中 EN
登录 注册账户

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。

登录 注册账户
01.
medRxiv (Medicine) 2026-06-23

Association between the hemoglobin albumin lymphocyte and platelet score and chronic kidney disease: insights from patient data and animal models

作者:
Zhang↗Wang↗Ye↗Chen↗Zhao↗

Introduction The hemoglobin, albumin, lymphocytes and platelets (HALP) score, a novel nutritional and inflammatory biomarker, has been used in various chronic disease studies. However, the relationship between the HALP score and chronic kidney disease (CKD) remains poorly elucidated. This study aimed to explore the possible association between the HALP score and CKD. Methods Our analysis encompassed 25,160 adult participants drawn from NHANES cycles spanning 2009 through 2018. Weighted multivariable logistic regression and generalized additive models (GAMs) were employed to evaluate the independent associations between the HALP score and CKD, albuminuria, and low-estimated glomerular filtration rate (eGFR). Threshold effects were examined using two-piecewise linear regression. Subgroup and sensitivity analyses were performed to assess robustness. Receiver operating characteristic (ROC) curve analyses were applied to compare the discriminative capacity of the HALP score with the prognostic nutritional index (PNI), systemic immune-inflammation index (SII), lymphocyte-to-monocyte ratio (LMR), and platelet-to-lymphocyte ratio (PLR). The clinical findings were further validated in a 5/6 nephrectomy rat model. Results After adjustment for multiple confounders, higher HALP scores were inversely associated with the risk of CKD (OR = 0.97, 95% CI: 0.94-0.99) and albuminuria (OR = 0.97, 95% CI: 0.93-0.99). However, after full adjustment for demographic characteristics, physical examination indices and laboratory parameters (Model 3), the correlation between the HALP score and low-eGFR was no longer statistically significant. Non-linear analyses revealed a threshold effect, with CKD risk declining as the HALP score increased up to an inflection point of 52.43 (OR = 0.97, 95% CI: 0.95-0.99), beyond which no further protective effect was observed. A similar threshold effect was identified for albuminuria. Subgroup and interaction analyses indicated no meaningful effect modification by age, sex, BMI, hypertension, or diabetes. Sensitivity analyses confirmed the robustness of the results. ROC analysis demonstrated that the HALP score showed superior discriminative ability for CKD and albuminuria compared with PNI, SII, LMR, and PLR. In the animal experiment, CKD model rats exhibited significantly lower HALP scores than controls. Inverse correlations were observed between the HALP score and serum creatinine (Scr), blood urea nitrogen (BUN), and urinary albumin-to-creatinine ratio (UACR), with UACR showing the strongest correlation, which was consistent with the clinical findings. Conclusion Lower HALP scores are independently associated with increased prevalence of CKD and albuminuria. As an affordable and readily measurable biomarker, the HALP score may facilitate CKD risk assessment.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-24

When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents

作者:
Tianyu Ding↗Juan Pablo De la Cruz Weinstein↗

Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test this proxy for pre-action policy classification in tau-bench using Qwen2.5-3B/7B classifiers. Under gold-policy conditioning, a compact structured state improves macro-F1 over raw trajectories by 0.13-0.17 after tuning. We then replace the benchmark-designated policy clause with the top-ranked clause retrieved from decision-time context. Although the exact governing clause is retrieved at rank 1 for only 7% of airline states, the primary 3B classifier obtains macro-F1 0.58 with retrieved clauses versus 0.60 with gold clauses (Delta=-0.02, task-cluster 95% CI [-0.23,+0.21]); mismatched-policy and no-policy controls score 0.32 and 0.21. We do not detect a macro-F1 difference between retrieved and gold clauses in this configuration, although the interval remains too wide to establish non-inferiority. The same qualitative pattern appears with a second retriever and at 7B, while varying across fine-tuning configurations. These results indicate that exact-match clause recall can underestimate downstream policy utility in this benchmark setting, motivating evaluation with retrieved policies in the classification loop rather than recall alone.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.AI) 2026-06-18

Towards Understanding What State Space Models Learn About Code

作者:
Jiali Wu↗Abhinav Anand↗Shweta Verma↗Mira Mezini↗

arXiv:2602.06774v2 Announce Type: replace Abstract: State Space Models (SSMs) have emerged as an efficient alternative to the Transformer architecture. Prior work shows that, when trained under comparable conditions, SSMs can match or surpass Transformers on code understanding tasks. However, their internal mechanisms remain a black box. We present the first systematic analysis of what SSM-based code models learn along with the direct comparison between SSM and Transformer models in this domain. Our analysis shows that SSMs capture syntactic and semantic structure more effectively than Transformers during pretraining but forgets certain relations during fine-tuning on some tasks. To investigate this behavior, we introduce SSM-Interpret, a frequency-domain framework that exposes a spectral shift toward short-range dependencies during fine-tuning. Guided by these findings, we propose architectural modifications that significantly improve the performance of SSM-based code model by upto +6 MRR on NLCodeSearch. This demonstrates that our analysis not only explains model behavior but also leads directly to better designs.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-24

CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking

作者:
Joeun Kim↗HoEun Kim↗Young-Sik Kim↗

Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining strict false-positive control. Existing ECC-based LLM watermarks rely largely on hard-decision decoding, discarding token-level reliability information. We propose CORE-BREW, a Constant-hit-Rate Embedding extension of block-wise BREW for robust multi-bit watermarking. CORE-BREW calibrates the watermark channel by targeting a fixed hit rate p-star, yielding closed-form per-token log-likelihood ratios (LLRs) for principled soft-decision decoding. It supports two detection modes: Strict-Safe, which preserves the bounded-distance designated-codeword acceptance region, and FPR-Calibrated, which uses likelihood-based scoring and lightweight list decoding to characterize the FPR-TPR trade-off. Experiments on open-source LLMs under token-level edits and paraphrasing demonstrate improved low-FPR discrimination and robustness over prior multi-bit watermarking baselines while maintaining comparable semantic quality.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CL) 2026-06-19

Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models

作者:
Hongliang Liu↗

Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output. We develop a budget normalized control window framework for single neuron steering. A dose along one write direction reduces to one control coordinate: the alignment between the residual stream and the write, driven along a universal saturation curve in units of a coherence budget set by the residual norm divided by the write norm. Coherent control exists when a behavior trigger lies below the collapse ceiling. The same coordinate governs benign mode switches and refusal; the ceiling follows from weights and one generic forward pass, while triggers are measured at rollout. On fifteen held out neurons, the predicted ceiling has mean absolute error 0.14, about 0.07 in bulk layers, and the committed open or closed verdict holds on eleven against a ten of fifteen majority baseline. Closed cases expose three failure modes rather than violations: collapse before trigger, too little depth to propagate, or a normalization that caps how far one neuron can push. The law explains why local gradient attribution anti predicts control: true controllers write off the readout axis and carry a near zero first order gradient. A forward only contrastive screen made precise by the window recovers controllers that attribution misses. On refusal, the hardest case, intervention success is typed, not scalar: coherent bypass and strict actionable reach separate, so a neuron can flip refusal in fluent, on task text with no actionable content, and genuine actionable reach appears only for three of six audited Llama pivots and only at later rollout horizons. Single neuron steering is therefore a budgeted, typed audit of controllability rather than a fixed dose anecdote.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CL) 2026-06-11

T2MM: An LLM Supported Architecture For Inquiry-Based Modeling

作者:
John Kos↗Rudra Singh↗Ashok Goel↗

Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts. We introduce Text to Multimodal Model (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment. To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics. Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.

阅读与讨论 → 访问原文 →
07.
PLOS Computational Biology 2026-06-03

IsoPepTracker: An interactive web application for peptide-driven isoform analysis

作者:
Araf Mahmud↗

by Araf Mahmud, Chen Huang Alternative splicing affects 95% of multi-exon genes, generating protein isoforms with distinct functions. While current alternative splicing analyses effectively identify splice events at the RNA level, they provide limited protein-level insight. To address this gap, we developed IsoPepTracker (https://www.isopeptracker.org), a user-friendly web application for analyzing and visualizing differential peptides across canonical and novel isoforms that are theoretically detectable by shotgun mass spectrometry-based proteomics. IsoPepTracker features four modules: Canonical Isoform Analysis, Novel Isoform Discovery, Peptide Sequence Search, and Alternative Splicing Analysis. Each module is tailored for distinct and complementary proteogenomics analyses. Users can input genes, novel cDNA sequences, peptides, or alternative splicing results to pinpoint peptides of interest and identify their associations with target genes or isoforms. We demonstrate the straightforward application of IsoPepTracker in proteogenomics through case studies. IsoPepTracker not only provides informative peptide signatures to understand the protein-level consequences of alternative splicing but also supplies peptide candidates for validation in shotgun proteomics.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-15

A Unified Framework for Structured Flow Modeling: From Representation to Verification and Model Discovery

作者:
Diego Casadei↗

arXiv:2605.18250v3 Announce Type: replace-cross Abstract: Many dynamical systems can be described in terms of structured flows combining source/sink behavior, cyclic dynamics, and topology-constrained transport. These features arise across a wide range of physical, engineered, and data-driven systems. The objective of this work is to establish a unified perspective on such systems, to identify modeling approaches that balance expressivity, interpretability, computational complexity, and data requirements, and to investigate how highly expressive models can be used to uncover the dominant mechanisms underlying observed dynamics. Starting from the Helmholtz-Hodge decomposition of continuous vector fields, we review the recently proposed Graph Vector Field (GVF) framework and its discrete representation on simplicial complexes. We then introduce a hierarchy of alternative approaches, including parametric conditional models, linear graph dynamical systems, and reduced Hodge representations. Finally, we propose a verification and validation methodology based on benchmark datasets from well-understood physical systems and on systematic model-reduction and ablation studies. The resulting family of structured-flow models within a common framework, ranging from low-dimensional parametric representations to full GVF formulations, supports a diagnostic methodology in which gradient, curl, harmonic, and topological contributions are systematically assessed through ablation studies. This process enables the identification of dominant mechanisms underlying the observed dynamics and guides the construction of simplified models tailored to the available data and operational constraints. By separating structural verification, behavioral verification, and domain-specific validation, the proposed approach provides a foundation for scalable and interpretable analysis of complex dynamical systems across multiple application domains.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CV) 2026-06-12

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models

作者:
Zeshang Li↗Shuoyang Zhang↗

Vision-Language Models (VLMs) hallucinate objects that are not present, and a growing line of work tries to curb this by feeding the model its own generated caption as auxiliary evidence – assuming that a caption, once available, is something to consume. We show this fails: naively appending a caption can lower accuracy rather than raise it, dropping Qwen2.5-VL-3B$^\dagger$ on HallusionBench by nearly ten points. To understand why, we build GD-Probe, a diagnostic set that pairs a global and a detail question on the same image, so that any difference in caption effect is attributable to the question alone. Caption utility proves to be a per-query property: the same caption helps global questions and harms detail ones, through a single mechanism – an embedded caption competes with the image for attention and pulls the model's evidence onto its own text – whose sign is set by whether the caption covers the queried content. Crucially, this regime is readable from quantities the decoder already emits, with no attention access or grounding. We turn this into GEASS (Gated Evidence-Adaptive Selective Caption Trust), a training-free, logit-level module that decides per query how much of the caption to trust, gating it by the clean path's confidence, weighting it by the entropy reduction it induces, and raising the evidence bar when the two pathways disagree. Across four VLMs and two benchmarks (POPE and HallusionBench), GEASS improves over both vanilla inference and contrastive decoding under a single fixed setting, adding only two forward passes and no parameters.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.LG) 2026-06-24

Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics

作者:
Chakshu Baweja↗

arXiv:2606.22054v2 Announce Type: replace-cross Abstract: Detectors for GNSS radio-frequency impairments (jamming, spoofing, multipath) are usually reported with a single AUC measured on the distribution they were tuned on. That number falls once conditions move, and the size of the drop is rarely known in advance because labelled field data is scarce. We ask whether this optimism can be predicted before any out-of-distribution data is seen. On an open, parameter-grounded synthetic testbed with a tunable severity shift, we evaluate thirteen detectors (five physics baselines, full-feature logistic regression and multilayer perceptrons, and single-feature learned controls) across four impairment classes. The optimism gap, the difference between in-distribution and shifted AUC, grows monotonically as the shift deepens (mean Spearman correlation 0.50). It is driven by how many observables a detector uses rather than by whether it is learned, and it varies systematically by class. Centrally, a ridge model built only from in-distribution score statistics predicts the gap for a detector it has never seen (R^2 = 0.47) and for an impairment class it has never seen (R^2 = 0.46); both are significant against a 2000-fold permutation null (p < 0.001) and survive removing the feature that is, by construction, part of the target. The headline findings are synthetic. We then run the pre-registered protocol on three open field corpora: on Jammertest 2024 the cross-detector prediction holds (R^2 = 0.11, p = 0.009), and on SatGrid, whose spoofer power sweep gives a calibrated severity axis, in-distribution AUC overstates higher-severity AUC by up to 0.22 and to the point of sign inversion, with in-distribution AUC and realised gap perfectly rank-correlated (Spearman rho = 1.0). The mechanism survives contact with real data, at smaller magnitude than in simulation. We release the testbed, a software-receiver front end, the ingest adapters and the protocol.

阅读与讨论 → 访问原文 →
11.
arXiv (quant-ph) 2026-06-24

Introduction to matrix-product states and tensor networks

作者:
Gr\'egoire Misguich↗

arXiv:2606.24803v1 Announce Type: cross Abstract: These notes provide an introduction to tensor-network methods in quantum many-body physics, with an emphasis on matrix-product states (MPS). They develop the basic tensor-network language, including graphical notation, virtual indices, bond dimensions, gauge freedom, canonical forms, QR and singular-value decompositions, and the role of entanglement in controlling the efficiency of the representation. The main MPS algorithms are then introduced, including contractions, correlation functions, matrix-product operators, DMRG, and time-evolution methods. The notes also briefly discuss projected entangled-pair states (PEPS) as a higher-dimensional generalization of MPS, together with the basic ideas behind approximate PEPS contraction. Finally, tensor-network representations of mixed states, quantum channels, and Lindblad dynamics are presented, with applications to thermal states and open quantum systems. The presentation is accompanied by short Julia code examples based on ITensor, ITensorMPS, and TensorMixedStates. These notes were written for the 9th Les Houches Summer School on Computational Physics: Open Quantum Systems, held in June 2026.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CL) 2026-06-11

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

作者:
Wanghan Xu↗Shuo Li↗Tianlin Ye↗Qinglong Cao↗Yixin Chen↗Hengjian Gao↗Yiheng Wang↗Qi Li↗Kun Li↗Sheng Xu↗Shengdu Chai↗Fangchen Yu↗…

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CV) 2026-06-19

Thinking in Boxes: 3D Editing in Real Images Made Easy

作者:
Pradhaan S Bhat↗Naveen Chandra R↗Rishubh Parihar↗Vaibhav Vavilala↗R. Venkatesh Babu↗D. A. Forsyth↗Anand Bhattad↗

Text and 2D-conditioning interfaces provide weak, ambiguous control over spatial transformations in image editing – particularly under large object motions and camera changes. Prior work has used 3D primitives such as boxes, but only as loose conditioning signals indicating approximate object location rather than specifying the transformation. We instead use 3D boxes as structured specifications: the user provides the input and output boxes of the edit, casting editing as a well-posed geometry problem. This ``thinking in boxes'' interface, where each box face is color-coded to convey 3D orientation, gives precise control over translation, rotation, scaling, and viewpoint changes in real images while preserving scene and object identity, and recovering previously unseen object regions. To ground transformations in scene appearance, we introduce a depth-aligned planar floor as a global reference frame, shaded with depth-aware cues. Conditioned on this structure, an image generator produces consistent results under large transformations. Trained in two stages – on synthetic multi-object scenes and a small set of real-world videos from Objectron – the system generalizes to complex, in-the-wild real images. Our method operates directly on real photographs and substantially outperforms recent state-of-the-art methods on large 3D edits.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-18

Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration

作者:
Junjie Xu↗Xingjiao Wu↗Zihao Zhang↗Yujia Xu↗Yuzhe Yang↗Jin Zhu↗Luwei Xiao↗Wen Wu↗Liang He↗

arXiv:2606.18259v1 Announce Type: cross Abstract: AI agents that plan, retain memory across sessions, invoke external tools and act with partial autonomy are transforming human–AI collaboration. Research on affective computing, simulated empathy in large language models, trust in automation and AI safety has illuminated important design principles, yet these literatures remain fragmented. No integrated account explains how affective cues operate within agentic collaboration – settings in which humans delegate, monitor and correct consequential tasks. This Review synthesises computational and interactional mechanisms of affective dynamics: the processes through which affective cues, emotion-like behaviour and perceived agent affect shape trust calibration, delegation decisions, error correction, dependence and governance. We trace how model-generated affective signals enter interaction loops that govern reliance, repair and oversight, and propose a framework that treats affect not as an internal property of AI but as a coordination layer through which humans and agents negotiate capability, uncertainty and responsibility. The framework provides a foundation for calibrated measurement, purposeful design and informed governance.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CL) 2026-06-18

Approximate Structured Diffusion for Sequence Labelling

作者:
Nicolas Floquet↗Joseph Le Roux↗Nadi Tomeh↗

Sequence labelling, a core task of Natural Language Processing (NLP), consists in assigning each token of an input sentence a label. From a Machine Learning point of view, sequence labelling is often cast as a Linear-Chain Conditional Random Field (CRF) parametrised by a neural network. While this approach gives good empirical results, CRFs assume a finite decision span (eg label bigrams) which can limit their expressivity and hurt performance when long-range dependencies are required. We show we can leverage diffusion to train a CRF conditioned on an entire label sequence, with the caveat that the condition is on a noisy version of labels. We show experimentally that this method, in conjunction with approximate CRF inference, improves label accuracy with a 16.5% error reduction for POS-tagging.

阅读与讨论 → 访问原文 →
16.
medRxiv (Medicine) 2026-06-18

Rare Coding Variants Reveal Distinct Genetic Architectures Across Multidimensional Sleep Phenotypes

作者:
Zhang↗Lu↗Kunorozva↗Jones↗S. E↗Maher↗Valliere↗Wood↗A. R↗Weedon↗M. N↗Tubbs↗…

Sleep and circadian traits have been widely studied using common variants, but the contribution of rare coding variation remains unclear. We analyzed rare coding variants in 397,065 whole-exome sequenced UK Biobank participants across 36 sleep phenotypes from self-report, diagnoses, sleep medication use and accelerometry, and meta-analyzed results with 171,536 whole-genome sequenced All of Us participants of diverse ancestries, with replication in the Mass General Brigham Biobank (N = 31,275). We identified 260 genes associated with sleep phenotypes, including novel associations with sleep medication use in 29 genes and 24 out of 29 have not previously been reported with any sleep phenotypes. We observed modest but significant rare variant heritability and strong genetic correlations between sleep medication use, insomnia and fatigue. Temporal gene expression trajectory analyses indicate that genes associated with self-reported sleep traits show constant high prenatal expression, whereas genes linked to sleep medication phenotypes exhibit peak expression in the late prenatal period. These findings highlight distinct biological mechanisms captured by different measurement sources of sleep phenotypes and reveal rare-variant-informed targets for therapeutic discovery.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CL) 2026-06-11

UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction

作者:
Sangmin Lee↗Eekgyun Ahn↗Woongjib Choi↗Hong-Goo Kang↗

We propose UR-BERT, a Romanized transcription-based text-to-speech (TTS) encoder for massively multilingual TTS systems. Conventional grapheme-to-phoneme (G2P)-based approaches are limited to around 100 languages due to the availability of reliable G2P resources. In contrast, UR-BERT scales to 495 languages by unifying diverse writing systems into a shared Romanization representation. To further enhance phonetic fidelity and text-speech alignment, we introduce a speech token prediction objective during training, which encourages the encoder to learn speech-aware phonetic representations in a data-efficient manner. Experiments show that TTS systems built on UR-BERT consistently outperform recent text encoder baselines across a wide range of languages and resource conditions, and demonstrate strong generalization to unseen languages.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.AI) 2026-06-12

PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent

作者:
Junfeng Guo Heng Huang↗

arXiv:2606.12896v1 Announce Type: cross Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration. In particular, recent work has revealed that RL agents are vulnerable to backdoor attacks, where a victim agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing backdoor defenses for RL either require access to the agent's internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL agents, we propose \texttt{PolicyGuard}, a test-time step-level backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.

阅读与讨论 → 访问原文 →
19.
arXiv (quant-ph) 2026-06-24

Clifford Volume and Free Fermion Volume: Complementary Scalable Benchmarks for Quantum Computers

作者:
Attila Portik↗Orsolya K\'alm\'an↗Thomas Monz↗Zolt\'an Zimbor\'as↗

arXiv:2512.19413v2 Announce Type: replace Abstract: As quantum computing advances toward the late-NISQ and early fault-tolerant eras, scalable and platform-independent benchmarks are essential for quantifying computational capacity in a classically verifiable manner. We introduce two volumetric benchmarks, Clifford Volume and Free Fermion Volume, that assess quantum hardware by testing the execution of random Clifford and free fermion operations. These two groups of unitaries possess a combination of properties that make them ideal for benchmarking: (i) each is individually efficient to simulate classically, enabling verification at scale; (ii) together they form a universal gate set; (iii) they serve as essential algorithmic primitives in practical applications (including shadow tomography and quantum chemistry); and (iv) their definitions are formulated abstractly, without explicit reference to hardware-specific features such as qubit connectivity or native gate sets. This framework thus enables scalable and fair cross-platform comparisons and tracks meaningful computational advancement. We demonstrate the practical feasibility of these benchmarks through extensive numerical simulations across realistic noise parameters and through experimental validation on Quantinuum's H2-1 trapped-ion quantum computer, which achieves a Clifford Volume of 34.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.CL) 2026-06-24

Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment

作者:
Arush Tagade↗Shaoheng Zhou↗Jiaxin Wen↗Shi Feng↗

Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content. Motivated by this connection, we study self-generated text recognition (SGTR) finetuning as a character-targeted intervention that is distinct from existing in-training defenses. We conduct two-stage finetuning experiments across three models (GPT-4.1, Qwen2.5-32B-Instruct, Seed-OSS-36B-Instruct) and multiple EM datasets to compare SGTR finetuning against benign finetuning baselines (correct domain-specific data, general knowledge, and word counting) to find it an effective defense in both reversal and prevention settings. We find that all interventions produce comparable EM reversal, but only when restoring capabilities that EM had degraded. For prevention, only SGTR finetuning consistently reduces misalignment without exacerbating any individual metric, suggesting that character fortification specifically drives prevention. We provide further evidence for EM's relation to the LLM's default character by showing that EM finetuning induces diversity into the LLM's identity self-reports, artificially corrupting self-recognition exacerbates misalignment caused by EM finetuning, and that removing the model's identity-bearing system prompt substantially reduces the effect of EM finetuning. Together, these findings reframe EM not as the adoption of a coherent misaligned persona but as the destabilization of aligned character.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-16

Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft

作者:
Juheon Yi↗Jinglu Wang↗Xiaoyi Zhang↗Yan Lu↗

arXiv:2606.15684v1 Announce Type: new Abstract: We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks. Our benchmark reflects four core characteristics of real-world collaboration: agent heterogeneity, mandatory collaboration, dynamic environments, and strict real-time constraints with failure risks. To enable this, we develop the TickingCollab framework, which supports the generation of diverse dynamic environments and abstracts Minecraft's primitive APIs to enable declarative YAML task specifications for composing these events. Building on this, we design a feasibility-aware automated benchmark generation pipeline, where an LLM drafts structurally diverse task configurations and feasibility verifier filters out invalid ones using approximate constraints. Evaluations demonstrate that lang latency and inherent difficulty of coordinating under partial observability and agent heterogeneity cause LLMs to frequently fail under dynamic environments and fall significantly short of a global-knowledge oracle.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CV) 2026-06-16

AI for Maritime Security: Comparative Evaluation of CNN and Vision Transformer Architectures for Maritime Object Detection

作者:
Ismet Gocer↗Zakirul Bhuiayn↗Shakeel Ahmad↗Raza Hasan↗

This study aims to enhance maritime security by using advanced Artificial Intelligence (AI) and Computer Vision (CV) techniques. For this purpose, it was designed and assessed intelligent object detection systems that can detect the presence of ships on the sea surface under different real-time environments. To achieve this goal, a maritime image dataset with 6,468 images was used, covering different weather conditions like cloudy, foggy, rainy, and sunny environments. Six deep learning architectures were evaluated, including a base Convolutional Neural Network (CNN) model, four transfer learning models (Xception, VGG16, MobileNetV2, and EfficientNetV2L), and a Vision Transformer (ViT) model. The models were compared using multiple performance indicators, including accuracy, Type I and Type II errors, model size, and video processing time. The results show that model performance varies depending on computational constraints and deployment conditions. While lightweight architectures are suitable for resource-limited devices, the ViT achieved the best overall performance, reaching 100% accuracy with the lowest error rates and the fastest video processing time. The findings highlight the potential of AI-driven computer vision systems for maritime surveillance, border protection, and autonomous navigation.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-12

MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback

作者:
Zehong Wang↗Yijun Ma↗Connor R. Schmidt↗Tianyi Ma↗Weixiang Sun↗Ziming Li↗Xiaoguang Guo↗Chuxu Zhang↗Matthew J. Webber↗Yanfang Ye↗

Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle physics. Designing an MD pipeline for a new system requires substantial expert knowledge: running it on even one molecule is expensive, ruling out trial-and-error. We automate this expert pipeline-design process with an LLM agent. Unlike existing MD agents that orchestrate a predefined tool set, we treat pipeline design as open-ended code generation in which the agent's behavior is reshaped online by verbal reward. Specifically, we build MDForge, an LLM agent whose in-context update rule densifies the sparse reward via a multi-agent debate among physics experts. On three SAMPL host-guest binding free-energy benchmarks, MDForge automatically designs MD pipelines competitive with human experts. Deployed on a library of unseen candidate guests, its CB[7] pipeline discovers a novel binder that wet-lab competition NMR confirms is a high-affinity, picomolar CB[7] binder. Our data and code are available at https://github.com/Zehong-Wang/MDForge.

阅读与讨论 → 访问原文 →
24.
medRxiv (Medicine) 2026-06-15

Validating Field-Feasible Measures of Recent Khat Use: A Diagnostic Accuracy Study Comparing Amphetamine Immunoassay and Assisted Self-Report Against HPLC in an Ethiopian Male Cohort

作者:
Atkinson↗H. F↗Mekonnen↗Suleman↗Oetzel↗Soboka↗Widmann↗Toennes↗S. W↗Tesfaye↗Stewart↗S. A↗…

Background: Khat (Catha edulis) is a widely consumed natural amphetamine-analog used across East Africa and the Arabian Peninsula. Accurate field-feasible measurement of recent khat use is a prerequisite for large-scale epidemiological research; yet no validated alternatives to laboratory reference methods have been identified in the scientific literature. This nested validation study evaluated the diagnostic accuracy of two point-of-care measures, a commercial amphetamine immunoassay and a Timeline Followback (TLFB) Assisted Self-Report (ASR), against high-performance liquid chromatography (HPLC) quantification of urinary norephedrine (NE), while additionally assessing agreement between the two field measures. Methods: A prospective, random sub-sample of 119 male participants aged 18-40 years from the Gilgel Gibe Field Research Center (GGFRC) longitudinal cohort, Ethiopia (validation timepoint T2, 2015), was used. Three index-reference comparisons were conducted: (1) amphetamine immunoassay (nal von minden, Drug-Screen AMP test, 300 ng/mL cutoff) vs. HPLC; (2) binary ASR (past-week use) vs. HPLC; and (3) binary ASR vs. immunoassay. Sensitivity (positive percent agreement, PPA), specificity (negative percent agreement, NPA), positive predictive value (PPV), negative predictive value (NPV), overall accuracy (overall percent agreement, OPA), and Cohen's kappa were calculated with 95% confidence intervals. Pre-specified secondary analyses applied three pharmacokinetically-informed recall windows (0-2, 3-5, and 6-7 days prior to interview) to ASR. Results: Against HPLC (77 positive, 42 negative), the immunoassay showed perfect specificity (1.0 [0.916-1.0]) and PPV (1.0 [0.91-1.0]) but low sensitivity (0.52 [0.40-0.64]), NPV (0.53 [0.42-0.65]), overall accuracy (0.69 [0.60-0.77]), and weak kappa (0.43 [0.34-0.52]). Binary ASR showed high sensitivity (0.96 [0.89-0.99]), specificity of 0.60 [0.433-0.74], PPV (0.81 [0.72-0.89]), NPV (0.89 [0.72-0.98]), with overall accuracy 0.83 [0.75-0.89] and moderate kappa (0.60 [0.51,0.69]). Restricting ASR to use within 0-2 days improved specificity to 0.69 [0.52-0.84], PPV to 0.86 [0.77-0.93], overall accuracy to 0.87 [0.79-0.93], and kappa to 0.69 [0.61-0.78] (moderate), while sensitivity (0.96 [0.89-0.99]) and NPV (0.89 [0.72-0.98]) remained stable. Against the immunoassay, ASR achieved high PPA of (1.0 [0.91-1.0]), NPA of 0.35 [0.25-0.47], OPA of 0.57 [0.48-0.66], and minimal kappa (0.27 [0.19-0.35]). Conclusions: Time-stratified ASR (0-2 days) is a valid, scalable alternative to biological testing for recent khat use in resource-limited settings. The immunoassay's 300 ng/mL cutoff functions as a marker of heavy or recent high-dose khat use rather than any-use detection. Its perfect specificity and PPV make it valuable as a confirmatory test for substantial exposure, while its lower sensitivity reflects calibration to amphetamine rather than to khat-derived cathinone metabolite. Keywords: khat; Catha edulis; diagnostic accuracy; STARD; self-report; immunoassay; HPLC; Ethiopia; substance use measurement

阅读与讨论 → 访问原文 →
25.
arXiv (CS.AI) 2026-06-12

The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements

作者:
Md Jafrin Hossain↗Mohammad Arif Hossain↗Weiqi Liu↗Nirwan Ansari↗

arXiv:2606.12797v1 Announce Type: new Abstract: Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage, and financial advising. We ask whether the frameworks used to build these systems provide architectural-level structural safety guarantees. Applying six containment principles derived from a compositional model of agentic architectures, we audit three dominant frameworks (LangChain, AutoGPT, and OpenAI Agents SDK) and find no native compliance in any of them. Memory integrity, a defense against one of the most prevalent vulnerability classes, is not observed in any of the three evaluated frameworks. We validate these findings empirically: in a simulated government benefits agent built on LangChain, a single memory-poisoning write induces persistent targeted corruption across all tested seeds and backends, increasing the wrongful denial rate for targeted applicants to 88.9%. Under a complex five-factor policy, the same attack preserves aggregate accuracy while increasing targeted wrongful denials by 3.5x, rendering the corruption difficult to detect through standard monitoring. We then introduce two lightweight containment mechanisms: a memory integrity validator and a policy gate, which eliminate both attack vectors with sub-millisecond overhead (

阅读与讨论 → 访问原文 →