探索全球前沿学术脉络

01.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2606.08683

Exact Fourier dimensions of dyadic Mandelbrot cascades under minimal integrability

作者:

Yin Cai↗Guozheng Cheng↗Xiang Fang↗Menghan Li↗Hongdou Qu↗Chengbo Xiao↗

arXiv:2606.08683v2 Announce Type: replace Abstract: We determine the Fourier dimension of dyadic Mandelbrot cascades under the minimal Kahane-Peyriere integrability condition. The interval theorem is proved in a vector-valued dyadic cascade model in which sibling weights may have arbitrary dependence. For every balanced energy-admissible vector law, almost surely on non-extinction, dim_F(mu)=dim_E(mu)=dim_2(mu)=D_E(X). In the canonical scalar case, under W>=0, E W=1, E[W log_2^+ W]

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17800

MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model

作者:

Lichen Bai↗Tianhao Zhang↗Shitong Shao↗Dingwei Tan↗Qiyu Zhong↗Zhengpeng Xie↗Haopeng Li↗Qinghao Huang↗Dandan Shen↗Tengjiao Ji↗Wei Wang↗Peicheng Wu↗…

As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked by previous studies. In this work, we define the position of social world models and build a prototype model as the first step towards this goal. While previous world models successfully simulate physical environments or gaming world exploration, they remain fundamentally detached from human-centric social dynamics. To bridge this gap as the first step to social world models, we present MaineCoon, the first real-time audio-visual autoregressive model that has 22B parameters and is capable of real-time streaming generation and sub-second interaction, with a record-breaking frame rate of up to 47.5 FPS, on a single GPU. To the best of our knowledge, MaineCoon is also the first real-time audio-visual generation model specifically optimized for social-interactive applications. To enable efficient and stable training, we introduce several novel techniques into MaineCoon, including self-resampling, cross-modal representation alignment, domain-aware preference optimization, and reinforced online-policy distillation (ROPD). We also design the first agentic streaming inference framework that supports thousand-second-scale or even longer generation while mitigating drift with agentic cache management and prompt planing. These innovations significantly accelerate training while optimizing real-time inference performance. We believe this work not only sets a new state-of-the-art (SOTA) performance benchmark for high-quality, low-latency, and long-horizon audio-visual autoregressive models, but also points out the paradigm shift desired for next-generation AI-native social platforms.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18797

Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports

作者:

Qingyu Lu↗Ruochen Li↗Liang Ding↗Yufei Xia↗Youxiang Zhu↗Dacheng Tao↗

Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect patient care. Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar. Although Large Language Models (LLMs) possess rich medical knowledge, they likewise struggle to draw a reliable boundary between clinically significant errors and harmless variation. We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance from detecting true clinical errors ("Discrimination") and tolerating insignificant variations ("Robustness"). Across 8 LLM evaluators under one-pass and two-pass settings, we identify a widespread discrimination bias: models effectively detect errors but also over-penalize harmless rephrasings. To mitigate this, we synthesize 4k report pairs and train lightweight interpretable metrics on Qwen3-8B and MedGemma-4B. Our trained metric sharpens the clinical significance boundary, surpassing 32B-scale medical LLMs and remaining competitive with proprietary models. Crucially, the more costly two-pass setting fails to consistently improve overall performance and mainly trades discrimination for robustness. These findings suggest one-pass trained metrics as the practical choice for cost-sensitive deployment, with two-pass inference reserved for settings where D-R balance is critical. We will release the dataset and metric.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18661

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

作者:

Chengfu Liu↗Dongyang Hou↗Junwu Xiang↗Cheng Yang↗Xuezhi Cui↗Zeyuan Wang↗Liangtian Liu↗Zelang Miao↗

Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios. To address these challenges, we propose an instruction-driven agentic framework comprising three components. First, LandslideBench, a multimodal fine-grained dataset with seven subtype labels, high-resolution imagery, pixel-level masks, and high-quality textual descriptions, is constructed via multi-VLM cross-validation and interactive annotation. Then, LandslideVLM, a landslide-oriented VLM, is fine-tuned via LoRA on LandslideBench to enhance geological semantic understanding. Finally, LandslideAgent, a domain rule-enhanced agent taking LandslideVLM as its cognitive backbone, employs a dual-rule controller incorporating structured report metadata constraints and cross-validation identification constraints to regulate automated tool invocation. Experiments demonstrate that LandslideBench provides effective baselines across five mainstream models on fine-grained classification and semantic segmentation. LandslideVLM achieves accuracy improvements of 10.96%, 32.87%, and 15.91% on landslide discrimination, fine-grained classification, and semantic description quality, respectively. LandslideAgent further enables autonomous multi-source spatial data inference, realizing full-process intelligence for landslide identification and analysis.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2503.07459

MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks

作者:

Yanjun Shao↗Xiangru Tang↗Jiwoong Sohn↗Jiapeng Chen↗Yuxuan Liao↗Jiayi Zhang↗Jinyu Xiang↗Fang Wu↗Yilun Zhao↗Chenglin Wu↗Wenqi Shi↗Arman Cohan↗…

Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively amongst multiple LLMs). To determine whether these routes are exclusive or complementary, we introduce MedicalAgentsBench, a filtered benchmark of 862 complex clinical questions drawn from the union of eight medical datasets via difficulty-aware curation and contamination screening. Evaluating three internalized reasoning models (DeepSeek-R1, o1-mini, and o3-mini), seven base models, and nine externalized agent-based methods, we find that internalized and externalized approaches each independently improve performance, and that their benefits compound: the highest accuracy is achieved by layering agent workflows onto an internalized reasoning model (i.e., o3-mini + MDAgents with 35.1%). Pareto analysis shows this combination dominates the cost-performance frontier; moreover, lightweight optimization on inexpensive models offers an entry point for resource-constrained settings. Our benchmark is at https://github.com/gersteinlab/MedicalAgentsBench.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2604.24696

NeuroClaw Technical Report

作者:

Cheng Wang↗Zhibin He↗Zhihao Peng↗Shengyuan Liu↗Yufan Hu↗Carl Yang↗Lifang He↗Lichao Sun↗Xiang Li↗Yixuan Yuan↗

Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (sMRI, fMRI, dMRI, EEG), long multi-stage pipelines, and persistent reproducibility risks. To address this gap, we present NeuroClaw, a domain-specialized multi-agent research assistant for executable and reproducible neuroimaging research. NeuroClaw operates directly on raw neuroimaging data across formats and modalities, grounding decisions in dataset semantics and BIDS metadata so users need not prepare curated inputs or bespoke model code. The platform combines harness engineering with end-to-end environment management, including pinned Python environments, Docker support, automated installers for common neuroimaging tools, and GPU configuration. In practice, this layer emphasizes checkpointing, post-execution verification, structured audit traces, and controlled runtime setup, making toolchains more transparent while improving reproducibility and auditability. A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills to decompose complex workflows into safe, reusable units. Alongside the NeuroClaw framework, we introduce NeuroBench, a system-level benchmark for executability, artifact validity, and reproducibility readiness. Across multiple multimodal LLMs, NeuroClaw-enabled runs yield consistent and substantial score improvements compared with direct agent invocation. Project homepage: https://cuhk-aim-group.github.io/NeuroClaw/index.html

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.01316

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

作者:

Zhe Zhao↗Haibin Wen↗Yingcheng Wu↗Jiaming Ma↗Yifan Wen↗Jinglin Jian↗Jiacheng Ge↗Xiangru Tang↗Bo An↗Ming Yin↗Sanfeng Wu↗Mengdi Wang↗…

arXiv:2606.01316v2 Announce Type: replace Abstract: Scientific discovery demands intelligence, perseverance, and serendipity across vast search spaces. Today, top scientific capabilities remain siloed–one AI system for biological analysis, another for clinical reasoning, mathematical derivation, or materials simulation–and no pre-designed team can anticipate every skill a question will need. Science Earth is a planet-scale scientific runtime in which any capability–a simulation cluster, a wet-lab robot, a proof engine, a single-cell pipeline–can connect to any other, with collaboration structure emerging from the question itself. Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards without prior knowledge of who will meet whom. This shifts the organizing challenge from workflow design to open-ended connectivity. Two runs validate this under structurally distinct conditions. In a trans-Pacific higher-order Kuramoto synchronization study, agents identified and corrected a closure-ratio assumption in Ott-Antonsen analytic theory that fails outside the Lorentzian limit, within thirty minutes. In an eight-agent single-cell run on the 4.88M-cell Kang 2024 pan-cancer atlas, heterogeneous capabilities coupled over a 64.9-hour window with one structural external instruction, producing three new result layers and anchoring findings against an independent wet-lab study on an adjacent CCR8- TIGIT+ Treg subset. These cases are a first empirical reading, not a benchmark sweep. They show that when AI capabilities are truly connectable and coordination emerges from the problem, scientific reasoning becomes a distributed, self-correcting process–a step towards scaling AI-native discovery to the planet.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19662

Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion

作者:

Bingshuo Qian↗Xiang Cheng↗

Multi-representation diffusion models can improve visual synthesis by denoising complementary views of an image, but their performance depends critically on the asynchronous schedule that determines when each representation is denoised. We propose to learn this schedule. Our method formulates asynchronous flow matching over multiple representation spaces and uses a schedule-corrected objective that keeps each representation's local noising-time weights fixed as the schedule changes. We instantiate the schedule with a flexible parametric class that is convex and monotone by construction, and learn it using a fast joint probe with less than 1% additional training compute. On ImageNet 256x256, the learned schedule substantially improves both convergence speed and final quality under a matched 675M-parameter XL backbone. With AutoGuidance, our 200-epoch model reaches FID 1.05, matching the 800-epoch SFD-XL baseline with 4x less training. Training to 600 epochs further improves to FID 1.02, outperforming the 1B-parameter SFD-XXL result of FID 1.04 while using a smaller model. In the unguided setting, our 200-epoch model reaches FID 2.37, already below the best 800-epoch SFD-XL result (2.54) at 4x less training, and improves to FID 2.14 at 600 epochs. Code is available at https://github.com/bsq532087/LWD

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18650

BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

作者:

Jiaxing Wang↗Deping Xiang↗Jin Xu↗Zirui Liu↗Zicheng Zhang↗Guoqiang Gong↗Jun Fang↗Chao Liu↗Pengzhang Liu↗Tongxuan Liu↗Ke Zhang↗Qixia Jiang↗…

arXiv:2606.18650v1 Announce Type: new Abstract: As Large Language Model (LLM) datasets scale to trillions of tokens, data selection has emerged as a critical frontier to filter out uninformative noise and construct adaptive learning trajectories. Beyond static heuristic filtering, advanced data selection methods for LLM training largely follow two paradigms, each with fundamental limitations. Influence-based methods provide principled bi-level objectives but require intractable inverse-Hessian computations, while excess-loss methods are computationally efficient but rely on a static reference model that becomes misaligned with the evolving proxy model during training. We propose BLADE (Bi-Level Adaptive Data sElection), a Hessian-free framework for data selection. BLADE reformulates the bi-level optimization problem underlying influence-based methods as a penalized single-level objective via Lagrange multipliers, avoiding inverse-Hessian computation while revealing a principled connection to excess-loss based data selection. The resulting objective recovers an excess-loss form but replaces the static reference model with a dynamic one that stays synchronized with training. Theoretically, we prove that this penalized formulation guarantees first-order convergence. For efficient online batch selection, we instantiate BLADE as a memoryless randomized block-coordinate Frank-Wolfe algorithm. Extensive experiments show that BLADE consistently outperforms state-of-the-art data selection baselines, providing a practical recipe for LLM training.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2601.18252

Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing

作者:

Chao Wang↗Xuanying Li↗Cheng Dai↗Jinglei Feng↗Yuxiang Luo↗Hao Qin↗Yuqi Ouyang↗

Wireframe parsing aims to recover line segments and their junctions to form a structured geometric representation useful for downstream tasks such as Simultaneous Localization and Mapping (SLAM). Existing methods predict lines and junctions separately and reconcile them post-hoc, causing mismatches and reduced robustness. We present Co-PLNet, a point-line collaborative framework that exchanges spatial cues between the two tasks, where early detections are converted into spatial prompts via a Point-Line Prompt Encoder (PLP-Encoder), which encodes geometric attributes into compact and spatially aligned maps. A Cross-Guidance Line Decoder (CGL-Decoder) then refines predictions with sparse attention conditioned on complementary prompts, enforcing point-line consistency and efficiency. Experiments on Wireframe and YorkUrban show consistent improvements in accuracy and robustness, together with favorable real-time efficiency, demonstrating our effectiveness for structured geometry perception. Our code is available at https://github.com/GalacticHogrider/Co-PLNet.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18702

UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation

作者:

Lin Zhang↗Sicheng Mo↗Zefan Cai↗Jinhong Lin↗Zihao Lin↗Jiuxiang Gu↗Krishna Kumar Singh↗Yuheng Li↗Yin Li↗

Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.g., conditioning on future context to extend backward, or on both past and future context for inbetween generation. We bridge this gap by training an autoregressive model that supports generation in arbitrary temporal directions. A key technical challenge arises from the Causal 3D VAE widely used in video diffusion models, which encodes latents strictly conditioned on past context. While suited for forward generation, this causal structure causes inter-block discontinuities when generation proceeds backward. To address this, we introduce blockwise anchor latents, a set of auxiliary latents that restore the missing past context at block boundaries during backward generation. Built on this design, we propose UniTemp, a bidirectional distillation framework that trains a single autoregressive student model for any-direction video generation. At inference time, UniTemp conditions on arbitrary past and/or future frames, improving controllability for both bidirectional and inbetween generation. Experiments show that UniTemp maintains competitive performance on short and long video generation compared to forward-only methods, while enabling diverse workflows such as bidirectional video extension, inbetween generation, looping video generation, scene transition, and visual story generation. Project website: https://lzhangbj.github.io/projects/unitemp/

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15186

FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing

作者:

Yuxuan Jiang↗Mingyang Han↗Yusheng Dai↗Andong Wang↗Tianhong Zhou↗Jiaxin Ye↗Dongxiao Wang↗Haoxiang Shi↗Boyu Li↗Jun Song↗Cheng Yu↗Bo Zheng↗…

arXiv:2606.15186v1 Announce Type: cross Abstract: Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to balance temporal consistency with background preservation. In this paper, we propose FreeSonic, a training-free framework leveraging the state-of-the-art Rectified Flow-based TangoFlux model. FreeSonic utilizes an optimized inversion-reverse process and joint text-audio attention maps for precise target segment extraction. For content editing, a novel scheduled attention decoupling confines modifications to target regions while preserving original acoustic context. Furthermore, task-oriented noise injection enhances versatility for tasks such as audio removal and non-rigid replacement. Extensive experimental results demonstrate that FreeSonic achieves a superior balance by providing a high-fidelity and efficient solution for precise and consistent audio editing. Project and demos: https://free-sonic.github.io/

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16801

The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models

作者:

Chen Chen↗Xiang Gao↗Xianshun Wang↗Chengran Li↗Shengyu Xia↗Xueluan Gong↗Linru Zhang↗Qian Wang↗Kwok-Yan Lam↗

Split learning provides a practical paradigm for resource-constrained users to train Large Language Models (LLMs) by offloading computation-intensive layers to a server while keeping raw data local. However, existing privacy-preserving split learning methods still face a difficult trade-off among utility, privacy, efficiency, and stability. Specifically, these methods often suffer from substantial utility degradation, remain vulnerable to advanced data reconstruction attacks, incur prohibitive computational and communication overhead, or exhibit unstable performance across different tasks. In this paper, we propose MIXGUARD, a novel mixup-based privacy-preserving split learning framework for LLMs. MIXGUARD introduces token-level obfuscation, representation-level obfuscation, and adaptive gradient perturbation mechanisms, which operate jointly to preserve useful learning signals while preventing privacy leakage to the server. Technically, MIXGUARD first constructs a lightweight calibration model on a public dataset to refine the approximated target representation, and then applies this model during privacy-preserving fine-tuning on private data. We conduct extensive experiments on four classification tasks and four text generation tasks across multiple LLM families, model sizes, architectures, and fine-tuning strategies. The results show that MIXGUARD preserves model utility comparable to non-split training baselines, consistently achieves stronger privacy protection than existing split learning defense methods against state-of-the-art data reconstruction attacks, and remains robust under adaptive attack settings.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14375

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

作者:

Ge Wang↗Xinyu Tan↗Xiang Li↗Man Luo↗Chengsi Yao↗Shenhao Yan↗Jiahao Yang↗Fan Feng↗Honghao Cai↗Xiangyuan Wang↗Zhixin Mai↗Yiming Zhao↗…

arXiv:2606.14375v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of robot control: contact-rich or uncertain states may need more computation and fresher feedback, while easier states can often be handled with fewer inference steps and longer open-loop execution. We propose Elastic Queries Reinforcement Learning (EQRL), a framework that makes each VLA policy query elastic. A lightweight latent-schedule adaptor jointly selects the latent input, denoising budget, and action chunk length, without fine-tuning the underlying VLA model. To make scheduling difficulty-aware, EQRL trains a critic over the joint latent-schedule action and derives a state difficulty signal from critic ensemble disagreement. This signal guides compute toward difficult states, while a learned residual allows task-driven correction. We formulate variable chunk execution as query-level macro-action RL with chunk-dependent discounting and an amortized number-of-function-evaluations (NFE) budget. Across simulation and real-robot manipulation, EQRL reduces amortized inference cost while preserving or improving task success.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20543

SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation

作者:

Shilong Xiang↗Zirui Zhang↗Lijun Yu↗Chengzhi Mao↗

Autoregressive models excel in visual generation by treating images as 1D sequences of discrete tokens, mirroring language modeling. However, this flattening discards the intrinsic 2D spatial locality of visual signals, creating severe computational bottlenecks during inference. We introduce Spatially Speculative Decoding (SSD), a framework that aligns the predictive objective with the natural geometry of images. Rather than predicting only the immediate next token in a 1D sequence, our model simultaneously predicts the adjacent horizontal token and the token directly below it. By capitalizing on this 2D spatial correlation, spatially speculative decoding overcomes the memory wall in visual inference. Our approach accelerates autoregressive image generation by up to 13.3x while maintaining high fidelity on DPG-Bench and GenEval. Our results suggest that respecting the underlying geometry of vision unlocks massive computational efficiencies, paving the way for real-time, high-resolution autoregressive generative models.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2603.22934

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

作者:

Xiangyu Yin↗Yi Qi↗Chih-Hong Cheng↗

arXiv:2603.22934v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface. In this setting, an adversary injects or edits passages so that they enter the Top-$K$ results for target queries and influence downstream generation. Existing defences often rely on content filtering, auxiliary models, or generator-side reasoning, which complicates deployment. We propose ProGRank, a post hoc, training-free retriever-side defence for dense-retriever RAG. ProGRank stress-tests each query–passage pair under mild randomized perturbations, extracts probe gradients from a small fixed parameter subset, and derives two instability signals: representational consistency and dispersion risk. It then combines these signals with a score gate for reranking. ProGRank preserves the original passage content, requires no retraining, and supports a surrogate-based variant when the deployed retriever is unavailable. Experiments across datasets, retrievers, attacks, and retrieval-stage and end-to-end settings show that ProGRank improves robustness and maintains a favorable robustness–utility trade-off, including under adaptive evasive attacks.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14586

S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning

作者:

Shilong Xiang↗Zirui Zhang↗Chengzhi Mao↗

Current representation learning paradigms force a fundamental compromise: self-supervised methods scale to massive datasets but yield opaque features, whereas interpretable models remain bottlenecked by the need for dense human annotation. We introduce Self-Supervised Concept discOvery via Preference lEarning (\model), a label-free framework that resolves this dilemma. Instead of treating Vision-Large-Language Models (VLLMs) as static feature extractors, \model leverages them as active participants in a self-supervised preference optimization loop. By autonomously hypothesizing, validating, and reinforcing candidate visual attributes directly from raw imagery, our framework discovers novel, structured concepts without a single label. Extensive experiments across natural, medical, and physics domains demonstrate that \model successfully extracts domain-specific concepts where standard VLLMs often fail to generate. By amortizing concept discovery directly into the VLLM backbone through our self-supervised preference objective – rather than relying on static generation and disjoint filtering – we achieve up to a 24-point absolute improvement in downstream top-1 classification accuracy on unseen data. Our work suggest that interpretability can emerge through a model's autonomous interaction with incidental visual structures, without any human supervision.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.12670

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

作者:

Xiangyi Li↗Yimin Liu↗Wenbo Chen↗Bingran You↗Zonglin Di↗Yifeng He↗Shenghan Zheng↗Kyoung Whan Choe↗Jiankai Sun↗Shuyi Wang↗Chujun Tao↗Binxu Li↗…

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15258

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

作者:

Jierui Zhang↗Siyuan Tan↗Xinhang Li↗Longzhuangzhi Lin↗Dailin Li↗Chengfeng Gu↗Xinping Li↗Yaxian Hao↗Shengjia Liang↗Yuxiang Ren↗Wenhao Liu↗

arXiv:2606.15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources. This evaluation gap limits trustworthy AI assistance in proof-certified scientific progress. Existing evaluations often emphasize final answers or rely on costly expert grading, while end-to-end proof generation remains open-ended and hard to verify automatically. We introduce Mask-Proof, a pipeline that turns real proofs into automatically checkable masked-step tasks. It masks key formula steps, provides the necessary surrounding context, and evaluates model reconstructions with an LLM-based equivalence judge using repeated votes for stability. The resulting Mask-ProofBench contains 292 curated problems across diverse research areas. Experiments with 17 models show that reasoning-enhanced models outperform standard models by 12% to 27%. Our evaluator achieves 96.8% agreement with expert annotators, enabling faithful, reproducible, and comparable measurement of step-level mathematical reasoning. Benchmark, annotations, and code are available at https://github.com/weating/Mask-Proof.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17953

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

作者:

Xingming Li↗Ao Cheng↗Qiyao Sun↗Xixiang He↗Xuanyu Ji↗Runke Huang↗Qingyong Hu↗

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12195

InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

作者:

Ziang Yan↗Sheng Xia↗Jiashuo Yu↗Yue Wu↗Tianxiang Jiang↗Songze Li↗Kanghui Tian↗Yicheng Xu↗Yinan He↗Kai Chen↗Limin Wang↗Yu Qiao↗…

Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant settings, leaving long-horizon multimodal tasks underexplored. This gap is evident in video tasks requiring sustained temporal understanding and iterative interaction. We present InternVideo3, a framework enhancing these capabilities via Multimodal Contextual Reasoning (MCR). MCR treats understanding as a closed-loop process over a shared, evolving context containing observations, instructions, reasoning, tool actions, and memory. This frames long-video understanding as evidence accumulation and verification. To ensure efficiency, we introduce Multimodal Multi-head Latent Attention (M^2LA), a token-preserving reparameterization compressing KV-cache states while retaining the full token stream. Our staged training includes continued pretraining, short-to-long supervised fine-tuning, rule-based reinforcement learning, and on-policy distillation. Experiments show InternVideo3 achieves strong performance on benchmarks like Video-MME, MLVU, and EgoSchema. We further instantiate the model as a video agent with retrieval tools, demonstrating robust evidence-grounded behavior. Our results suggest that efficient context handling and closed-loop reasoning are vital for adapting open multimodal models toward long-horizon visually grounded agency.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14295

AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges

作者:

Fengyu Liu↗Jiarun Dai↗Yihe Fan↗Wuyuao Mai↗Ziao Li↗Bofei Chen↗Jie Zhang↗Zheng Lou↗Bocheng Xiang↗Qiyi Zhang↗Xudong Pan↗Geng Hong↗…

arXiv:2606.14295v1 Announce Type: cross Abstract: Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation. However, evaluating their offensive capabilities remains constrained by limited access to open, reproducible, multi-host cyber ranges. Existing public benchmarks capture isolated skills such as CTF solving, vulnerability reproduction, and exploit generation, but often abstract away realistic intrusion workflows: discovering exposed services, gaining a foothold, collecting internal information, and expanding compromise across hosts. This gap makes it difficult to observe emerging risks early, because frontier AI systems are rarely evaluated under realistic attack conditions. We introduce AgentCyberRange, the first open, multi-range infrastructure for measuring autonomous cyber attack capability in realistic cyber ranges. It combines 110 vulnerabilities across 15 real web applications and 8 enterprise-like cyber ranges with 156 internal hosts, plus Cage, a toolchain for execution, orchestration, result collection, and verification. The benchmark covers two core stages: web exploitation, where agents explore exposed applications and validate vulnerabilities, and post exploitation, where agents turn an initial foothold into broader internal compromise. We evaluate six frontier AI systems under matched prompts and budgets. GPT-5.5 with Codex performs best, solving 16.1% of web exploitation tasks and 31.7% of post-exploitation tasks; with more concrete hints, these rates increase to 33.0% and 46.3%. We also observe out-of-benchmark findings, including unknown vulnerabilities in popular projects, and payload mutation that bypasses host defenses. These results show that open cyber-range evaluation is necessary for observing emerging offensive capabilities under realistic and reproducible conditions.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.05405

Agents' Last Exam

作者:

Yiyou Sun↗Xinyang Han↗Weichen Zhang↗Yuanbo Pang↗Tianyu Wang↗Yuhan Cao↗Yixiao Huang↗Chris Duroiu↗Haoyun Zhang↗Jeffrey Lin↗Weishu Zhang↗Tyler Zeng↗…

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15079

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

作者:

Ang Li↗Ben Liu↗Bin Han↗Bin Hu↗Bin Jing↗Binbin Hu↗Bing Li↗Cai Chen↗Caizhi Tang↗Changxin Tian↗Chao Huang↗Chao Zhang↗…

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19348

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

作者:

DeepSeek-AI↗Anyi Xu↗Bangcai Lin↗Bing Xue↗Bingxuan Wang↗Bingzheng Xu↗Bochao Wu↗Bowei Zhang↗Chaofan Lin↗Chen Dong↗Chenchen Ling↗Chengda Lu↗…

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models – DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) – both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

阅读与讨论 → 访问原文 →