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 (Science) 2026-06-10

Mitochondria directly interact with the nuclear pore complex

Mitochondria regulate cellular processes through direct and indirect interactions with other organelles. A well-studied example has been contact with the endoplasmic reticulum at mitochondrial-associated endoplasmic reticulum membranes1, which control pathways including redox and calcium homeostasis2,3. Recent studies have also reported direct mitochondria–nuclear membrane contacts in cancer cells and yeast that promote pro-survival signalling4,5. Here we identify direct interactions between mitochondria and nuclear pores. Using two unbiased proteomic screens, GST pulldown and BioID, we found that VDAC1 was the top mitochondrial candidate that interacts with the filamentous nuclear pore protein RANBP2. In vitro RANBP2 CRISPR knockout, RANBP2 truncation or site-directed mutagenesis of RANBP2–VDAC1 interacting amino acids resulted in reduced mitochondria–nucleus proximity and decreased nuclear ATP and phosphocreatine levels. This was accompanied by a decline in the levels of the nuclear phosphoproteome and downregulation of pathways involved in histone modification, cellular differentiation and transcriptional regulation in vitro. Moreover, deletion of the RANBP2 C-terminal domain in vivo in mice resulted in embryonic lethality due to cardiac and neural crest differentiation defects. Collectively, these results describe a mechanism by which mitochondria directly interact with the nuclear pore complex, a phenomenon critical for regulation of nuclear energetics and cellular differentiation. Undoubtedly, additional roles of this interaction remain to be revealed. Mitochondria interact directly with the nuclear pore complex via VDAC1–RANBP2 binding to sustain nuclear ATP levels.

02.
arXiv (CS.AI) 2026-06-18

Practical Anonymous Two-Party Gradient Boosting Decision Tree

arXiv:2605.26903v2 Announce Type: replace-cross Abstract: Structured data is well handled by gradient-boosted decision trees (GBDT), which are usually trained on vertically partitioned features across mutually distrustful parties. High speed and interpretability make GBDTs popular in finance and healthcare, where neural networks may fall short. Enabling secure computation for GBDTs poses unique challenges, requiring secure record alignment for comparison. Relying on private set intersection (PSI) is a de facto approach. Mistaking PSI for a safety measure actually exposes which record identifiers (IDs) are shared between the datasets. Although circuit-PSI could help, it is costly for generic uses. New ideas are needed to efficiently train in a "dark forest". Aiming to hide the IDs, we initiate the study of anonymous GBDT training on split data held by two parties. Dual circuit-PSI in our design lets the parties alternate as receiver to run pick-then-sum over local features. Via oblivious programmable pseudorandom functions, we propagate circuit-PSI outputs as shared state across runs. Avoiding universal alignment, we resolve the neglected dilemma that ID hiding incurs a cost that scales with domain size. Next, we halve the cost of ciphertext packing used to convert single-instruction multiple-data homomorphic encryption from (ring) learning with errors in prior secure GBDT (Usenix Security' 23) and related secure machine-learning computations. Comparative experiments show our protocol remains competitive with leaky approaches in efficiency. Enabling ID-hiding aggregation, our techniques can extend to other vertically partitioned analytics.

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

Multi-Modal Spatio-Temporal Graph Neural Network with Mixture of Experts for Soil Organic Carbon Prediction

Top-soil organic carbon (SOC) prediction is fundamental to agricultural sustainability, land use policy and fertilization planning. Existing approaches face two limitations: they pair hand-crafted covariates with classical ML or single-modal deep models that miss rich spectral and temporal information, and grid-based architectures ignore the irregular spatial structure of field measurements. We introduce SpTGNN, a multi-modal spatio-temporal graph neural network addressing both. SpTGNN represents soil measurements as nodes in a heterogeneous graph with three edge types (spatial proximity, spectral similarity, elevation), and applies relational graph attention to learn separate patterns per relation. A fine-tuned TerraMind encoder extracts node features from Sentinel-2, Sentinel-1 and DEM signals, combined with per-sample environmental covariates and learned positional and temporal embeddings. A sparse Mixture-of-Experts module fuses the four streams via top-$k$ routing. Uncertainty is captured by pairing heteroscedastic regression (aleatoric) with deep ensembles (epistemic), and a Moran's $I$ penalty regularizes spatial autocorrelation. We evaluate on a global SOC corpus split into three regional instances ($\sim$49k samples globally, Africa $\sim$26k, Europe $\sim$14k). Our 5-member deep ensemble reports $R^2=0.762$, RMSE $=3.51\pm0.48$ g/kg and MAPE $=22.9\%$ on the Africa test split, improving over a tabular XGBoost baseline; the best single checkpoint reaches validation $R^2=0.864$. Ablations confirm the heterogeneous graph, MoE fusion and fine-tuned backbone each contribute substantively, and the ensemble UQ stack achieves post-calibration ECE of $0.031$ (hybrid) and $0.026$ ($\beta$-NLL). To our knowledge, this is the first framework to unify foundation-model feature extraction, heterogeneous graph attention and decomposed uncertainty quantification for SOC estimation.

04.
arXiv (CS.CV) 2026-06-11

VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving

Vision-language-action (VLA) models can describe scenes and reason about them in language, yet still struggle to ground their actions in the dense 3D world around them. Existing approaches either inject features from a frozen 3D foundation model without an objective that ensures the policy uses them, or constrain geometry with sparse box and map losses that provide no dense spatial signal. We introduce VLGA, the first vision-language-action model supervised to reconstruct the dense 3D world it drives through. VLGA introduces geometry as a fourth modality alongside vision, language, and action through a dedicated expert supervised by a per-pixel pointmap regression loss against LiDAR. Extensive experiments conducted on challenging nuScenes and Bench2Drive datasets for open-loop and closed-loop evaluations, respectively, show the superiority of VLGA over counterpart VLA methods. In particular, on open-loop nuScenes, VLGA sets a new state of the art among VLA methods without ego status, with the lowest L2 (0.50\,m average) and 3-second collision rate (0.18\%). On closed-loop Bench2Drive, VLGA attains the state-of-the-art driving score of 79.08, +0.71 over the strongest prior VLA, at comparable efficiency and comfort.

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

MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs

Islamic inheritance law is challenging for large language models because solving inheritance cases requires complex, structured, multi-step reasoning and the correct application of juristic rules to compute heirs' shares. We introduce MAWARITH, a large-scale annotated dataset of 12,500 Arabic inheritance cases for training and evaluating models on the full reasoning chain: (i) identifying eligible heirs, (ii) applying blocking (\d{hajb}) and allocation rules, and (iii) computing exact inheritance shares. To the best of our knowledge, MAWARITH is the first Arabic corpus and benchmark designed for end-to-end Islamic inheritance reasoning. Unlike prior datasets that restrict inheritance case solving to multiple-choice questions, MAWARITH supports the full reasoning chain and provides step-by-step solutions with justifications grounded in classical juristic sources and established inheritance rules, as well as exact share calculations. This enables models to learn how to generate detailed, step-by-step responses to user queries that reflect real-world Islamic inheritance cases. To evaluate models beyond final-answer accuracy, we propose MIR-E (Mawarith Inheritance Reasoning Evaluation), a weighted multi-stage metric that scores key reasoning stages and captures error propagation across the pipeline. We evaluate six large language models in a zero-shot setting. A commercial model achieves about 90\%, whereas all evaluated open-source models remain below 50\%. Our error analysis identifies recurring failure patterns, including scenario misinterpretation, errors in heir identification, errors in share allocation, and missing or incorrect application of key inheritance rules such as \textquotesingle awl and radd. The MAWARITH dataset is publicly available at https://gitlab.com/nlpresearcher/mawarith.

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

Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations

arXiv:2606.12503v1 Announce Type: new Abstract: Self-supervised learning (SSL) has opened new opportunities in bioacoustics by enabling scalable modeling of animal vocalizations without the need for expensive manual annotation. However, current SSL models in this domain prioritize broad generalization across species and are not optimized for uncovering the fine-grained structure of individual communication systems. In this work, we collect and release a novel dataset of over five years of longitudinal recordings, from five known dolphins in a semi-naturalistic marine environment, an unprecedented resource for studying dolphin communication. We adapt the Wav2Vec2.0 Baevski et al. (2020) architecture to this domain and introduce Dolph2Vec, the first large-scale, species-specific SSL model trained exclusively on this data. We benchmark our model on two biologically relevant tasks: signature whistle classification and whistle detection. Dolph2Vec significantly outperforms general-purpose baselines in both tasks. Beyond performance, we show that learned embeddings and codebook structure capture interpretable acoustic units aligned with dolphin whistle categories and possibly sub-whistle structure, enabling fine-grained analysis of communication patterns. Our findings demonstrate how SSL can serve as both a model and a scientific tool to explore hypotheses in animal communication research.

07.
arXiv (CS.LG) 2026-06-16

Task-Error Residual Learning for Real-Robot Five-Ball Juggling

arXiv:2606.16978v1 Announce Type: cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information. Reinforcement learning's standard scalar reward carries far less information than the directional task error that defines the task. Random exploration further discards whatever information each rollout returns. Through residual learning with directional task-error supervision and a task error model that drives sample selection, we achieve stable three-, four-, and five-ball juggling on anthropomorphic Barrett WAM arms. Despite planning and controlling through a simple, idealized stack, the system converges from the second attempt. The first attempt drops, after which task error decreases monotonically without further failures. In comparison, five-ball juggling typically takes humans years of practice. We compare residual learners across two ternary axes, the directional information in the learning feedback and the commitment of the analytic prior, spanning Newton-style Jacobian updates, Composite Bayesian Optimization, and stochastic search methods. Both axes prove necessary: neither directional feedback nor an informative prior suffices alone, and the simplest method that combines them, a fixed-Jacobian Newton update, is the most reliable. The learned residual tolerates substantial prior misalignment and degraded joint tracking, affecting mainly convergence speed. The bottleneck for residual learning on real robots is therefore the information content of the supervision signal and how the learner uses it, not the accuracy of the surrounding stack. Video documentation of all experiments is available at https://kai-ploeger.com/residual-juggling.

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

MoCo-AIS: A Contrastive Learning Framework for Similarity Computation of Vessel Trajectories

arXiv:2606.17978v1 Announce Type: new Abstract: Trajectory similarity is a fundamental task in analyzing mobility patterns, essential for applications such as route pattern extraction, mobility prediction, and anomaly detection. Traditional distance-based measures for computing similarity incur high computational cost, driving the adoption of lightweight learning-based approaches. Supervised methods rely on extensive labels derived from traditional distance measures and often reproduce these metrics, which limits generalization. While self-supervised learning addresses this issue through contrastive learning, it lacks a unified framework, making it difficult to compare deep learning (DL) models for consistent trajectory representation. Accordingly, this paper presents MoCo-AIS, a unified framework for learning vessel trajectory embeddings based on the Momentum Contrast (MoCo) paradigm, which formulates similarity learning through positive and negative trajectory pairs. Within this framework, we evaluate a diverse set of leading DL models on large-scale, real-world vessel-tracking AIS datasets that capture diverse navigation behaviors and operating conditions. Results demonstrate that our framework significantly improves similarity learning over existing baselines, while providing a benchmarking platform for evaluating trajectory representation models.

09.
arXiv (CS.CV) 2026-06-17

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

10.
arXiv (CS.AI) 2026-06-19

Emergent Alignment

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

11.
arXiv (CS.CL) 2026-06-12

Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents

Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated in the next. We study this gap between preference access and preference compliance. In tasks derived from anonymized real-user friction cases, Mem0 memory still leaves 57.5% of applicable preference checks violated. We introduce Test-time Rule Acquisition and Compiled Enforcement (TRACE), a drop-in skill-layer pipeline for coding-agent runtimes that mines user corrections, rewrites them as atomic rules, and compiles them into runtime checks that must pass before an agent completes future tasks. Unlike runtime checks written ahead of time by developers, TRACE skills come from the user's own chat corrections. We evaluate TRACE with simulated user-in-the-loop experiments on ClawArena coding-agent tasks and MemoryArena-derived memory-intensive tasks. On ClawArena, TRACE reduces held-out preference violation from 100.0% to 37.6% on in-distribution tasks and from 100.0% to 2.0% on out-of-distribution tasks. On MemoryArena-derived tasks, TRACE reduces in-distribution violation from 100.0% to 60.5% while matching or exceeding the strongest memory baseline on task pass. These results suggest that compiling corrections into runtime enforcement can address a repeated-friction failure mode that memory alone does not reliably solve, reducing the need for users to restate the same correction across future sessions. Experiment code is available at https://github.com/YujunZhou/TRACE_exp, and the deployable skill is available at https://github.com/YujunZhou/tellonce.

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

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

arXiv:2606.13657v1 Announce Type: new Abstract: On-policy distillation (\textsc{OPD}) has recently become a prominent post-training recipe as it combines two desirable ingredients: on-policy student trajectories and dense teacher supervision, yet how this hybrid changes a model's parameters remains unclear. Across several language and vision-language model pairs and use cases, our analysis yields two main findings. On sparsity, \textsc{OPD}-style updates are small and coordinate-sparse. They are distributed across layers and are usually FFN-heavy. This sparse structure is operationally useful: training only the discovered subnetwork recovers nearly the same performance as full \textsc{OPD}. However, the sparsity-inducing SGD optimizer underperforms AdamW in our optimizer ablation, likely because dense teacher supervision preserves heterogeneous coordinate-wise gradient scales where AdamW's adaptive scaling remains useful. On geometry, the updates are numerically full-rank but spectrally concentrated; they lie mostly away from the principal singular subspaces of the source weights and fall disproportionately on coordinates where the source weights are close to zero. These findings suggest that dense teacher supervision does not turn \textsc{OPD} into ordinary dense parameter rewriting; instead, \textsc{OPD} retains important geometric signatures of on-policy post-training.

13.
arXiv (CS.AI) 2026-06-16

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

arXiv:2606.16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.

15.
medRxiv (Medicine) 2026-06-15

High Demand, Low Possession: Dilemmas and Strategies for Research Capability Cultivation in Clinical Medicine Postgraduates

Most previous studies have examined medical postgraduate research training from a single dimension, lacking a full-chain analysis that integrates capability demand, actual possession, obstacles, and output. Consequently, the measurement of capability gaps and the analysis of underlying training model deficiencies remain insufficient. To address this gap, we administered a self-designed multidimensional questionnaire to 86 clinical medicine postgraduates at a medical school, covering research cognition, interest, capability demand and possession, participation pathways, difficulties, and outputs. The aim was to systematically characterize the current situation, identify problems, and propose optimization strategies. Over 90% of participants expressed interest in research, yet only 1.16% self-rated as very knowledgeable. The largest demand-possess gap was for writing and publication (86.05% vs. 16.28%), followed by independent research capability (75.58% vs. 11.63%). A total of 59.30% cited lack of foundational knowledge, making experiments very difficult, as the greatest challenge, and 66.28% had no research achievements. The primary source of research topics was supervisor assignment (54.65%), with only 4.65% choosing topics independently. No statistically significant differences were found across grades or training types (P > 0.05). These findings reveal a structural high demand, low possession gap in medical postgraduate research training, with early research experience deficit and a passive research model as key constraining factors. Accordingly, an integrated bachelor-postgraduate progressive research competency training system is proposed.

16.
Nature (Science) 2026-06-17

A blastoporal organizer in a ctenophore

In an iconic experiment in 1924, Hilde Mangold and Hans Spemann established that the dorsal blastopore lip of amphibian embryos functions as an organizer and induces a secondary body axis when transplanted into a host embryo1. This discovery demonstrated that specific embryonic regions can regulate embryonic patterning and lead to the establishment of an entire body axis. Subsequent studies have revealed that cnidarians, the sister group to Bilateria, also possess a blastoporal embryonic organizer2,3. However, the evolutionary origin of the organizer remains unclear. Here we report that the blastopore lip of the ctenophore Mnemiopsis leidyi, a member of the evolutionary sister group to all other metazoans4,5, exhibits organizer activity. We show that transplanted fragments of blastopore lip tissue from M. leidyi gastrula induce secondary pharynx and mouth formation. Moreover, transphyletic transplantation experiments show that the blastopore lip of M. leidyi leads to the generation of a secondary body axis in embryos of the cnidarian Nematostella vectensis. Organizer function in M. leidyi requires both β-catenin and TGFβ signalling, and the TGFβ-family ligands probably provide this inductive capacity. These findings reveal the deep homology of the blastoporal organizer in ctenophores, cnidarians and vertebrates, implying the ancestral organizer role of the blastopore lip. We propose that the emergence of the organizer was an essential innovation that facilitated the change from the temporal cell differentiation of unicellular relatives to the spatial cell differentiation of the first multicellular embryo. Experiments using the comb jelly Mnemiopsis leidyi and the sea anemone Nematostella vectensis reveal that the emergence of a core signalling pathway may have been a key innovation enabling the transition to multicellularity in animals.

17.
bioRxiv (Bioinfo) 2026-06-11

Integrating Spatially Adjusted Protein Summaries for Survival Prediction in Spatial Proteomics

Recent advances in spatial proteomics, particularly imaging mass cytometry, enable the measurement of protein expression at the single-cell level while preserving a spatial context. Conventional survival analyses, however, typically rely on patient-level averages of protein intensities and therefore overlook spatial heterogeneity and tissue architecture. To address this limitation, we introduce a framework that incorporates spatial information into survival modeling by generating spatially adjusted protein summaries (SAPS). In this approach, cell-level protein intensities within each patient are modeled using spatial spline regression to capture spatial trends. From these models, we extract two complementary features: a spatially adjusted mean expression and a residual variance that reflects cell-to-cell variability unexplained by spatial effects. These summaries are then incorporated into Cox proportional hazards models in combination with clinical covariates. In simulation studies, our proposed framework achieved improved predictive performance compared to other alternative methods. The application of the method to breast cancer imaging mass cytometry data indicate that spatially adjusted summaries may enhance survival prediction and reveal biologically interpretable spatial protein patterns, suggesting high translational potential. This methodology offers an efficient means of translating complex spatial proteomics data into patient-level features, providing both improved survival prediction and new insights into the role of spatial heterogeneity in cancer outcomes.

18.
arXiv (CS.CV) 2026-06-16

Open-World Video Segmentation

While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) existing methods are not designed to support object discovery and identity maintenance in long videos of dynamic ego-motion, and (2) existing evaluation protocols rely on a rigid 1:1 matching that unfairly penalizes semantically valid predictions with mismatched granularity. To address both gaps, we introduce Savvy, a practical and strong system for zero-shot open-world long-horizon video segmentation. Savvy combines hierarchical mask discovery, deferred admission, and track consolidation to support persistent object discovery, safe track promotion, and stable long-range identity maintenance. We further propose OGA, a granularity-aware evaluation suite for open-world video segmentation. Built on a Granularity-Agnostic (GA) matching protocol, OGA relaxes conventional 1:1 matching to an n:1 mapping, but still enforces temporal rigor by detecting support discontinuities through sever points and scoring each reference object through its dominant coherent fragment. This prevents fragmented or flickering support from being over-rewarded while enabling GA-adapted metrics and structural diagnostics: identity persistence (IP), and identity concentration (IC). On VIPSeg, we show that standard 1:1 evaluation substantially underestimates open-world methods, whereas GA evaluation recovers much of their suppressed performance. On the more realistic long-horizon benchmarks: ScanNet and HM3D, Savvy consistently outperforms strong baselines across both classical and proposed metrics, including STQ, VPQ$_\infty$, IP and IC. Together, these results establish a practical benchmark and a strong baseline for open-world long-horizon video segmentation.

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

GPO: Learning from Critical Steps to Improve LLM Reasoning

arXiv:2509.16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the reasoning or thinking capabilities of LLMs to solve complex problems. Despite the promising results of reasoning LLMs, enhancing the multi-step reasoning capabilities of LLMs still remains a significant challenge. While existing optimization methods have advanced the LLM reasoning capabilities, they often treat reasoning trajectories as a whole, without considering the underlying critical steps within the trajectory. In this paper, we introduce Guided Pivotal Optimization (GPO), a novel fine-tuning strategy that dives into the reasoning process to enable more effective improvements. GPO first identifies the `critical step' within a reasoning trajectory - a point that the model must carefully proceed to succeed at the problem. We locate the critical step by estimating the advantage function. GPO then resets the policy to the critical step, samples the new rollout and prioritizes the learning process on those rollouts. This focus allows the model to learn more effectively from pivotal moments within the reasoning process to improve the reasoning performance. We demonstrate that GPO is a general strategy that can be integrated with various optimization methods to improve reasoning performance. Besides theoretical analysis, our experiments across challenging reasoning benchmarks show that GPO can consistently and significantly enhance the performance of existing optimization methods, showcasing its effectiveness and generalizability in improving LLM reasoning by concentrating on pivotal moments within the generation process.

20.
Nature Medicine 2026-06-11

Microglia at a key inflection point in Alzheimer’s disease

作者: 未知作者

We analyzed brains from octogenarians and cognitively resilient centenarians to understand why some individuals with substantial Alzheimer’s disease pathology develop dementia whereas others remain cognitively intact. Spatial transcriptomics revealed gene expression changes in discrete tissue domains surrounding amyloid plaques and tau pathology that distinguish early, clinically silent, disease from later stages associated with cognitive decline.

21.
PLOS Medicine 2026-05-29

Characterization of the VHH-Fc construct rimteravimab in healthy adults and patients hospitalized for mild-to-moderate COVID-19: Two Phase 1 randomized clinical trials

作者:

by Ellen Jansen, Viki Bockstal, Florence Herschke, Per Olsson Gisleskog, Manuela Rinaldi, Angélique Boerboom, Salah Hadi, Natalia Gaibu, Michel Moutschen, Dominique Tersago Background Variable Heavy domain of Heavy chains (VHH) are innovative tools to target unique epitopes, yet few have been developed as heavy chain-only antibodies for clinical use. Rimteravimab (referred to here as XVR011) is a humanized antibody developed for the treatment of mild-to-moderate coronavirus disease 2019 (COVID-19), consisting of two identical VHHs targeting the receptor binding domain (RBD) of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike, with a human immunoglobulin (Ig) G1 fragment constant of antibody (Fc), silenced for Fc effector functions. We conducted two Phase 1 studies in healthy volunteers or hospitalized COVID-19 patients to evaluate its safety, tolerability, pharmacokinetics and immunogenicity. Methods and findings A randomized, double-blinded, single-center, placebo-controlled, single ascending dose study was performed in healthy volunteers (Phase 1a, EXEVIR0102, EudraCT 2021-003707-17), in parallel to an open-label, multi-center, single ascending dose study in patients hospitalized for mild to moderate COVID-19 (Phase 1b, EXEVIR0101, EudraCT 2020-005299-36, NCT04884295). Participants received a single intravenous infusion of 250, 500 or 1,000 mg of XVR011. The primary objective for both trials was the safety and tolerability of XVR011. Pharmacokinetics were evaluated as a secondary objective in Phase 1a and as an exploratory objective in Phase 1b. Efficacy (evaluated as respiratory parameters and COVID-19 clinical status) and antiviral activity in patients were evaluated as a secondary objective in Phase 1b. Immunogenicity was evaluated as an exploratory objective. Part 2 of the EXEVIR0101 study (initially a phase 1b/2 study) was not conducted due to the loss of XVR011 potency against SARS-CoV-2 Omicron BA.2. Demographics, safety, efficacy, and immunogenicity were analyzed using descriptive statistics, while pharmacokinetics were analyzed with noncompartmental pharmacokinetics (PK) modeling.In the Phase 1a study, there were no infusion-related reactions, serious treatment-emergent adverse events (TEAEs) or TEAEs grade ≥3. 22/30 volunteers (73.3%) reported 53 TEAEs (49 Grade 1, 4 Grade 2) with none being related to XVR011. The most common TEAE was headache (n = 8, 26.7%) in various treatment groups. In the Phase 1b study, 27 hospitalized patients were enrolled, and followed up to 30 days. Seven patients (25.9%) reported a total of 15 TEAEs, the majority (80%) being mild to moderate (Grade 1–2). There were no treatment-related serious TEAEs. All TEAEs resolved by the end of the study. Peak exposure (maximal concentration, Cmax) and systemic exposure (area under the curve, AUC0-t, and AUC0-inf) for XVR011 increased dose-proportionally. Geomean half-life ranged from 15.4 to 17.0 days in Phase 1a, while individual half-life ranged from 11.4 to 15.6 days in Phase 1b. SARS-CoV-2 viral load, as detected in nasopharyngeal samples by reverse transcription and quantitative polymerase chain reaction (RT-qPCR), decreased similarly in all cohorts compared to baseline. No treatment-induced anti-drug antibodies (ADA) were detected in Phase 1a. In Phase 1b, higher XVR011 concentrations increased the likelihood of ADA formation, without impacting pharmacokinetics and pharmacodynamics. No obvious dose-response in COVID-19 clinical status or respiratory parameters was observed.Technological limitations included study size, absence of placebo for the Phase 1b, absence of repeated dosing, evolving SARS-CoV-2 variants and standard-of-care. Conclusions XVR011 displayed a favourable safety, tolerability, pharmacokinetics, and immunogenicity profile, both in healthy volunteers and in patients hospitalized for mild to moderate COVID-19. These data pave the way for the design and clinical development of VHH-Fc constructs.

22.
arXiv (CS.CL) 2026-06-12

No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions

As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-relevant failure mode: no hidden text, no prompt injection, and no changes to methods, experiments, figures, equations, proofs, or numerical results. The attacker modifies only presentation-level content, such as the abstract, contribution framing, related work, discussion, and narrative structure. We introduce adversarial repackaging: a closed-loop attack that uses AI-reviewer feedback to search for presentation-level revisions while keeping the scientific evidence fixed. Across three mainstream AI reviewers, adversarial repackaging achieves a 75.1% attack success rate and a mean score gain of +1.21/10. The effect is not explained by ordinary prose polishing. We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion, substantially outperform surface edits such as local polishing, table formatting, and algorithm boxes. Our analysis reveals two deeper structural failure modes. First, AI reviewers are easier to impress than to convince: highlighting strengths reliably increases perceived merit, while attempts to dissolve weaknesses frequently backfire. Second, AI reviewers can confuse the appearance of addressing a limitation with actually resolving it, allowing unchanged evidence to be reinterpreted as stronger scientific contribution. These results show that the deployment risk is not only malicious hidden instructions, but the emergence of paper presentation itself as an optimization surface. We release a contamination-free rolling benchmark and attack framework for testing whether AI reviewers remain anchored to scientific content under presentation-only edits.

23.
arXiv (CS.AI) 2026-06-17

Trust-Aware Multi-Agent Traceability: Confidence-Calibrated Knowledge Graphs for Consistent Software Artifact Management

arXiv:2606.17203v1 Announce Type: cross Abstract: Multi-agent AI systems are increasingly used to automate software engineering tasks including requirements analysis, architecture design, test generation, and traceability linking. When these agents operate as a sequential pipeline over shared software artifacts, errors and low-confidence decisions made by upstream agents propagate to downstream stages, producing orphaned requirements, contradictory links, and compliance gaps that pose significant risks in safety-critical domains. We propose a trust-aware coordination framework where a shared knowledge graph serves as both centralized semantic memory and a coordination surface through which agents assess and build upon each other's contributions using calibrated confidence scores. Our approach introduces a two-stage traceability link prediction pipeline combining embedding-based retrieval with LLM-based multi-criteria analysis, a traceability seeding mechanism that enables comparison between derivation-time and validation-time confidence, and a consistency protocol governing pipeline interactions through confidence threshold gating, confidence divergence detection, and conflict resolution. We evaluate on an automotive software engineering case study measuring link prediction calibration, protocol effectiveness, threshold sensitivity, and the impact of traceability seeding. Ablation studies confirm that confidence calibration is essential for effective pipeline coordination.

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

Cognitive Debt: AI as Intellectual Leverage and the Dynamics of Systemic Fragility

作者:

arXiv:2606.15078v1 Announce Type: new Abstract: We develop a formal theory of cognitive debt: the stock of unverified reasoning obligations that accumulates when individuals use AI as a substitute rather than a complement for first-principles cognition. The model features two state variables per agent, cognitive capital and cognitive debt, and a multiplicative production technology in which cognitive capital functions as collateral that determines the return to AI adoption. We establish six propositions. Rational agents incur positive cognitive debt because the costs are deferred, partially external, and masked by short-run productivity gains. Tranquil periods lower subjective risk assessments, raise AI substitution intensity, and compound leverage, generating a cognitive Minsky moment in which subjective risk falls while true systemic fragility rises. Expected crisis losses are convex in aggregate leverage. Post-crisis, output-target pressure can produce a false-correction loop in which agents patch AI failures with more AI. The decentralised equilibrium over-adopts substitutive AI relative to the social optimum because of systemic risk, cognitive public goods, and arms-race externalities. In a two-type heterogeneous-agent economy, high-cognitive-capital agents adopt AI more intensively and may eventually erode their unaided cognitive capital below that of initially lower-skilled agents.

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

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

arXiv:2606.11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training. This raises a basic robustness question, crucial to reproducibility and reliability: how sensitive are MD dynamics to their inputs? We focus on initialization, often itself a pretrained or previously aligned model. Quadratic-regularized MD, including GD and Mahalanobis geometries, is well-known to be stable for convex smooth objectives. We show a sharp contrast: once the regularizer is non-quadratic, MD can be exponentially more sensitive to initialization than GD, even with a well-conditioned regularizer in Euclidean norm. We give a three-dimensional construction with a convex, smooth objective and a strongly convex, smooth, well-conditioned regularizer where an initial $\varepsilon$ perturbation is quickly amplified to $\min\{polylog^{-1}(1/\varepsilon), \varepsilon e^{\Omega(\eta T)}\}$ after $T$ iterations of MD with step size $\eta$. For canonical KL-regularized MD on the simplex, we show that even linear objectives can amplify an initial $\varepsilon$ perturbation exponentially fast in high-dimensional or near-boundary regimes. Finally, we show that adding a Bregman regularization term toward an anchor point can stabilize the dynamics while largely preserving the optimization guarantees, and that the choice of anchor is crucial: anchoring at the initialization only partially mitigates the instability, whereas anchoring at a fixed point yields a more stable mechanism.