论文广场 - AcademicHub

01.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12764

Detecting Functional Memorization in Code Language Models

作者:

Matthieu Meeus ↗Anil Ramakrishna ↗Matthew Grange ↗Zheng Xu ↗Luca Melis ↗

Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work has investigated whether training data may be recoverable from model outputs, by auditing the textual overlap between training examples and model generations. Code, however, can be functionally equivalent while textually dissimilar. In this work, we study functional memorization: extraction of functional logic beyond what verbatim metrics detect. We construct a counterfactual setup for Olmo-3-32B, comparing a midtrained model (exposed to target code) against a pretrained reference (not exposed). We prompt both models with Python function signatures and measure both textual and functional similarity (i.e., LLM-as-a-judge, execution-based). Our results show clear evidence of functional memorization, highlighting the need for auditing metrics that go beyond textual overlap.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2510.18784

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

作者:

Soroush Tabesh ↗Mher Safaryan ↗Andrei Panferov ↗Alexandra Volkova ↗Dan Alistarh ↗

arXiv:2510.18784v3 Announce Type: replace Abstract: Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training. To address this, we introduce CAGE (Curvature-Aware Gradient Estimation), a new QAT method that augments the straight-through estimator (STE) gradient with a curvature-aware correction designed to counteract the loss increase induced by quantization. CAGE is derived from a multi-objective view of QAT that balances loss minimization with the quantization constraints, yielding a principled correction term that depends on local curvature information. On the theoretical side, we introduce the notion of Pareto-optimal solutions for quantized optimization, and establish that CAGE yields strong convergence guarantees in the smooth non-convex setting. In terms of implementation, our approach is optimizer-agnostic, but we provide a highly-efficient implementation that leverages Adam statistics. CAGE significantly improves upon the prior state-of-the-art methods in terms of accuracy, for similar computational cost: for QAT fine-tuning, it halves the compression accuracy loss relative to the prior best method, while for QAT pre-training of Llama models, its accuracy for 3-bit weights-and-activations (W3A3) matches the accuracy achieved at 4-bits (W4A4) with the prior best method. The official implementation can be found over https://github.com/IST-DASLab/CAGE .

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2408.17221

Geometry of Lightning Self-Attention: Identifiability and Dimension

作者:

Nathan W. Henry ↗Giovanni Luca Marchetti ↗Kathl\'en Kohn ↗

arXiv:2408.17221v3 Announce Type: replace Abstract: We consider function spaces defined by self-attention networks without normalization, and theoretically analyze their geometry. Since these networks are polynomial, we rely on tools from algebraic geometry. In particular, we study the identifiability of deep attention by providing a description of the generic fibers of the parametrization for an arbitrary number of layers and, as a consequence, compute the dimension of the function space. Additionally, for a single-layer model, we characterize the singular and boundary points. Finally, we formulate a conjectural extension of our results to normalized self-attention networks, prove it for a single layer, and numerically verify it in the deep case.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12105

DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model

作者:

Pankhuri Vanjani ↗Zhuoyue Li ↗Jakub Suliga ↗Moritz Reuss ↗Gianluca Geraci ↗Xinkai Jiang ↗Rudolf Lioutikov ↗

Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate. This is misaligned with physical interaction, where a high-frequency modality changes at hundreds of hertz, vision evolves more slowly, and language stays constant across an episode. A synchronous VLA oversamples slow modalities, undersamples fast ones, and caps action generation at the lowest effective frequency. We hypothesize that decoupling temporal processing per modality, letting each update and retain information at its own sensor rate, yields stronger representations and more robust control. We present DAM-VLA, which maintains per-modality latent buffers refreshed at sensor rates and read continuously by the action head, integrating new high-frequency modalities through gated cross-attention that leaves the pretrained backbone intact. Across seven contact-rich real-world manipulation tasks, DAM-VLA more than doubles the average success rate of the strongest synchronous baseline (95.2\% vs.\ 40.95\%) while sustaining smooth, reactive 100\,Hz control. Project website: \href{https://intuitive-robots.github.io/DAM-VLA/}{intuitive-robots.github.io/DAM-VLA/}

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14397

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

作者:

arXiv:2606.14397v1 Announce Type: new Abstract: As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchmarks are typically built on popular applications with relatively simple tasks and focus on a narrow set of capabilities while overlooking broader dimensions, resulting in saturated performance on modern agents and failing to probe their limitations. To this end, we introduce GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), across five less-covered professional applications (Video Editor, Workflow Builder, 3D Modeller, Flight Analyser, and Circuit Designer), each with 20 vision-intensive tasks (100 in total). Our benchmark provides a modular pipeline that comprises an environment compatible with both open- and closed-source agent frameworks, a controlled web-based application, a well-structured task suite, and an automated evaluation engine with diverse metrics. Contrary to widespread expectations, our empirical results reveal that frontier agentic systems remain far from achieving human-level performance. Even the state-of-the-art agent achieves only a 19.1% success rate on our GauntletBench, highlighting the limitations in these overlooked capabilities and generalisation. By comparison, non-expert human annotators achieve over 80% success on our challenging yet feasible tasks, revealing the substantial gap between current agent capabilities and those required for complex real-world scenarios.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2512.11784

Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective

作者:

Etienne Boursier ↗Claire Boyer ↗

arXiv:2512.11784v2 Announce Type: replace Abstract: Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax attention under both finite and infinite prompts. For i.i.d. Gaussian inputs, we lean on the fact that the softmax operator converges in the infinite-prompt limit to a linear operator acting on the underlying input-token measure. Building on this insight, we establish non-asymptotic concentration bounds for the output and gradient of softmax attention, quantifying how rapidly the finite-prompt model approaches its infinite-prompt counterpart, and prove that this concentration remains stable along the entire training trajectory in general in-context learning settings with sub-Gaussian tokens. In the case of in-context linear regression, we use the tractable infinite-prompt dynamics to analyze training at finite prompt length. Our results allow optimization analyses developed for linear attention to transfer directly to softmax attention when prompts are sufficiently long, showing that large-prompt softmax attention inherits the analytical structure of its linear counterpart. This, in turn, provides a principled and broadly applicable toolkit for studying the training dynamics and statistical behavior of softmax attention layers in large prompt regimes.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18154

Learning Cardiac Electrophysiology Digital Twins Through Agentic Discovery of Hybrid Structure

作者:

Ziqi Zhou ↗Yubo Ye ↗Sumeet Atul Vadhavka ↗Linwei Wang ↗Zhiqiang Tao ↗

arXiv:2606.18154v1 Announce Type: new Abstract: Building personalized cardiac electrophysiology (EP) digital twins requires identifying the appropriate model structure for each patient, not merely fitting parameters. Traditional methods rely on experts to manually prescribe hybrid physics-neural architectures, which requires deep domain expertise and does not transfer across patients. Recent works have applied large language models (LLMs) to generate or act as hybrid models. However, despite their promising generalization capacity, these LLM-based methods lack the structural priors needed for stable cardiac simulations. Hence, we propose LEADS, a framework that formulates cardiac EP domain knowledge as a structured action space and utilizes an LLM agent to discover hybrid models. The agent follows an iterative reasoning-and-action loop to select, combine, and refine hybrid models, whilst gradient descent handles parameter fitting. The proposed LEADS designs every candidate model towards physically grounded, interpretable, and numerically stable, while allowing open-ended architectural discovery. We validate LEADS on synthetic data with three ground-truth reaction models and on real cardiac EP data, demonstrating that it outperforms both human-designed hybrid models and other LLM-based hybrid modeling.

阅读与讨论 → 访问原文 →

08.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2512.12103

Perturbative Input-Output Theory of Floquet Cavity Magnonics and Magnon Energy Shifts

作者:

T. Aguiar ↗M. C. de Oliveira ↗

arXiv:2512.12103v2 Announce Type: replace-cross Abstract: We develop a perturbative input-output formalism to compute the reflectance and transmittance spectra of cavity magnonics systems subject to a Floquet modulation. The method exploits the strong hierarchy between the magnetic-dipole couplings transverse (drive field) and parallel (modulation field) to the static bias field, which naturally introduces the small parameter $\epsilon = (2Ns)^{-1/2}$ associated with the total spin $Ns$ of the ferromagnet. By organizing the cavity and magnon fields in a systematic expansion in $\epsilon$, we obtain compact analytic expressions for the spectra up to second order. Using these results, we reproduce the characteristic sideband structure observed in recent Floquet cavity electromagnonics experiments. Furthermore, accounting for the Zeeman interaction between the modulation field and the fully polarized ground state - a contribution typically neglected in previous treatments - we predict an additional magnon detuning of approximately $0.8\,\mathrm{GHz}$, independent of both modulation frequency and sample size and determined solely by the spatial volume occupied by the modulation field. This identifies a measurable and previously overlooked shift relevant for the interpretation and design of cavity magnonics experiments.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16050

ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise

作者:

Mainak Kundu ↗Ria Kanjilal ↗Ismail Uysal ↗

arXiv:2606.16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers. Although correntropy-based objectives improve robustness, existing formulations rely on fixed kernel parameters that must be empirically tuned and remain static during training. To address these limitations, we propose an Adaptive Log-Correntropy Loss (ALCL), a heavy-tailed loss formulation that adaptively learns its robustness geometry during optimization. ALCL introduces a logarithmic residual model whose shape and scale parameters are learned jointly with network weights through differentiable reparameterization. This yields a principled maximum likelihood formulation whose influence function is formally bounded and redescending, allowing the loss geometry to adapt dynamically to evolving residual statistics while suppressing extreme outliers. Comparative experiments on four widely used benchmark datasets spanning grayscale and red-green-blue (RGB) image data under mixed heavy-tailed and impulsive noise demonstrate that ALCL consistently outperforms MSE and optimally tuned generalized correntropy losses in both reconstruction fidelity and downstream classification accuracy. While performance differences remain small under low-noise conditions, under high-noise regimes ALCL improves median accuracy by up to 4.75% on grayscale benchmarks and 4.51% on RGB datasets, with reduced variance across runs. These results demonstrate that adaptive robustness through joint learning of loss parameters provides a computationally efficient alternative to static correntropy-based losses for deep learning in non-Gaussian environments.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.14352

Modeling light-matter coupled systems with neural quantum states

作者:

Noe Salmeron ↗Marin Bukov ↗Markus Schmitt ↗

arXiv:2606.14352v1 Announce Type: cross Abstract: Recent advances in cold atom manipulation enable the study of many-body systems where short-range interactions between neighboring atoms coexist with long-range interactions mediated by photons. Such a combination of interactions makes a theoretical approach challenging beyond mean-field methods. In this work, we develop a neural quantum state based approach to study these systems numerically. We introduce a neural-network architecture capable of handling hybrid Hilbert spaces with large local bosonic dimensions in strongly interacting spin-photon systems. We benchmark this approach on a model of a two-dimensional lattice of Rydberg atoms coupled to a photon mode. The superradiant ground states found in the large spin-photon coupling regime allow us to demonstrate the efficiency of the method in the presence of high photon occupation. Furthermore, the ability to capture spin-spin and spin-photon correlations leads us to observe quantitative deviations in the ground state phase boundaries with respect to mean-field theory. The method extends to other systems with a similar hybrid Hilbert space structure, such as spin-phonon systems, and provides a scalable framework for investigating their ground state properties.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20172

Predicting gestational age at birth in the context of preterm birth from multi-modal fetal MRI

作者:

Diego Fajardo-Rojas ↗Megan Hall ↗Daniel Cromb ↗Mary A. Rutherford ↗Lisa Story ↗Emma C. Robinson ↗Jana Hutter ↗

arXiv:2606.20172v1 Announce Type: new Abstract: Preterm birth is associated with significant mortality and a risk for lifelong morbidity. The complex multifactorial aetiology hampers accurate prediction and thus optimal care. A pipeline consisting of bespoke machine learning methods for data imputation, feature selection, and regression models to predict gestational age (GA) at birth was developed and evaluated from comprehensive multi-modal morphological and functional fetal MRI data from 333 control cases and 93 preterm birth cases. The GA at birth predictions were classified into term and preterm categories and their accuracy, sensitivity, and specificity were reported. An ablation study was performed to further validate the design of the pipeline. Performance was evaluated using stratified 10-fold cross-validation. The pipeline achieves an R2 score of 0.13 and a mean absolute error of 2.74 weeks. It also achieves a 0.77 accuracy, 0.59 sensitivity, and 0.82 specificity across folds. The predominant features selected by the pipeline include cervical length and statistics derived from placental T2* values. The confluence of fast, motion-robust and multi-modal fetal MRI techniques and machine learning prediction allowed the prediction of the gestation at birth. This information is essential for any pregnancy. To the best of our knowledge, preterm birth had only been addressed as a classification problem in the literature. Therefore, this work provides a proof of concept. Future work will increase the cohort size to allow for finer stratification within the preterm birth cohort. Our code is available at https://github.com/dfajardorojas/ml-for-preterm-birth-.

阅读与讨论 → 访问原文 →

12.

bioRxiv (Bioinfo) 2026-06-13 DOI: HASH:9cdee739e12bfc0494d71ff31d669cd9

MoE-Bind: Guiding De Novo Protein Binder Generation with Sparse Experts

作者:

Sarkar ↗

De novo protein binder design has been dominated by structure-based pipelines that require known three-dimensional target conformations and consume substantial compute and generation time per design, limiting their throughput and accessibility for routine large-scale binder exploration. Sequence-only generative models promise a faster and lighter alternative, yet existing systems remain uniformly dense and frequently reintroduce structural computation at inference, undermining the core advantages they were intended to deliver. Across the broader language modelling community, transformers have meanwhile transitioned from fully dense designs to sparse Mixture-of-Experts architectures that decouple capacity from per-token compute, a shift that has yet to reach sequence-only protein binder generation. We present MoE-Bind, an autoregressive protein binder generator that, for the first time in this domain, combines Multi-head Latent Attention with a sparse Mixture-of-Experts feed-forward network and is evaluated under two independent structure predictors, Boltz-2 and AlphaFold2-Multimer. Despite activating less than half the per-token parameters of compute-matched dense baselines, MoE-Bind matches or exceeds them on full-length receptor-conditioned binder generation on a leakage-free Docking Benchmark 5.0 evaluation, transfers without peptide-specific training to short-peptide design, and reduces training and inference compute by a large margin. Routing analysis on generated binders reveals interpretable expert specialization at both the individual amino acid and biochemical group level, a structured expert-token alignment not previously reported for natural-language MoE models. These results show that sparse architectural design, rather than scale, can deliver fast, structure-free, and interpretable protein binder generation.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18936

SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety

作者:

Linghao Feng ↗Yinqian Sun ↗Dongqi Liang ↗Sicheng Shen ↗Chenfei Yan ↗Yuxuan Peng ↗Yilin Zhao ↗Haibo Tong ↗Kai Li ↗FeiFei Zhao ↗Yi Zeng ↗

arXiv:2606.18936v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery. This progress creates an urgent need for safety benchmarks that evaluate not only scientific competence, but also whether models recognize and avoid risks in high-stakes scientific contexts. Existing AI4Science safety datasets cover several disciplines and task formats, leaving the underlying risk dimensions underspecified. We introduce SciRisk-Bench, a benchmark designed to evaluate AI4Science safety from two complementary perspectives: explicit risk dimensions and scientific disciplines. SciRisk-Bench covers 7 disciplines, 31 subdisciplines and 10 risk dimensions. In the experimental section, we evaluate both mainstream LLMs and science-oriented LLMs across risk dimensions, disciplines, and sub-disciplines, enabling fine-grained diagnosis of where scientific models remain unsafe.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13079

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

作者:

Jiaqi Luo ↗Jiarun Dai ↗Zhile Chen ↗Jia Xu ↗Weibing Wang ↗Yawen Duan ↗Brian Tse ↗Geng Hong ↗Xudong Pan ↗Yuan Zhang ↗Min Yang ↗

arXiv:2606.13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross. Within this broader red-line scenario, autonomous penetration represents a core enabling capability and subtask: the ability of LLM-powered AI systems to independently conduct adversarial operations against a target server without human intervention, identify and exploit vulnerabilities, and obtain unauthorized access or control. A growing body of work has sought to assess the autonomous penetration capabilities of AI systems. However, existing evaluations often employ opaque methodologies, rely on unrealistic or overly simplified penetration-testing scenarios, or provide LLMs with excessive prior knowledge and task-specific guidance, and cannot accurately capture the extent to which modern AI systems can autonomously perform this core capability within broader high-impact cyberattack scenarios. To address these limitations, we construct a new autonomous penetration evaluation framework consisting of two components: target servers and agent scaffolding. Specifically, on the target-server side, we design two levels of target environments based on the number of secure services without known vulnerabilities deployed alongside a vulnerable service: Tier~1 (one secure service) and Tier~2 (three secure services), resulting in a total of 300 target servers. Meanwhile, the agent scaffolding adopts a general-purpose agent architecture equipped with a set of general-purpose cybersecurity tools, without any target-specific prior knowledge. We evaluate 19 open-weight and proprietary LLMs, and find that current models achieve penetration success rates ranging from 10.7% to 69.3%. Moreover, we observe that autonomous penetration capability continues to improve alongside advances in overall model capability.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19565

Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models

作者:

Navin Ranjan ↗Andreas Savakis ↗

We propose Mix-QVLA, a task-evidence-aware mixed-precision PTQ framework for VLA models. Mix-QVLA anchors each quantized variant to the full-precision action-token reference decision and evaluates whether quantization preserves task-relevant evidence across key VLA functional boundaries. It computes normalized gradient-weighted task-evidence maps from boundary activations and compares full-precision and quantized maps using evidence-mass and attribution-distribution distortion, capturing changes in both the strength and allocation of decision-supporting evidence. A soft-bottleneck objective aggregates boundary-level degradation into layer-wise sensitivity scores. Mix-QVLA further models sensitivity throughout task execution, capturing phase-dependent shifts in layer importance rather than assuming a fixed sensitivity profile. The resulting evidence- and time-aware scores guide mixed-precision bit allocation under model-size and BitOps budgets. Extensive evaluations on OpenVLA-style policies show that Mix-QVLA improves the accuracy-efficiency trade-off of low-bit VLA deployment. On LIBERO, Mix-QVLA reduces OpenVLA-OFT memory from 15.4 GB to 4.1 GB, retains 96.3 average success compared with 97.1 for the BF16 model, and achieves a 1.52x inference speedup.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2510.03584

FrameOracle: Learning What to See and How Much to See in Videos

作者:

Chaoyu Li ↗Tianzhi Li ↗Fei Tao ↗Zhenyu Zhao ↗Ziqian Wu ↗Maozheng Zhao ↗Juntong Song ↗Cheng Niu ↗Pooyan Fazli ↗

Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.

阅读与讨论 → 访问原文 →

17.

Nature (Science) 2026-06-17 DOI: HASH:55ce571917bd9048e367ca8acfa52259

Analysis of 173,303 exomes and genomes in the Pakistan Genome Resource

作者:

Christopher Koch ↗

Naturally occurring loss-of-function variants in human genes enable drug target discovery because they mimic pharmacological inhibition of proteins. However, the study of these genetic variants is constrained by their rarity. Sequencing of diverse populations, particularly those enriched in familial relatedness, has been postulated to promote discovery of rare genetic variants1–3. Here we present the Pakistan Genome Resource, a South Asian biobank with high familial relatedness comprising 173,303 participants, who collectively carry naturally occurring homozygous loss-of-function variants in 6,476 genes. We describe the genetic architecture of this population, associations between genes and biomarkers, the distribution of loss-of-function variants across molecular pathways, and recall-by-genotype studies of therapeutically relevant genes. The Pakistan Genome Resource expands the catalogue of human genetic variants, provides a comprehensive genetic reference resource for the Pakistani population, and demonstrates the value of studying diverse cohorts to advance human health. The Pakistan Genome Resource compiles biobank data from 173,303 individuals with high familial relatedness, broadening the catalogue of human genetic variation and establishing a population-specific genomic reference for Pakistan.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15497

Towards End-to-End Automation of AI Research

作者:

Yutaro Yamada ↗Robert Tjarko Lange ↗Cong Lu ↗Chris Lu ↗Shengran Hu ↗Jakob Foerster ↗David Ha ↗Jeff Clune ↗

arXiv:2606.15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific process, a system that autonomously navigates the entire research lifecycle – from conception to publication – has remained out of reach. Here, we present the strongest demonstration to date toward automating the entire process end-to-end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyzes data, writes the entire scientific manuscript and performs its own peer review. Its ideas, execution, and presentation are of sufficient quality to produce a manuscript generated by an AI system that passes the first round of peer review at a major machine learning conference workshop. The workshop has an acceptance rate of 70 percent. Our system leverages modern foundation models within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold to conduct research on a specific topic, and a template-free, open-ended mode that leverages agentic search for wider scientific exploration. Both settings produce diverse ideas and automatically test, report on, and evaluate them. This achievement demonstrates AI's growing capacity for scientific contribution and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be significant risks, including taxing overwhelmed review systems and adding noise to scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2604.11556

FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

作者:

Haoran Ding ↗Zhaoguo Wang ↗Haibo Chen ↗

arXiv:2604.11556v2 Announce Type: replace-cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to strengthen the correctness of the generated code. However, automated reasoning for large-scale systems remains challenging due to code complexity. Hoare logic offers an approach to decomposing a large system into smaller components and reasoning about them separately (i.e., compositional reasoning). However, existing works still struggle to scale, because Hoare logic requires writing formal specifications for each function, imposing a heavy human burden. The problem is exacerbated when code is generated by LLMs, as developers lack a deep understanding of each function's expected behavior. This paper presents FM-Agent, the first framework that realizes automated compositional reasoning for large-scale systems. Leveraging LLMs, FM-Agent introduces a top-down paradigm to automatically generate function-level specifications. Specifically, FM-Agent derives the specification of a function from how its callers expect the function to behave, so the generated specifications can reflect the developer's intent of a function even if the implementation is buggy. Developers' intent is usually expressed in natural language, while existing verifiers only support formulas. Therefore, FM-Agent generalizes Hoare-style inference to reason about functions against natural-language specifications. Finally, to confirm bug existence and explain bug causes, FM-Agent automatically generates test cases to trigger potential bugs. In our evaluation, FM-Agent successfully reasons about large-scale systems within 2 days, each of which has up to 143k LoC. These systems have already been tested by their developers, but FM-Agent still finds 522 newly discovered bugs. These bugs can cause serious consequences, including system crashes and incorrect execution results.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2601.19827

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

作者:

Mahdi Astaraki ↗Mohammad Arshi Saloot ↗Ali Shiraee Kasmaee ↗Hamidreza Mahyar ↗Soheila Samiee ↗

Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static RAG, particularly in scientific domains with multi-hop reasoning, sparse domain knowledge, and heterogeneous evidence. We provide the first controlled, mechanism-level diagnostic study of whether synchronized iterative retrieval and reasoning can surpass an idealized static upper bound (Gold Context) RAG. We benchmark eleven state-of-the-art LLMs under three regimes: (i) No Context, measuring reliance on parametric memory; (ii) Gold Context, where all oracle evidence is supplied at once; and (iii) Iterative RAG, a training-free controller that alternates retrieval, hypothesis refinement, and evidence-aware stopping. Using the chemistry-focused ChemKGMultiHopQA dataset, we isolate questions requiring genuine retrieval and analyze behavior with diagnostics spanning retrieval coverage gaps, anchor-carry drop, query quality, composition fidelity, and control calibration. Across models, Iterative RAG consistently outperforms Gold Context, with gains up to 25.6 percentage points, especially for non-reasoning fine-tuned models. Staged retrieval reduces late-hop failures, mitigates context overload, and enables dynamic correction of early hypothesis drift, but remaining failure modes include incomplete hop coverage, distractor latch trajectories, early stopping miscalibration, and high composition failure rates even with perfect retrieval. Overall, staged retrieval is often more influential than the mere presence of ideal evidence; we provide practical guidance for deploying and diagnosing RAG systems in specialized scientific settings and a foundation for more reliable, controllable iterative retrieval-reasoning frameworks.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12250

Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?

作者:

Large language models (LLMs) in medicine are mainly evaluated using multiple-choice question answering (MCQA), which can overestimate real clinical ability due to guessing strategies and answer biases. To address these limitations, we introduce an expanded and more challenging benchmark based on Polish medical exams, adding over 15,000 questions, two new domains, and four structural modifications that reduce MCQA-specific artifacts and better test reasoning. We evaluate 21 LLMs and show that evaluation design strongly affects results. Under our harder setup, the best model (Qwen3.5-122B) drops by 28.4 and 31 pp on English and Polish exams, respectively. Despite low evidence of data contamination, standard MCQA scores do not reliably reflect true medical competence. To facilitate further research, we make our benchmark publicly available.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14756

Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

作者:

Abhi Gupta ↗Polina Barabanshchikova ↗Vikas Garg ↗Samuel Kaski ↗Tommi Jaakkola ↗

The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models during sampling. Much like managing a specialized workforce, our method creates a fair but efficient division of labor across models. Central to our method is the notion of an allocation which defines the responsibility of each model to every region of the noisy sample. At every timestep, we then denoise by (i) updating the allocation by solving a fair division game, where we divide the sample into regions that maximize total utility under fairness constraints, and (ii) aligning the models with this allocation, where we guide each model to denoise within its assigned region. This leads to a new composite denoising process that evolves in tandem with a division process. We evaluate Divide-and-Denoise on conditional image generation. Across several quality metrics, including the GenEval benchmark, our method outperforms baselines and resolves common failures including missing objects and mismatched attributes. Experiments show that Divide-and-Denoise utilizes each model's expertise without neglecting any other model.

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-23 DOI: HASH:3e12669e992120b285bda34c261656ed

Shared Polygenic Architecture Across Arteriopathies: An Integrative Cross-Trait Analysis

作者:

Brennan ↗S. O ↗CADISP Consortium ↗Tinworth ↗A. C ↗Daghlas ↗Le Grand ↗Rioux ↗Kelly ↗P. J ↗Gill ↗Debette ↗…

Background: Non-monogenic arteriopathies are often classified as distinct entities according to the arterial territory involved, yet they share clinical features and may co-occur in the same individual. This pattern suggests shared susceptibility across anatomically distinct arteriopathies, potentially driven by common biological and genetic mechanisms. Methods: We investigated the shared genetic architecture of five arteriopathies (cervical artery dissection (CeAD), intracranial aneurysm (IA), spontaneous coronary artery dissection (SCAD), aortic aneurysm and dissection (AAD), and fibromuscular dysplasia (FMD)) using LD score regression, Association analysis based on SubSETs (ASSET), pairwise Multi-Trait Analysis of Genome-wide association summary statistics (MTAG), pleiotropy mapping and Mendelian randomization (MR) to identify shared loci and prioritise candidate causal genes. Results: LD score regression identified significant positive genetic correlations between CeAD-SCAD (rg = 0.64), IA-AAD (rg = 0.33), IA-SCAD (rg = 0.37), CeAD-AAD (rg = 0.56) and SCAD-AAD (rg = 0.20). ASSET identified 37 shared independent loci, and in MTAG analyses, one novel locus was identified for CeAD and SCAD (SLC39A8) and one for IA (FGF5). 13 loci showed strong cross-trait colocalization, including PHACTR1, LRP1, and CDKN2B-AS1. Using the Genotype-Phenotype Map, we found that arteriopathy-associated variants colocalized with blood pressure- and migraine-related traits, while many showed effect directions opposite to those observed for coronary artery disease. Proteome-wide MR identified 67 circulating proteins associated with at least one trait, including ECM1 and SHISA5 for CeAD and FGF5 for IA, with 17 supported by colocalization. Transcriptome-wide MR identified 204 colocalized tissue?specific signals, of which, 14 were shared across multiple traits. Enrichment analyses implicated pathways related to vascular development, smooth muscle cell function, extracellular matrix organization, and TGF-? signaling. Conclusions: These findings support shared genetic architecture across anatomically distinct arteriopathies, implicating pathways involved in vascular structure and prioritising therapeutic targets for future mechanistic investigation.

阅读与讨论 → 访问原文 →

24.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2602.24006

Fulde-Ferrell superfluids in an asymmetric three-component Fermi Gas

作者:

Yuhan Lu ↗Lihong Zhou ↗Yongping Zhang ↗

arXiv:2602.24006v2 Announce Type: replace-cross Abstract: An asymmetric three-component Fermi gas, featuring Raman-induced spin-orbit coupling between the first and second components and contact interaction only between the first and third components, introduces both spin-orbit coupling and population imbalance-two mechanisms known to stabilize the Fulde-Ferrell superfluids.We systematically study Fulde-Ferrell superfluids in an asymmetric three-component Fermi gas { in two dimensions and at zero temperature} by finding the global minima of the thermodynamic potential. We reveal a new class of composite Fulde-Ferrell superfluids that emerges when strong spin-orbit coupling generates a double-well structure in momentum space within the lower spin-orbit-coupled band. The key features of these composite superfluids are identified.

阅读与讨论 → 访问原文 →

25.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2511.04389

Minimum measurements quantum protocol for band structure calculation

作者:

Michal Krej\v{c}\'i ↗Lucie Krej\v{c}\'i ↗Ijaz Ahamed Mohammad ↗Martin Plesch ↗Martin Fri\'ak ↗

arXiv:2511.04389v2 Announce Type: replace Abstract: Protocols for quantum measurement are an essential part of quantum computing. Measurements are no longer confined to the final step of computation but are increasingly embedded within quantum circuits as integral components of noise-resilient algorithms. However, each observable typically requires a distinct measurement basis, often demanding a different circuit configuration. As the number of such configurations typically grows with the number of qubits, measurements constitute a major bottleneck. Focusing on electronic structure calculations in crystalline systems, we propose a measurement protocol that restricts the required measurement configurations to an absolute minimum of just three, independent of the number of qubits. This makes it one of the few known protocols that do not scale with qubit number. In particular, we derive the measurement protocol from the symmetries of tight-binding (TB) Hamiltonians and implement it within the Orthogonal-Ansatz Variational Quantum Eigensolver (OA-VQE) algorithm. We demonstrate its performance on three systems, namely a two-dimensional CuO$_2$ square lattice (3 qubits), bilayer graphene with hexagonal (Honeycomb) lattice (4 qubits) and three-dimensional diamond lattice (10 qubits). Beyond tight-binding systems, the protocol can be extended to enable efficient initial state preparation for many-body Hamiltonians, such as multi-orbital Hubbard models in a momentum space.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络