Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
medRxiv (Medicine) 2026-06-17

Real-World Effectiveness and Safety of Avacopan in ANCA-Associated Vasculitis: A Systematic Literature Review and Meta-analysis

Background: The efficacy and safety of avacopan in ANCA-associated vasculitis (AAV) has been established in randomized trials of of avacopan as a glucocorticoid (GC) sparing therapy. However, real world evidence (RWE) has an important role in confirming effectiveness and evaluating safety in more generalizable settings. This study aimed to synthesize RWE on the effectiveness and safety of avacopan in adults with AAV. Methods: A systematic literature review and meta analysis of non interventional real world studies was conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) guidelines. Eligible studies included adults with AAV treated with avacopan in routine clinical practice. Pooled estimates of effectiveness and safety outcomes were calculated using random effects meta-analyses. Primary outcomes included remission at 6 and 12 months and sustained remission at 12 months. Secondary outcomes included relapse, GC use and dosing, hepatotoxicity, infections, and treatment discontinuation. Exploratory outcomes included changes in estimated glomerular filtration rate (eGFR) and dialysis related endpoints. Results: A total of 71 studies were included and contributed to quantitative analyses. Pooled remission for patients on avacopan was 87% (95% CI: 75%-94%) at 6 months and 93% (95% CI: 86%-97%) at 12 months, and sustained remission was 86% (95% CI: 74%-93%) at 12 months. Relapse at 12 months was low (7%; 95% CI: 4%-11%). GC use was 36% at both 6 and 12 months. Improvements in eGFR were observed at 6 months (18 mL/min/1.73 m2) and 12 months (18 mL/min/1.73 m2), and dialysis liberation was 66% in a limited subset. Among avacopan patients, 11% experienced any hepatotoxicity, including 7% with serious (defined as directly reported or requiring hospitalization) hepatotoxicity, while 7% experienced serious (defined as directly reported or requiring hospitalization) infection. Conclusions: In real world clinical practice, avacopan is associated with high remission rates, low relapse rates, and a consistent GC sparing effect, with effectiveness comparable to standard of care regimens. Findings support its clinical use with appropriate safety monitoring; however, the observed heterogeneity in hepatotoxicity and the limited comparative effectiveness evidence highlight areas requiring further investigation.

02.
arXiv (CS.CL) 2026-06-15

Creative Integration: A Decidable Criterion of Creativity

"Integrative" solutions are widely praised but rarely defined: we lack an operational way to tell a genuine integration – one that makes the world cheaper to describe – from a tidy re-description. Building on the lineage that treats creativity and intelligence as compression, we give such a criterion for creative integration (CI): the resolution of a real conflict between A and B is CI if and only if, under a fixed description language, the description length strictly shrinks (C = L_pre/L_post > 1), with the reduction located in the conflict itself. We make the judgment decidable through four binary, conjunctive gates, and we fix its extension through a taxonomy of pseudo-integration that names and rejects the look-alikes. We back the criterion with a curated, multi-domain corpus and – crucially – validate it not by human inter-rater agreement but by four falsifiable tests it could fail: an independent computational check, discrimination against hard negatives, out-of-sample prediction, and description-language robustness; all pass with margin. The contribution is not "creativity is compression" but its decidability, discrimination, and corpus: on this account, what makes a move genuinely creative – rather than merely novel – is that it compresses a conflict, with novelty and value as downstream symptoms; whether all creativity is so constituted we state as an explicit conjecture. We claim only the sign of C-1; we judge, not generate. The result is a citable primitive for a broader program.

03.
arXiv (CS.AI) 2026-06-16

Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?

arXiv:2606.15762v1 Announce Type: cross Abstract: We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model (LLM) security review is on the same JavaScript code, prompt, and benchmark harness. The headline result is that LLM security findings were unevenly repeatable: reference-matched findings were stable, but extra model reports varied heavily from run to run. Across 250 model runs, 80 of 161 unique unmatched findings appeared in only one of five identical repetitions, while only 22 appeared in all five. By contrast, when Claude matched a Snyk Code reference finding, the behavior was much more stable: 134 of 158 unique reference-matched findings appeared in all five repetitions. The benchmark also shows complementarity. Models consistently found familiar, high-signal exploit shapes, and in one case surfaced a likely Snyk Code product gap. Snyk Code static application security testing (SAST) was deterministic and better at systematically enumerating repeated data-flow sinks. The results support combining agentic LLM review with deterministic SAST rather than treating either technique as a replacement for the other.

04.
arXiv (CS.CV) 2026-06-18

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning

Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of works focus on plane geometry while usually fail in solid geometry due to 3D spatial diagrams and complex reasoning. To bridge this gap, we introduce Hilbert-Geo, the first unified formal language framework for solid geometry, including an extensive predicate library and a dedicated theorem bank. Based on this framework, we propose a Parse2Reason method containing two steps of first parsing then reasoning. In the parsing step, we utilize conditional description language (CDL), a formalized language composed of predicates specifically designed to construct geometric conditions, to represent both problem description (natural text) and solid diagrams (visual image). In the reasoning step, we leverage those formal CDL and the theorem bank to perform relational inference and algebraic computation, generating strictly correct, verifiable, and human-readable reasoning processes. Notably, our proposed Hilbert-Geo is also applicable to plane geometry. To advance geometric reasoning, we curate two expert-annotated dataset SolidFGeo2k and PlaneFGeo3k, which are furnished with geometric formal language annotations, solutions and answers. Extensive experiments show that our proposed method achieves the state-of-the-art (SOTA) performance 77.3% in SolidFGeo2k and 84.1% in MathVerse-Solid (one small subset in MathVerse dedicated to solid geometry), substantially outperforming leading MLLMs, such as Gemini-2.5-pro (54.2% on SolidFGeo2k) and GPT-5 (62.9% on MathVerse-Solid). In addition, our method achieves the SOTA accuracy 80.2% in PlaneFGeo3k, demonstrating the generality of the Hilbert-Geo in geometric reasoning. Our code and datasets are released at https://github.com/PremiLab-Math/Hilbert-Geo.

05.
bioRxiv (Bioinfo) 2026-06-22

Dynamic balance of sparse flux vectors for efficient simulation of culture dynamics and metabolic network reduction

Dynamic Flux Balance Analysis (DFBA) enables simulation of microbial culture dynamics under changing environmental conditions, but remains computationally expensive for tasks such as parameter calibration and fermentation optimization when applied using genome-scale metabolic models (GEMs). To address this challenge, we introduce Dynamic Flux Vector Balancing (DFVB), a reformulation of DFBA that solves an equivalent problem using a pre-computed, sparse basis of flux solutions that reduces the dimensionality of the internal optimization problem without information loss. Notably, DFVB provides a compact, interpretable representation of flux states that can readily identify dynamically inactive pathways and enable simulation-based automatic metabolic network reduction. We showed that DFVB produces the same culture dynamics as DFBA across multiple model scales and conditions, and identifies inactive reactions more accurately than Flux Variability Analysis (FVA) when compared to transcriptomic data profiles. Furthermore, computational performance analyses demonstrated that integrating DFVB with solver warm-start strategies and model reduction enhances computational efficiency relative to DFBA, yielding up to 3-fold reductions in simulation time for large-scale metabolic models. Finally, kinetic parameter estimation of culture dynamics with DFVB in two fermentation scenarios using a large-scale yeast GEM reached equal or higher prediction fidelity and narrower confidence intervals than DFBA, indicating improved parameter identifiability and robustness. Together, these results position DFVB as a scalable, robust, and biologically coherent framework for dynamic metabolic modeling, easing the integration of GEMs for culture dynamics simulation.

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

The Significance of Style Diversity in Annotation-Free Synthetic Data Generation

arXiv:2606.20400v1 Announce Type: new Abstract: Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings. In this paper, we propose a framework for synthetic dialogue generation that works entirely without human-annotated data, relying solely on intent definitions. Our proposed dialogue generation framework utilizes two different types of topic and style attributes to improve data diversity. Also, we propose two novel post-hoc stylization models called Univ and Exam to transform synthetic LLM-generated utterances into more varied, human-like linguistic styles. To enhance data quality, we utilize an LLM-as-a-judge filtering process. Experimental results on both industrial and public datasets demonstrate that the proposed approach achieves up to 93.3% of the performance obtained using human-annotated training data. Crucially, the findings reveal that style diversity is more critical than topic diversity for synthetic data utility, as it prevents models from learning spurious stylistic correlations. Furthermore, the study shows that incorporating style attributes during the generation process is more effective than post-hoc style adaptation.

07.
arXiv (CS.LG) 2026-06-12

Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing

arXiv:2606.12816v1 Announce Type: cross Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by standard overhead metrics can still lose fidelity when they pass through poorly calibrated couplers. We study a calibration-aware graph reinforcement-learning router that uses same-day IBM Heron r2 calibration data to choose hardware-edge SWAPs. We train the policy with proximal policy optimization and evaluate it with exact simulated fidelity across nine Munich Quantum Toolkit (MQT) Bench circuits and three calibration snapshots. Across these evaluations, pooled mean exact fidelity is $0.727$, compared with $0.440$ for SABRE-best20 and $0.481$ for target-aware SABRE. Fidelity gains come with higher routed two-qubit counts and are concentrated in the 5q and 8q circuit families; under the fixed tree action graph, all 10q families favor SABRE-best20. Overall, our results show that calibration-aware learned routing can improve fidelity beyond gate-count-driven compilation.

08.
arXiv (CS.CL) 2026-06-17

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation. This paradigm is particularly well-suited for code generation, where holistic structural planning and non-sequential refinement are critical. Despite this potential, tailoring dLLMs for CUDA kernel generation remains challenging, obstructed not only by the high specialization but also by the severe lack of high-quality training data. To address these challenges, we construct CuKe, an augmented supervised fine-tuning dataset optimized for high-performance CUDA kernels. On top of it, we propose a bi-phase curated reinforcement learning (BiC-RL) framework consisting of a CUDA kernel infilling stage and an end-to-end CUDA kernel generation stage. Leveraging this training framework, we introduce DICE, a series of diffusion large language models designed for CUDA kernel generation, spanning three parameter scales, 1.7B, 4B, and 8B. Extensive experiments on KernelBench demonstrate that DICE significantly outperforms both autoregressive and diffusion LLMs of comparable scale, establishing a new state-of-the-art for CUDA kernel generation.

09.
arXiv (CS.AI) 2026-06-19

DynAMO:Dynamic Asset Management Orchestration via Topological Multi-Agent Scheduling

arXiv:2606.19382v1 Announce Type: cross Abstract: While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.0 deployment is hindered by latency, concurrency instability, and safety risks. We present DynAMO (Dynamic Asset Management Orchestration), a deployment-ready engine using a Plan-then-Execute architecture to generate verifiable workflow graphs. DynAMO supports both SequentialWorkflow (topological execution) and ParallelWorkflow (dependency-aware concurrency). By dynamically identifying independent tasks, DynAMO preserves structural correctness and safety while significantly improving efficiency through controlled reasoning overlap. Across six controlled experiments on the AssetOpsBench industrial benchmark, DynAMO demonstrates substantial performance and robustness gains. Parallel execution reduces end-to-end latency by a median of 1.6x over sequential orchestration, rising to 1.8x on highly parallelizable workflows. After instrumenting external tool calls with realistic latencies, a latency decomposition shows that LLM reasoning and orchestration still account for more than 90% of execution time, identifying model inference as the primary system bottleneck. Structured context pruning reduces inference latency by approximately 30%, and DynAMO maintains correct functional behaviour (task completion, agent sequencing, and output quality) while exhibiting graceful degradation under controlled fault injection. Reproducibility analysis further confirms stable execution under repeated runs, with parallel scheduling reducing latency variance. These findings establish DynAMO as a practical blueprint for scalable, safe, and latency-aware agent deployment in Industry 4.0 automation pipelines. Code is available at: https://github.com/kushwaha001/DynAMO

10.
arXiv (CS.CL) 2026-06-16

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure that supports the organization, grounding, and continuous evolution of agent skills by transforming heterogeneous knowledge into reusable skill assets linked to their originating evidence. Our demonstration presents the complete skill lifecycle, from knowledge ingestion and skill production to provenance-aware exploration, governance, and execution-driven evolution. SkillWiki highlights a future in which knowledge, skills, and execution experience co-evolve within a shared infrastructure. The live demonstration and source code are publicly available at https://github.com/Huangdingcheng/SkillWiki.

11.
PLOS Medicine 2026-06-02

Proteomic signatures of early retinal neurodegeneration in type 2 diabetes mellitus

Authors:

by Huangdong Li, Ziyu Zhu, Shaopeng Yang, Weijing Cheng, Shaoying Tan, Zhuoyao Xin, Lei Zhang, Zhuoting Zhu, Shida Chen, Wenyong Huang, Wei Wang Background Retinal neurodegeneration is an early and independent feature of diabetic retinal disease and has been proposed as a window into the systemic neural consequences of diabetes, yet accessible molecular biomarkers and individualized prediction tools remain scarce. We aimed to identify circulating plasma protein signatures of diabetic retinal neurodegeneration (DRN) and to translate them into a clinically usable risk prediction system. Methods and findings In this multi-cohort prospective observational study, we integrated high-throughput plasma proteomics with longitudinal optical coherence tomography (OCT) in two independent populations. The discovery cohort comprised 1,492 participants had baseline plasma proteomics and OCT, and 1,218 were followed with repeated OCT over 6 years in Guangzhou Diabetic Eye Study (GDES). DRN was quantified by the annualized OCT-derived retinal nerve fiber layer thinning rate. In multivariable analyses adjusted for age, sex, smoking, systolic blood pressure, HbA1c, and diabetes duration, we identified 71 plasma proteins associated with development and progression of DRN. These proteins mapped onto pathways governing inflammatory immune recruitment, extracellular matrix remodeling, and microvascular homeostasis, providing a plausible biological basis for DRN. We developed a proteomics-based DRN model (Pro-DRN) using eight machine learning (ML) algorithms, including XGBoost and LightGBM. In the independent test set, Pro-DRN achieved a C-index of 0.860, rising to 0.908 when integrated with clinical variables. Compared with six conventional models, Pro-DRN improved discrimination (ΔC-index 0.137 to 0.159; all P 

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

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training. Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations. Collecting such supervision can be costly or unavailable. We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations. SD-Zero trains a single model to play two roles: a Generator, which produces an initial response, and a Reviser, which conditions on that response and its binary reward to produce an improved response. We then perform on-policy self-distillation to distill the reviser into the generator, using the reviser's token distributions conditioned on the generator's response and its reward as supervision. In effect, SD-Zero trains the model to transform binary rewards into dense token-level self-supervision. On math and code reasoning benchmarks with Qwen3-4B-Instruct and Olmo-3-7B-Instruct, SD-Zero improves performance by at least 10% over the base models and outperforms strong baselines, including Rejection Fine-Tuning (RFT), GRPO, and Self-Distillation Fine-Tuning (SDFT), under the same question set and training sample budget. Extensive ablation studies show two novel characteristics of our proposed algorithm: (a) token-level self-localization, where the reviser can identify the key tokens that need to be revised in the generator's response based on reward, and (b) iterative self-evolution, where the improving ability to revise answers can be distilled back into generation performance with regular teacher synchronization. Code: https://github.com/princeton-pli/Self-Distillation-Zero.

13.
arXiv (CS.CV) 2026-06-17

When LLMs Analyze Scars: From Images to Clinically-Meaningful Features

Medical image classification faces a fundamental dilemma: while deep learning models achieve remarkable performance at scale, real-world clinical scenarios often suffer from severe data scarcity due to annotation costs, privacy constraints, and disease rarity. This challenge is particularly pronounced in pathological scar classification, where differentiating keloids from hypertrophic scars requires subtle expert knowledge and labeled images are extremely limited. We propose a novel paradigm that repositions large language models (LLMs) as knowledge-driven feature engineers rather than end-to-end classifiers. We call this framework ScaFE (Scar Feature Engineering). Our key insight is that LLMs encode rich medical knowledge that can be externalized as executable feature extraction code, enabling the transformation of high-dimensional images into low-dimensional, clinically interpretable representations. Specifically, we prompt an LLM with established scar assessment criteria to generate deterministic Python code that extracts features aligned with clinical scoring systems such as the Vancouver Scar Scale. Our approach offers three key advantages: (1) data efficiency, achieving robust performance with limited training samples by decoupling knowledge acquisition from statistical learning; (2) privacy preservation, as raw images are processed locally without exposure to external LLMs; and (3) interpretability, through explicit features grounded in clinical reasoning. Extensive experiments on scar classification demonstrate that our method consistently outperforms end-to-end deep learning baselines or using LLMs as black-box classifiers under limited data conditions, establishing a promising direction for integrating LLMs into data-efficient and clinically transparent medical AI systems.

14.
arXiv (CS.AI) 2026-06-18

SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector

arXiv:2606.18309v1 Announce Type: cross Abstract: Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off between unlearning and retention. We have found that the retention activation bias can also be used to quantify the damage an unlearning method inflicts on retention, without considering the specific implementation of the unlearning process. This allows us to restore retention performance for any unlearning method using a post-hoc approach. Therefore, we propose a complementary post-hoc setting to sanitize the final update vector without rerunning the original unlearning pipeline. In this setting, we design SAGE, Spectral Activation-GEometry Sanitization, a source-agnostic correction for final unlearning updates. SAGE collects real module inputs from a small retain proxy, extracts their dominant activation geometry, and solves a source-anchored optimization objective in closed form, which suppresses update components aligned with high-energy retained directions while preserving the source method's forgetting carrier. Across multiple unlearning methods, model scales, and benchmarks, SAGE consistently relieves the retain-forget trade-off, identifying post-hoc sanitization of final vectors as a practical and underexplored axis for machine unlearning.

15.
arXiv (CS.LG) 2026-06-19

DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

arXiv:2605.30456v2 Announce Type: replace Abstract: Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these problems are often accompanied by rich domain knowledge derived from physical laws, operational requirements, and expert heuristics. Such knowledge is frequently expressed as rules involving logical propositions and linear inequalities. Existing neuro-symbolic methods typically enforce these rules approximately through soft penalties, assume input-independent rules when designing specialized architectures, or rely on non-differentiable post-processing at inference time to achieve hard constraint satisfaction. While recent advances in differentiable optimization layers enable end-to-end feasibility enforcement within neural networks, extending these approaches to logical or mixed-integer rules remains challenging due to inherent nonconvexity. In this work, we propose a unified end-to-end framework for enforcing hard, input-dependent mixed integer linear constraints within neural networks. Our approach represents rules as disjunctive constraints and applies hierarchical convex relaxations to obtain convex hull formulations. These relaxations yield tractable linear constraints that can be embedded as differentiable optimization layers while enabling exact rule satisfaction. We demonstrate the effectiveness of the proposed framework on real-world datasets, achieving perfect rule satisfaction and strong predictive performance.

16.
arXiv (CS.AI) 2026-06-17

MIVE: A Minimalist Integer Vector Engine for Softmax LayerNorm and RMSNorm Acceleration

arXiv:2606.17781v1 Announce Type: cross Abstract: The rapid growth of Large Language Models (LLMs) has intensified the need for specialized hardware accelerators that can satisfy stringent inference latency and power constraints. Although matrix multiplications dominate the overall computational workload, non-linear vector normalization operations, such as LayerNorm, RMSNorm and Softmax can become critical hardware bottlenecks. Existing accelerators typically implement these functions using dedicated hardware blocks, leading to duplicated resources and inefficient silicon utilization. To address this limitation, we propose a Minimalist Integer Vector Engine (MIVE), a programmable architecture capable of executing all three operations within a unified datapath. By exploiting common computational patterns across LayerNorm, RMSNorm and Softmax the proposed vector engine maximizes hardware sharing while reducing implementation overhead. Physical ASIC implementation results show that MIVE provides comprehensive multi-function support while achieving higher area and hardware efficiency than most state-of-the-art standalone accelerators.

17.
arXiv (CS.AI) 2026-06-15

FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization

arXiv:2606.13737v1 Announce Type: cross Abstract: Stream guardrails enable token-level safety detection before full responses are generated. However, they often make overly conservative judgements and block those sensitive but safe tokens, which is known as over-refusal. Due to lack of full context, they also fail to detect implicitly harmful content from jailbreaking. To address these challenges, we propose FreoStream, a novel streaming guardrail framework. Specifically, FreoStream fine-tunes a LoRA module to perform Future-Aware Reasoning when the base guardrail detects unsafe tokens. The reasoning process follows a Future-Reason-Judge paradigm: predict the future, reason about the full context and give the final judgement. This design can effectively reduce over-refusal by incorporating the future information. Moreover, we introduce the Safety-Aligned Optimization module that extracts the safety-aligned component from the reasoning gradients to update the base guardrail model, thereby enhancing streaming safety detection. Extensive experiments on various safety benchmarks demonstrate that FreoStream achieves lower over-refusal rates and better jailbreak defense compared to existing streaming guardrails.

18.
arXiv (CS.CL) 2026-06-12

Operadic consistency: a label-free signal for compositional reasoning failures in LLMs

Detecting LLM reasoning failures at inference time without ground-truth labels has motivated a wide range of confidence baselines, including self-consistency, semantic entropy, and P(True), built on within-question sampling and self-evaluation. Operad theory, the formalism for systems built by iterated substitution, suggests a complementary diagnostic: a model's direct answer to a compositional query should agree with the answer it produces by composing a stated decomposition of the same query. We instantiate this idea as operadic consistency (OC), a per-question signal. Across twelve instruction-tuned LLMs (4B to 671B parameters, open-weights and closed-source) on four multi-hop QA datasets, OC is strongly correlated with accuracy on every dataset (Pearson $r \in [0.86, 0.94]$, all $p \leq 0.0004$), and is the only signal we evaluate with $r \geq 0.85$ uniformly across all four datasets. Chain-of-thought self-consistency (CoT-SC; Wang et al., 2023) matches OC on HotpotQA and DROP ($r = 0.93, 0.87$) but drops to $r \approx 0.45$ on MuSiQue and StrategyQA. At the per-question level, OC contributes information beyond CoT-SC and semantic entropy on every dataset (cluster-robust $p \leq 10^{-16}$ for the OC coefficient), and the conclusion is robust to additionally controlling for constructed decomposition-aware baselines ($p \leq 10^{-13}$). The same signal yields selective-prediction improvements (accuracy at fixed coverage) over a tuned CoT-SC baseline at the equal-cost $K = 3$ budget (AUARC lifts of +0.086 to +0.096 and AUROC lifts of +0.092 to +0.164; 95% CIs exclude zero on every cell). On five frontier thinking models, where the decomposition is extracted from the model's own chain of thought, the same equal-cost comparison gives positive selective-prediction point-estimate lift on all 16 (dataset, budget, metric) cells tested, with 95% CIs excluding zero on 12 of the 16.

19.
arXiv (CS.CV) 2026-06-18

Automatic ply-specific analyses of CFRP micrographs using shortest-path-based ply distinction

We present an automated approach to distinguish between ply instances in semantic segmentation masks of high-resolution carbon-fiber reinforced polymer micrographs. Interpreting the segmentation mask as a graph with pixels as vertices, enables us to use a shortest-path algorithm yielding the ply-separating paths. Thereby, we bridge the gap between semantic segmentation and ply instance segmentation using global information. We successfully apply our approach on high-resolution micrographs featuring a broad range of characteristics like artificially added gaps in single or multiple plies, different stacking sequences and ply traversing cracks. Assigning each fiber pixel to a ply based on the calculated paths, allows for a comprehensive, quantitative ply analysis with respect to its microstructural properties like the local fiber volume fraction as well as locally resolved ply and interleaf layer thickness. These insights help to reveal manufacturing-induced inhomogeneities, draw conclusions on manufacturing parameters and link mechanical properties to underlying microstructural imperfections.

20.
arXiv (quant-ph) 2026-06-11

TensorKit.jl: A Julia package for large-scale tensor computations, with a hint of category theory

arXiv:2508.10076v2 Announce Type: replace-cross Abstract: TensorKit$.$jl is a Julia-based software package for tensor computations, especially focusing on tensors with internal symmetries. This paper introduces the design philosophy, core functionalities, and distinctive features, including how to handle abelian, non-abelian, and anyonic symmetries through the ``TensorMap'' type. We highlight the software's flexibility, performance, and its capability to extend to new tensor types and symmetries, illustrating its practical applications through select case studies.

21.
arXiv (CS.AI) 2026-06-16

MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance

arXiv:2605.22664v3 Announce Type: replace Abstract: LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet enterprise needs, frontier AI labs have developed agents that can construct entire spreadsheets from scratch. This is especially relevant in finance, where core workflows such as financial modeling, forecasting, and scenario analysis are commonly conducted through spreadsheets. Yet, existing spreadsheet benchmarks do not measure this advanced capability, focusing instead on question-answering or single-formula edits. To address this gap, we provide one of the first evaluations of agents on end-to-end spreadsheet tasks, focusing on economically critical financial workflows such as modeling and scenario analysis. Since deliverables therein are routinely reviewed and revised by multiple stakeholders, judging their quality necessarily involves high-level criteria such as readability or ease of modification. To reflect the multidimensional nature of solution quality, we develop an evaluation taxonomy comprising three dimensions: Accuracy, Formula, and Format, each comprising fine-grained criteria that reflect professional standards. The Claude family leads the benchmark and produces the most professional-looking outputs in our qualitative review, but even the strongest agents frequently fall short of professional finance standards and degrade sharply as the difficulty increases beyond a few chained calculations. This suggests that current agents are not yet able to reliably produce professional-quality spreadsheets at the level of complexity real-world workflows demand.

22.
medRxiv (Medicine) 2026-06-18

Human Intuition vs. Computational Precision: Neurologists, Feature-based Models, and Deep Learning for Stroke Prognosis

Background: Prognostication in large vessel occlusion (LVO) stroke remains challenging. Although several prognostic models exist, their comparison to clinician performance, human-model interaction, and specific sources of human bias remain poorly understood. Methods: Using pre-treatment clinical and CT data from the MR CLEAN trial (n=500), six neurologists predicted three-month modified Rankin Scale (mRS) scores for 40 patients, both unaided and assisted by a validated feature-based model (MR PREDICTS). Human performance was benchmarked against MR PREDICTS and a multimodal, interpretable deep learning (DL) approach using raw imaging data. We explicitly assessed neurologists? ability to estimate model-required imaging features and identified systematic human biases. Models were additionally validated in a larger MR CLEAN trial cohort (n=404). Results: For predicting the full mRS distribution, standalone models achieved good ordinal agreement (MR PREDICTS quadratic weighted kappa (QWK) 0.51 [0.24 to 0.70]; DL model 0.49 [0.25 to 0.67]), significantly outperforming unaided neurologists (QWK 0.27 [0.10, 0.42]). Neurologists showed systematic overoptimism, predicting lower mRS scores than observed. Furthermore, there was poor accuracy in extracting imaging features. Raters? ASPECTS predictions deviated by 3.4 points from the confirmed scores, and collateral score accuracy was 44.6%. However, for predicting binary mRS (0-2 vs. 3-6), accuracy was comparable between unaided neurologists (64.17% [55.42% to 72.92%]) and models (MR PREDICTS 67.50% [52.50% to 82.50%]; DL model 63.16% [47.37% to 78.95%]). Model-assistance modestly improved and harmonized neurologists? predictions (QWK 0.41 [0.22 to 0.55]; binary accuracy 68.75% [58.33% to 78.34%]. Model performance remained robust in the larger cohort. Conclusions: Multimodal prognostic models outperform clinicians in predicting the full range of mRS outcomes, while human error in imaging assessment and systematic optimism bias are primary drivers of prognostic inaccuracy. End-to-end DL models eliminate human-input variability and hold strong potential as an automated second opinion to support prognostication and decision-making in acute LVO stroke.

23.
medRxiv (Medicine) 2026-06-15

Repurposing cardiovascular disease risk models to predict incident and co-occurring cardiovascular, cardiometabolic and neurocognitive outcomes.

Background: Cardiovascular disease (CVD), cardiometabolic and neurocognitive conditions share risk factors and frequently co-occur. We evaluated whether four established CVD risk prediction models (QRISK3, PCE, SCORE2, SCORE2-OP) can be repurposed to predict 10-year risk of these conditions and their co-occurrence with CVD. Methods: The models were recalibrated using 20% of the UK Biobank (UKB) and evaluated in the remaining 80%. We performed external validation using data from Clinical Practice Research Datalink (CPRD) Aurum, assessing model discrimination (c-statistics) and calibration (intercept and slope). We used permuted feature importance to determine the influence of each individual predictor in the models. Results: Depending on the model, the c-statistics for incident CVD ranged from 0.71 to 0.74 in the UKB test set (16,137 events). Discrimination was equal to or higher than CVD when evaluated against non-traditional CVD outcomes: 0.74 to 0.77 for heart failure (3,471 events), 0.72 to 0.73 for atrial fibrillation (9,213 events), 0.73 to 0.75 for peripheral arterial disease (1,927 events) and 0.80 to 0.82 for abdominal aortic aneurysm (595 events). For the multimorbidity endpoints, model discrimination ranged from 0.74 for the composite of CVD and T2DM (SCORE2-OP) to 0.83 for the composite of CVD and dementia or Parkinson's disease (QRISK3). When considering the onset of any cardiovascular, cardiometabolic, or neurocognitive outcome discrimination ranged from 0.71 to 0.72. The repurposed models slightly underestimated the predicted risk in the CPRD compared to the UKB: average difference in calibration intercept was at most -0.64. After age and sex, smoking status and systolic blood pressure contributed most to model predictions. Conclusions: Repurposed CVD models can be used to identify 10-year risk of many CVD-related conditions and their multimorbidity. These may be used to support risk-based approaches to prevention and screening. The repurposed models have been made available at: https://repurposed-cvd-risk-models.shinyapps.io/cvd_cmd_dementia_app/ Keywords: Risk prediction; cardiovascular disease; cardiometabolic disease; dementia; disease prevention.

24.
arXiv (CS.CV) 2026-06-16

Chronological Blindness: Benchmarking Temporal Reasoning in Vision-Language Models with CHRONOSIGHT

Human perception of visual scenes is inherently temporal. We instinctively recognise whether a fruit is ripening or rotting, whether construction is progressing or being demolished, and approximately how much time separates two photographs of the same subject. Whether large vision-language models (VLMs) share this competence remains an open and practically important question. We introduce CHRONOSIGHT, a rigorously controlled benchmark evaluating five dimensions of visual temporal reasoning: CHRONORANK (chronological ordering of image sequences), CHRONOLOCATE (ordinal stage localisation from a single image), CHRONODELTA (estimation of time elapsed between two images on a logarithmic scale), CHRONOREVERSE (detection of temporally reversed sequences), and CHRONOODD (identification of a temporal outlier within a set). The benchmark comprises 1{,}000 items across eight process families (biological growth, food transformation, physical weathering, construction, environmental change, human ageing, astronomical phenomena, and urban dynamics) spanning timescales from minutes to millennia. We evaluate eight open-source VLMs (500 M to 19 B parameters) under two prompting regimes and collect human performance baselines. Human performance averages 0.89 across tasks; the best open model (Qwen2.5-VL-7B) reaches 0.40 under direct prompting, a gap we term chronological blindness. Lightweight LoRA fine-tuning on 151 examples raises CHRONODELTA accuracy from near-zero to 0.43, transferring zero-shot to related tasks (CHRONOODD: 0.37; CHRONOREVERSE: 0.64)suggesting the bottleneck is partly instruction following rather than visual perception. Benchmark, code, and predictions will be released upon acceptance.

25.
arXiv (CS.AI) 2026-06-12

How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope

arXiv:2606.07489v2 Announce Type: replace Abstract: Frontier AI systems are bridging the gap between intelligence and utility by shifting from conversational assistants to autonomous agents that execute tasks end to end. Using production data from Perplexity's Search and Computer products, we study this transition by examining how AI agents accelerate and reshape knowledge work. Three key empirical findings emerge. First, using sessions with near-identical initial query pairs as natural experiments for the same underlying task attempted with both products, Computer performs 26 minutes of autonomous work per user session, versus 33 seconds for Search. Computer automates task decomposition and execution that Search users might otherwise manually orchestrate and implement. As a result, Computer shifts follow-up query distribution toward higher-order work such as verification and extension. Autonomy also increases execution quality, with per-query dissatisfaction rates 55% lower on Computer than on Search. Second, due to its autonomy advantage, Computer reduces completion time from 269 to 36 minutes on matched tasks, lowering estimated time and cost by 87% and 94%, respectively, compared to humans equipped with Search alone. Third, Computer changes the scope of work that users attempt: Computer queries more often cross occupational boundaries, require higher-order cognition, draw on broader expertise, take the form of composite tasks that bundle interdependent subtasks into a single query, and unlock work activities that are essentially absent from Search usage among the same users. Together, the evidence indicates that AI agents accelerate workflows, enhance output quality, reduce costs, and expand the breadth and depth of automated work.