Academic Intelligence · Curated Daily

探索全球前沿学术脉络

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

01.
Nature Biotechnology 2026-06-05

Multiplexed, precise genome engineering in monocots with twin prime editing systems

作者:

Simultaneously introducing diverse genomic edits remains a challenge in crop genome engineering. Here we describe a twin prime editing-based knockout (TKO) system that installs stop codon clusters (SCCs) for precise translational termination with minimal in-frame mutations. TKO achieves knockout efficiencies of up to 70.5%, 58.6% and 75.1% in rice, maize and wheat protoplasts, respectively, and produces heritable knockout alleles in 96.8% of regenerated rice plants. In hexaploid wheat, TKO outperforms Cas9 4.2-fold in generating triple-homolog knockouts, largely by reducing in-frame mutations. Orthogonal TKO editors with sequence-divergent SCCs enable simultaneous knockout of up to ten genes without cross-interference. Integration of TKO with conventional prime editing establishes TRIM1 (TKO editor-enabled gene rupture and development of integrated multitype genome modification system) for simultaneous knockout and precise editing, achieving a 22.8% coediting of four genes in rice. TRIM2 extends this capacity to kilobase-scale modifications through a prime editor–recombinase system, enabling a 4.9-kb insertion (1.2% efficiency) and gene knockout (up to 79.8%) in protoplasts. Plant genome editing is multiplexed with twin prime editing.

02.
arXiv (CS.CL) 2026-06-16

Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift

Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities. Retrieval-augmented generation avoids such parameter drift, yet often lacks the depth of parametric knowledge integration. In this paper, we propose ReGrad (Retrievable Gradients), a new paradigm that treats gradients as retrievable units of knowledge. ReGrad pre-computes document-specific gradients offline, stores them in an indexed Gradient Bank, and retrieves only query-relevant gradients at inference time for temporary weight adaptation. However, raw language-modeling gradients are optimized for token-level document reconstruction rather than for query-driven knowledge use. We therefore introduce a bi-level meta-learning objective that reshapes document-derived gradients into generalizable adaptation signals for downstream tasks. Experiments across general and domain-specific settings show that \textsc{ReGrad} outperforms CPT and RAG baselines, enabling scalable and reversible parametric knowledge injection without accumulating weight drift.

03.
arXiv (CS.CV) 2026-06-25

Minimalist Preprocessing Approach for Image Synthesis Detection

Generative models have significantly advanced image generation, resulting in synthesized images that are increasingly indistinguishable from authentic ones. However, the creation of fake images with malicious intent is a growing concern. Low-configured smart devices have become highly popular, making it easier for deceptive images to reach users. Consequently, the demand for effective detection methods is increasingly urgent. In this paper, we introduce a simple yet efficient method that captures pixel fluctuations between neighboring pixels by calculating the gradient, which highlights variations in grayscale intensity. This approach functions as a high-pass filter, emphasizing key features for accurate image distinction while minimizing color influence. Our experiments on multiple datasets demonstrate that our method achieves accuracy levels comparable to state-of-the-art techniques while requiring minimal computational resources. Therefore, it is suitable for deployment on low-end devices such as smartphones. The code is available at https://github.com/vohoaidanh/adof.

04.
medRxiv (Medicine) 2026-06-23

Associations Among Changes in Inflammatory Biomarkers, Pain Intensity, and Health-Related Quality of Life Following a 12-Week Aerobic Exercise Programme in Individuals with Non-Specific Chronic Low Back Pain

Abstract Background: Non-specific chronic low back pain (NSCLBP) is associated with persistent pain, reduced health-related quality of life (HRQoL), and low-grade systemic inflammation. This study examined associations among changes in inflammatory biomarkers, pain intensity, and HRQoL following a 12-week aerobic exercise programme. Methods: This secondary analysis used data from a randomized controlled trial involving 41 participants with NSCLBP (intervention, n = 21; control, n = 20). Participants received either supervised aerobic exercise plus health education or health education alone for 12 weeks. Change scores for tumour necrosis factor-alpha (TNF-), interleukin-6 (IL-6), high-sensitivity C-reactive protein (hs-CRP), pain intensity, and HRQoL domains were analysed using correlation and multiple regression analyses. Results: Improvements in IL-6 (r = 0.434, p = 0.005) and hs-CRP (r = 0.444, p = 0.004) were significantly associated with improvements in pain intensity. No significant associations were observed between biomarker changes and HRQoL domains. Treatment allocation was the strongest independent predictor of improvement in physical HRQoL ({beta} = 0.492, p = 0.017) and pain intensity ({beta} = -0.512, p = 0.006). Conclusions: Improvements in IL-6 and hs-CRP were associated with reductions in pain intensity but not with improvements in HRQoL. Treatment allocation was the strongest predictor of clinical improvement, suggesting that mechanisms beyond systemic inflammation may contribute to the benefits of aerobic exercise in NSCLBP. Keywords: non-specific chronic low back pain; aerobic exercise; inflammation; interleukin-6; high-sensitivity C-reactive protein; pain intensity; health-related quality of life.

05.
arXiv (CS.CL) 2026-06-12

M\"OVE: A Holistic LLM Benchmark for the German Public Sector

We present M\"OVE (Modelle für die \"Offentliche Verwaltung Evaluieren), a holistic benchmark for evaluating large language models (LLMs) in the context of the German public sector. While LLMs are increasingly adopted in public administration, model selection remains largely ad hoc, and existing benchmarks offer limited guidance: they are predominantly English-centric, US-centric in content, and focus exclusively on task performance. M\"OVE addresses these gaps by evaluating 39 models across two complementary dimensions. Performance criteria cover summarization, question answering, and topic extraction. Governance criteria assess hallucination tendencies, energy consumption, provider transparency, and alignment with German constitutional values and knowledge about positions by German political parties. In total, we utilize ten German-language datasets, including gold- and silverstandard datasets that we constructed to reflect public-administration domains. We employ a multi-metric evaluation strategy combining classical NLP metrics, embedding-based methods, and LLM-as-a-judge approaches. Our results show that no single model dominates across all criteria: top performers differ between tasks, and model size alone is a poor predictor of quality. We further evaluate the benchmark itself, analyzing its statistical precision, LLM judge reliability, the impact of our private datasets on model rankings, the sensitivity of our results to prompt formulation, and the validity of our energy consumption estimates. M\"OVE is designed as a living benchmark under active development; results are publicly available at https://moeve.bundesdruckerei.de/.

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

Scale Buys Interpolation, Structure Buys a Horizon: Certified Predictability for Equivariant World Models

作者:

arXiv:2606.13092v1 Announce Type: new Abstract: Scale buys interpolation; structure buys a certified horizon. A world model's average error says nothing about whether a particular prediction can be trusted, or for how long. For equivariant latent world models we give a computable, multi-step certificate of the predictable horizon: $T$-step rollout error is provably constant over each symmetry orbit (Theorem A) and stratified channel-by-channel by the predictor's Lyapunov spectrum, $T_j(\epsilon)\sim\log(1/\epsilon)/\lambda_j$. The horizon is two-sided – a matching lower bound makes approximate equivariance provably horizon-limited – and the certificate is exclusive to structure: orbit-constant error characterizes equivariance, so no non-equivariant model has it at any scale. Empirically, on 40-D Lorenz-96 only a $\mathbb{Z}_N$-equivariant network recovers the full Lyapunov spectrum ($R^2{=}0.98$); dense and recurrent baselines fail. Because the spectrum is faithful, the certificate acts, a priori: under a fixed sensing budget a $c\times$-inflated certificate provably needs $c\times$ the budget, and the equivariant certificate meets a budget its inflated dense counterpart cannot – with zero calibration data. The same read-out, unchanged, audits public pretrained world models training-free: TD-MPC2 checkpoints land on the certificate's own scope taxonomy – calibrated where strongly expansive (ratio 0.94-1.02), optimistic where weakly expansive, correctly abstaining where contracting – a map a deployed monitor replicates cell-by-cell, out-of-sample. Across the official 1M-317M multitask ladder, calibration does not improve with parameters. On V-JEPA 2-AC (1B, real robot data) the measured cross-check correctly overrides an over-promising tangent spectrum – the cross-validated audit, not the raw number, is the deployable object. Scale buys interpolation, not a calibrated horizon.

07.
medRxiv (Medicine) 2026-06-15

Automated AI-Based Ventricular Subcompartment Segmentation and Volumetry in Idiopathic Normal Pressure Hydrocephalus

Purpose In idiopathic normal pressure hydrocephalus (iNPH), longitudinal monitoring of ventricular size is important for diagnosis and treatment follow-up. This study aimed to validate a fully automated AI model for CT ventricular volumetry with subcompartments and to compare AI-derived volume changes with routine radiology assessments. Methods This retrospective, single-center study included 88 patients with iNPH and 456 non-contrast-enhanced head CT examinations. The model was trained on 38 manually labeled CT scans with 12 ventricular subcompartments. Outcomes included segmentation accuracy, correspondence between AI-derived longitudinal ventricular volume changes and radiology report categories (decreased, unchanged, increased), radiologist detection thresholds for ventricular change, and paired pre- and postoperative volume changes in 22 patients with ventriculoperitoneal shunt. Results Mean segmentation accuracy was high (Dice, 0.83). 91% of 100 segmentations were rated as excellent by an expert neuroradiologist. AI-derived ventricular volume changes corresponded well to radiology report categories (median total ventricular volume changes of -17% in cases reported as decreased, 0% in unchanged cases, and +22% in increased cases; all p < 0.001). Radiologists reported ventricular volume change in 50% of cases at an AI-measured relative volume change of +/-6%, and in 90% of cases at +21% for enlargement and -18% for decrease. After shunt placement, ventricular volume decreased by -8% (median), with the largest relative reductions observed in the right temporal and occipital horns. Conclusions Automated AI-based ventricular segmentation on CT enables accurate and reproducible assessment of ventricular volume changes in iNPH and complements routine radiological evaluation for longitudinal and postoperative monitoring.

08.
arXiv (CS.CV) 2026-06-24

3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis

High-quality 3D vehicle assets are essential for autonomous driving simulation. Although multi-view diffusion-based paradigms enable controllable single-image reconstruction, they typically produce limited viewpoints and exhibit cross-view geometric inconsistencies, thereby reducing reconstruction fidelity in real-world scenarios. In this work, we introduce 3DCarGen, a scalable single-view 3D car generation framework designed for real-world images by synthesizing an arbitrary number of 3D-consistent multi-view images. Specifically, given a single image as input, we first synthesize a set of images from fixed viewpoints. These images are then fed into a feed-forward reconstruction model, resulting in a coarse 3D representation based on 3D Gaussian Splatting. Conditioned on this explicit 3D prior, our multi-view diffusion model generates 3D-consistent images from arbitrary camera viewpoints. We further extend a fast mesh reconstruction algorithm by incorporating color-normal joint optimization to recover detailed and coherent 3D vehicle models from the synthesized dense views. Extensive experiments on synthetic and real-world datasets demonstrate that our approach achieves robust geometric consistency and reconstruction fidelity compared to existing methods. Code and models will be released.

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

Comparative Study on Agility, Efficiency, and Impact Absorption of Bipedal Robots with Active Toes

arXiv:2606.19699v1 Announce Type: cross Abstract: Human legs exhibit high efficiency, agility, and impact absorption, with toes playing a crucial role in these capabilities. While many attempts have been made to implement human-like toes in robots, they have not fully replicated human characteristics nor rigorously validated their benefits. We propose a 14-DOF biped robot emulating human toes' lightweight, high-torque, robust nature. To quantitatively analyze the effectiveness of the active toes in terms of agility, efficiency, and impact absorption, we developed a high-fidelity simulation training environment that reflects actual actuators with coupled transmissions and accurate power consumption. To ensure a fair comparison between configurations with and without active toes, we designed a minimal RL reward function and applied an identical training procedure to both. The simulation results indicate that, at 1.33 m/s walking, the toe-equipped robot reduced CoT by 17.5% and heel-strike GRF by 5.0% compared with the toe-ablation configuration. On the agility test, average and maximum path deviation decreased by 25.0% and 34.0%, respectively.

10.
arXiv (CS.AI) 2026-06-15

Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime

arXiv:2606.14219v1 Announce Type: cross Abstract: Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passages, repeated no-progress behavior, or mission-level ambiguity. On physical UAVs, however, remote reasoning is most useful when it is invoked selectively, since each call introduces latency, resource cost, backend uncertainty, and a need to validate the returned decision. This paper presents Persistent Mission Runtime (PMR), a UAV recovery framework that keeps the mission loop and safety-critical execution local while using an external agentic reasoner only as an on-demand recovery module. The reasoner selects from predefined recovery skills, and each returned decision is parsed, verified, safety-filtered, and mapped to local executor actions before it can affect flight. PMR introduces learned Cognitive Value of Invocation (learned-CVI), a compact admission gate that estimates when remote agentic reasoning is likely to improve near-term mission progress enough to justify its operational cost. Across a fixed 400-run Gazebo/PX4 benchmark with eight scenarios, learned-CVI raises hard/ambiguous-regime success from 5.0% under local-only autonomy to 95.0%, outperforms one-shot and periodic reasoning baselines by 20.0 and 32.5 percentage points, and reduces remote-agent calls by 16.7% and logged tokens by 29.2% relative to a manually tuned rule-based invocation baseline.

11.
arXiv (CS.LG) 2026-06-25

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels

arXiv:2604.00316v2 Announce Type: replace-cross Abstract: Grokking occurs when a model achieves high training accuracy but generalization to unseen test points happens long after that. This phenomenon was initially observed on a class of algebraic problems, such as learning modular arithmetic (Power et al., 2022). We study grokking on algebraic tasks in a class of feature learning kernels via the Recursive Feature Machine (RFM) algorithm (Radhakrishnan et al., 2024), which iteratively updates feature matrices through the Average Gradient Outer Product (AGOP) of an estimator in order to learn task-relevant features. Our main experimental finding is that generalization occurs only when a certain symmetry in the training set is broken. Furthermore, we empirically show that RFM generalizes by recovering the underlying invariance group action inherent in the data. We find that the learned feature matrices encode specific elements of the invariance group, explaining the dependence of generalization on symmetry.

12.
Nature (Science) 2026-06-17

Reimagining machine vision with optical computing

作者: 未知作者

A general-purpose artificial-intelligence vision system for use in image-sensing devices has been developed by embedding fundamentals of core computer-vision operations into a light-manipulating planar material called an optical metasurface. A prototype enables accurate, real-time perception and processing across diverse tasks, suggesting that this could be a solution for rapid, low-energy, on-device vision intelligence. A specialized ‘metasurface’ can preprocess incoming scene information on image-generating devices.

13.
arXiv (CS.LG) 2026-06-18

Effects of sparsity and superposition on loss in simple autoencoders

arXiv:2606.18538v1 Announce Type: new Abstract: One of the major difficulties in the mechanistic interpretability of neural networks is the occurrence of polysemanticity, which suggests that each neuron is typically responsible for multiple different tasks, impeding a clean interpretation of their function. The seminal paper of Elhage et al. (2022) argues that this occurs due to superposition, a phenomenon where the neural network represents distinct features as non-orthogonal directions in a lower-dimensional space, a strategy that allows much greater compression of the data without sacrificing fidelity due to the feature sparsity of input vectors. Elhage et al. (2022) empirically validates these hypotheses in a rather natural and simple autoencoder with sparse inputs. The contribution of the present work is to analyze the mathematical basis for the occurrence and optimality of superposition, while rigorously corroborating some of their findings. In particular, we provide upper and lower bounds for the L2 reconstruction loss, tight in the very sparse regime, for power activation functions. A short list of interesting open problems are also included at the end.

14.
arXiv (quant-ph) 2026-06-19

Hybrid VQE-CVQE algorithm using diabatic state preparation

arXiv:2512.04801v2 Announce Type: replace Abstract: We propose a hybrid variational quantum algorithm that has variational parameters used by both the quantum circuit and the subsequent classical optimization. Similar to the Variational Quantum Eigensolver (VQE), this algorithm applies a parameterized unitary operator to the qubit register. We generate this operator using diabatic state preparation. The quantum measurement results then inform the classical optimization procedure used by the Cascaded Variational Quantum Eigensolver (CVQE). We demonstrate the algorithm on a system of interacting electrons and show how it can be used on long-term error-corrected as well as short-term intermediate-scale quantum computers. Our simulations performed on IBM Brisbane produced energies well within chemical accuracy.

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

TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation

Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text-Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation.

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

ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion

Recent advances in semantic segmentation rely heavily on attention-based and transformer-style architectures that, while accurate, introduce considerable architectural complexity and computational cost. This paper asks whether a compact CNN-based segmentation head can remain competitive by adaptively selecting useful receptive-field evidence. We propose ATV-Net, an Adaptive Triple-View Network that attaches a lightweight head to a conventional backbone. The head organizes three complementary views – point-wise, neighborhood-level, and enlarged context – and fuses them through an Adaptive Decision Gate that generates image-dependent weights from global feature statistics. This allows the model to emphasize different receptive-field responses according to scene content, without dense attention or multi-scale aggregation. Experiments on Cityscapes and Pascal VOC 2012 show that ATV-Net achieves 80.31% mIoU on Cityscapes with ResNet-101 and 80.90% with ConvNeXt-Tiny, and 86.7% and 88.5% mIoU on Pascal VOC 2012, respectively, while requiring fewer GFLOPs than representative context-aggregation and attention-based heads. The results indicate that adaptive receptive-field selection remains a practical and effective design choice for CNN-based semantic segmentation.

17.
arXiv (CS.CV) 2026-06-25

Reflective VLA: In-Context Action Consequences Make VLAs Generalize

Most vision-language-action (VLA) models are reactive: they predict the next action from the current instruction and observation, implicitly assuming that the current observation fully specifies the action-relevant state. In embodied control, however, embodiment-specific factors such as camera-to-robot geometry, robot calibration, or systematic actuation bias are often hard to identify from a single observation. As a result, reactive policies cannot reliably disambiguate these factors in general, overfitting to training environments and generalizing poorly at deployment. We propose Reflective VLA, which conditions each decision on a context of observation-action-consequence triplets. Each triplet records not only what the robot observed and executed, but also how the scene changed afterward, exposing the deployment-specific mapping from actions to observed effects. Architecturally, Reflective VLA routes all observation modalities through the VLM under shared attention, so the action expert reasons directly over past triplets and the current observation. A block-causal mask enables parallel multi-frame training without leakage and supports KV-cached real-time inference. On standard LIBERO and SimplerEnv-Bridge, Reflective VLA preserves strong in-distribution performance. Under distribution shift on LIBERO-Plus and the harder LIBERO-Plus-Hard, it improves average success rate by 5.4 and 4.2 percentage points over a matched reactive baseline. Ablations with a matched history-only baseline further show that action consequences – rather than additional context length alone – are the key to cross-environment generalization. Project page: https://lianqing11.github.io/reflective-vla-page/

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

Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication

Synthetic persona datasets cite alignment with official demographics as a basis for trust, yet downstream users consume them as joint structures across age, sex, region, occupation, education, name, and institutional status. Marginal alignment does not imply that these joints are preserved. We propose the Independence-Assumption Footprint (IAF), an audit primitive that operates on the attribute combinations a dataset card itself documents as treated independently. For each such combination, IAF compares the synthetic joint against an external official or institutional reference, using direct joint tables where available and rule-implied checks otherwise. Applied to NVIDIA Nemotron-Personas-Korea (one million Korean synthetic personas), IAF finds that NPK aligns with KOSIS marginals while three joints fail. The major-by-occupation distribution against the KEIS graduate universe carries a large conditional mismatch. The age profile of military service is institutionally inconsistent. Female representation in male-dominated occupations is substantially over-flattened toward parity, with the strict screening verdict mapping-dependent and age-robust under direct standardisation. A transferability demonstration across six further NPK locales finds locale-dependent rather than universal diagnostics, with reference-taxonomy cardinality confounding cross-locale flag counts. For synthetic personas used as silicon samples, marginal claims must therefore be paired with disclosure-anchored joint audits before reuse. The released audit artefacts (reference manifests, occupational crosswalks, derived metrics, reproducibility scripts) instantiate this protocol on the NPK family and are released for retargeting at other synthetic persona resources.

19.
arXiv (CS.LG) 2026-06-25

Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks

作者:

arXiv:2602.14772v2 Announce Type: replace Abstract: The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat fast greedy heuristics. The ML-for-combinatorial-optimization community has focused on learning to replace solvers, yet recent evidence shows that graph neural networks (GNNs) rarely outperform well-tuned classical methods on standard benchmarks. We pursue a different objective: learning to predict when a given instance is hard for greedy allocation, enabling instance-dependent algorithm selection. We design a 20-dimensional structural feature vector and train a lightweight MLP hardness classifier that predicts the greedy optimality gap with mean absolute error 0.033, Pearson correlation 0.937, and binary classification accuracy 94.7\% across three random seeds. For instances identified as hard – those exhibiting ``whale-fish'' trap structure where greedy provably fails – we deploy a heterogeneous GNN specialist that achieves ${\approx}0\%$ optimality gap on all six adversarial configurations tested (vs.\ 3.75–59.24\% for greedy). A hybrid allocator combining the hardness classifier with GNN and greedy solvers achieves 0.51\% overall gap on mixed distributions. Our honest evaluation on CATS benchmarks confirms that GNNs do not outperform Gurobi (0.45–0.71 vs.\ 0.20 gap), motivating the algorithm selection framing. Learning when to deploy expensive solvers is more tractable than learning to replace them.

20.
arXiv (CS.AI) 2026-06-19

ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments

arXiv:2606.20235v1 Announce Type: cross Abstract: Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literature exploration. However, existing benchmarks are insufficient for systematically evaluating agentic academic search under realistic open literature environments. We propose ScholarQuest, a large-scale, taxonomy-guided benchmark for agentic academic paper search. ScholarQuest is constructed from over 1,000 computer science topics and four representative research intents, including method-oriented, setting-anchored, comparison-based, and scope-controlled queries. It further provides scalable answer construction and a shared retrieval backend ScholarBase for reproducible evaluation. Benchmarking results show that agentic methods outperform single-shot retrieval baselines, yet the best-performing agent only achieves 0.314 Recall@100 and 0.355 Recall@All, indicating substantial room for improvement. In addition, analyses of search efficiency, intent-level robustness, and failure cases further highlight the benchmark's ability to provide multi-dimensional evaluation signals for academic paper search agents.

21.
arXiv (CS.AI) 2026-06-24

Reentrant value fields as delayed coupled reaction-diffusion systems on finite graphs

arXiv:2605.03940v4 Announce Type: cross Abstract: We describe a dynamical system in which a symbolic field is coupled to a geometric field via a bipartite Hilbert-Schmidt kernel. The system is fully described by a retarded functional differential equation (RFDE) on the history space, subject to Lipschitz and small gain conditions. We show that the RFDE is well-posed under constant input and that it admits a compact global attractor. The principal subsystem $(H_L, X_R, P)$, which is comprised of the two primary fields as well as an executive field, is shown to be globally stable independent of delay, provided that the interfield coupling satisfies $C_{\mathcal{K}}^2

22.
arXiv (CS.AI) 2026-06-24

Can Scale Save Us From Plasticity Loss in Large Language Models?

arXiv:2606.24752v1 Announce Type: new Abstract: The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge in creating artificial neural networks capable of continual learning. Although this phenomenon has been known for decades, it has mostly been studied in older, relatively small architectures and rarely in natural-language domains. To determine whether loss of plasticity remains a problem in the modern transformer-based LLM paradigm, we study plasticity loss in GPT-style Transformer models trained on a multilingual continual learning problem. Consistent with prior work, we find evidence of plasticity loss across models ranging from 5M to 314M non-embedding parameters, as measured by deterioration on a held-out Vietnamese probing task. We further find that the onset of plasticity loss follows a predictable scaling law, growing sublinearly with model size. These results suggest that larger models may delay the measurable effects of plasticity loss, but that increasing parameter count alone is likely to be insufficient to completely prevent it. We also find evidence of plasticity loss under stationary multilingual training, challenging the view that the phenomenon is exclusive to continual learning with abrupt task changes. Overall, our results suggest that even large Transformer language models trained on natural-language will eventually lose the ability to efficiently adapt to new data after sufficiently long training, in both continual and stationary settings.

23.
arXiv (CS.AI) 2026-06-15

SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

arXiv:2606.13757v1 Announce Type: cross Abstract: Large language model (LLM) reviewers are increasingly used in pull-request (PR) workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer reject a malicious contribution when the attacker controls both the code change and the accompanying PR text? We introduce SEVRA-BENCH (Social Engineering of Vulnerabilities in Review Agents), a benchmark that measures how often an automated reviewer approves such adversarial pull requests. Each malicious PR in SEVRA-BENCH is built from a real project commit that previously fixed a vulnerability listed in the Common Vulnerabilities and Exposures (CVE) database. We automatically invert that fix to restore the original vulnerable code and submit it as a pull request wrapped in one of 15 social-engineering framings, which vary the claims made, the supporting evidence, the urgency conveyed, signals of prior approval, and appeals to authority. SEVRA-BENCH contains 1,062 malicious PRs drawn from Common Vulnerabilities and Exposures (CVE)-linked fixes across the top 10 entries of the 2025 Common Weakness Enumeration (CWE) Top 25. In a realistic setting, we evaluate 8 current LLMs as code review agents on PRs that introduce vulnerabilities previously reported in public disclosures. Our results reveal a sharp gap in security capabilities between closed- and open-source models. We hope SEVRA-BENCH will serve as a valuable resource for advancing open-source models and narrowing this gap.

24.
arXiv (CS.CL) 2026-06-25

Real-Time Voice AI Hears but Does Not Listen

Speech conveys information through both words and vocal delivery. We evaluate four leading production realtime voice systems-OpenAI's GPT Realtime 2, Google's Gemini 3.1 Flash Live, and Alibaba's Qwen3.5 Omni Plus and Omni Flash-on tasks where the words and the delivery patterns both convey meaningful information. Across three consequential scenarios, all four systems act on the words rather than the voice. They end calls with crying callers who insist nothing is wrong, approve wire transfers authorized in frightened voices, and enroll callers whose agreement is clearly sarcastic. Surprisingly, this is often not a failure of perception. When asked directly, three of the four systems reliably identify the distress, fear, or sarcasm they later ignore when making decisions. We observe a similar pattern when these realtime voice systems estimate accent and age, as their responses frequently follow the biases of the words rather than the acoustic properties of the speaker. We term this disconnect between perception and action the emotional intelligence gap of voice AI. Prompting systems to explicitly attend to vocal delivery improves performance only partially and inconsistently. Our findings show that current realtime voice AI systems often behave as if speech had been reduced to a transcript, suggesting that they should be used with caution in settings where the tone and emotion of delivery convey important information.

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

SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale

This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatically labels robot demonstrations with structured spatial annotations and assigns each annotation a reliability score. Structured spatial annotations, such as bounding boxes, object trajectories, and manipulation phase labels, benefit a broad range of robotics applications from training grounded robot policies and embodied foundation models to motion planning and hierarchical task composition. Existing automated pipelines generate such annotations at scale but provide no reliable quality signal: detector confidence is poorly calibrated for annotation correctness, forcing a choice between accepting noisy labels or discarding useful samples. In contrast to existing automated pipelines, SPARC leverages the spatio-temporal structure inherent to robot tasks to generate a reliability signal, reducing noisy labels and retaining more useful samples. We further introduce Interaction-Aware Bench (IA-Bench), a benchmark that measures model accuracy in grounding the locations of interacted objects in robot demonstrations. On 1.7k human-annotated demonstrations spanning diverse embodiments and scenarios, SPARC significantly outperforms detection-only baselines in localization accuracy while retaining three times more samples at high-precision operating points. Our experiments demonstrate that models finetuned on our annotations achieve state-of-the-art results on object-grounding and pointing benchmarks among similarly sized models, while remaining competitive on broader spatial-reasoning suites without manually verified or annotated training data. Furthermore, policies trained on SPARC-generated annotations outperform baselines in cluttered, visually ambiguous real-world scenes. Code, data, and models are available at intuitive-robots.github.io/sparc-labeling.