: the minimum number of o3-mini reasoning tokens needed for tasks a model solves with $50\%$ success rate. We find that the no-CoT $50\%$ TH of frontier models has been doubling roughly every year over the past six years, with GPT-5.5's TH reaching over 3 minutes and reasoning token horizon exceeding 1,500 tokens. Our median estimates predict that frontier no-CoT THs could exceed 7 minutes by 2028, and 25 minutes by 2030, though these projections carry substantial uncertainty. We recommend frontier developers track this explicitly.