❌

Reading view

↗️

SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kuangshi Ai · Haichao Miao · Kaiyuan Tang · Nathaniel Gorski · Jianxin Sun · Guoxi Liu · Helgi I. Ingolfsson · David Lenz · Hanqi Guo · Hongfeng Yu · Teja Leburu · Michael Molash · Bei Wang · Tom Peterka · Chaoli Wang · Shusen Liu
arXiv:2603.29139v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled agentic systems that translate natural language intent into executable scientific visualization (SciVis) tasks. Despite rapid progress, the community lacks a principled and reproducible benchmark for evaluating these emerging SciVis agents in realistic, multi-step analysis settings. We present SciVisAgentBench, a comprehensive and extensible benchmark for evaluating scientific data analysis and visualization agents. Our benchmark is grounded in a structured taxonomy spanning four dimensions: application domain, data type, complexity level, and visualization operation. It currently comprises 108 expert-crafted cases covering diverse SciVis scenarios. To enable reliable assessment, we introduce a multimodal outcome-centric evaluation pipeline that combines LLM-based judging with deterministic evaluators, including image-based metrics, code checkers, rule-based verifiers, and case-specific evaluators. We also conduct a validity study with 12 SciVis experts to examine the agreement between human and LLM judges. Using this framework, we evaluate representative SciVis agents and general-purpose coding agents to establish initial baselines and reveal capability gaps. SciVisAgentBench is designed as a living benchmark to support systematic comparison, diagnose failure modes, and drive progress in agentic SciVis. The benchmark is available at https://scivisagentbench.github.io/.
  •  
  • ↗️
↗️

Towards High-Consistency Embodied World Model with Multi-View Trajectory Videos

✇cs.AI, q-bio.NC updates on arXiv.org
By: Taiyi Su · Jian Zhu · Yaxuan Li · Chong Ma · Jianjun Zhang · Zitai Huang · Hanli Wang · Yi Xu
arXiv:2511.12882v3 Announce Type: replace-cross Abstract: Embodied world models aim to predict and interact with the physical world through visual observations and actions. However, existing models struggle to accurately translate low-level actions (e.g., joint positions) into precise robotic movements in predicted frames, leading to inconsistencies with real-world physical interactions. To address these limitations, we propose MTV-World, an embodied world model that introduces Multi-view Trajectory-Video control for precise visuomotor prediction. Specifically, instead of directly using low-level actions for control, we employ trajectory videos obtained through camera intrinsic and extrinsic parameters and Cartesian-space transformation as control signals. However, projecting 3D raw actions onto 2D images inevitably causes a loss of spatial information, making a single view insufficient for accurate interaction modeling. To overcome this, we introduce a multi-view framework that compensates for spatial information loss and ensures high-consistency with physical world. MTV-World forecasts future frames based on multi-view trajectory videos as input and conditioning on an initial frame per view. Furthermore, to systematically evaluate both robotic motion precision and object interaction accuracy, we develop an auto-evaluation pipeline leveraging multimodal large models and referring video object segmentation models. To measure spatial consistency, we formulate it as an object location matching problem and adopt the Jaccard Index as the evaluation metric. Extensive experiments demonstrate that MTV-World achieves precise control execution and accurate physical interaction modeling in complex dual-arm scenarios.
  •  
  • ↗️
↗️

A monocyte-centered framework for predicting immunochemotherapy efficacy in lung squamous cell carcinoma patients

✇Omics In Lung
By: Jiangnan Zhao · Zijin Wang · Manyu Xiao · Yeyuan Zhang · Boxin Liu · Silin Chen · Yiping Tian · Dongqing Lv · Pingli Wang · Hai Song · Yuefeng Wu · Jian Liu · Kai Wang

EMBO Mol Med. 2026 Mar 30. doi: 10.1038/s44321-026-00410-y. Online ahead of print.

ABSTRACT

Lung cancer is the leading cause of cancer-related mortality worldwide, with lung squamous cell carcinoma (LUSC) comprising 20-30% of cases. Immunochemotherapy (IC) is the standard first-line treatment for advanced LUSC, yet reliable predictors of therapeutic response remain unavailable. Using single-cell multi-omics profiling of paired pre- and post-treatment tumor and blood samples, we observed that patients responding to IC exhibited significantly higher baseline levels of peripheral blood monocytes, tumor-infiltrating classical monocytes, and APOBEC3A+ monocytes across both compartments compared with non-responders. These associations were independently validated in additional cohorts using routine complete blood count testing and multiplex immunofluorescence analysis of native tumor tissues. Our findings reveal monocyte-related parameters as clinically accessible indicators that link systemic immunity with the tumor microenvironment and hold promise for predicting IC responsiveness in patients with LUSC.

PMID:41912871 | DOI:10.1038/s44321-026-00410-y

  •  
  • ↗️
↗️

A monocyte-centered framework for predicting immunochemotherapy efficacy in lung squamous cell carcinoma patients

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Jiangnan Zhao · Zijin Wang · Manyu Xiao · Yeyuan Zhang · Boxin Liu · Silin Chen · Yiping Tian · Dongqing Lv · Pingli Wang · Hai Song · Yuefeng Wu · Jian Liu · Kai Wang

EMBO Mol Med. 2026 Mar 30. doi: 10.1038/s44321-026-00410-y. Online ahead of print.

ABSTRACT

Lung cancer is the leading cause of cancer-related mortality worldwide, with lung squamous cell carcinoma (LUSC) comprising 20-30% of cases. Immunochemotherapy (IC) is the standard first-line treatment for advanced LUSC, yet reliable predictors of therapeutic response remain unavailable. Using single-cell multi-omics profiling of paired pre- and post-treatment tumor and blood samples, we observed that patients responding to IC exhibited significantly higher baseline levels of peripheral blood monocytes, tumor-infiltrating classical monocytes, and APOBEC3A+ monocytes across both compartments compared with non-responders. These associations were independently validated in additional cohorts using routine complete blood count testing and multiplex immunofluorescence analysis of native tumor tissues. Our findings reveal monocyte-related parameters as clinically accessible indicators that link systemic immunity with the tumor microenvironment and hold promise for predicting IC responsiveness in patients with LUSC.

PMID:41912871 | DOI:10.1038/s44321-026-00410-y

  •  
  • ↗️
↗️

Dynamic Targetable Extracellular Vesicle Surface Proteins Monitor Depth of Response to CAR T Therapy

✇MRD
By: Chen Zhao · Lei Qiu · Ning An · Yong Ju · Jacqueline Ziqian Yang · Hyoyong Kim · Ryan Y Zhang · Junseok Lee · Jingjing He · Liang-Yan Chen · Yaya Xu · Yue Ma · Emily Ren · Sophie Pan · Pranay Sashikanth · Jina Kim · Di Wang · Peiling Zhang · Jianlin Hu · Yang Gao · Yuhan Bao · Yanhua Tu · Li Wang · Zhili Wang · Zhicheng Zhang · Renjun Pei · Edwin M Posadas · Sungyong You · Wanxing Chai-Ho · Tasha L Lin · Sarah M Larson · Dinesh S Rao · Hsian-Rong Tseng · Na Sun · Chunrui Li · Yazhen Zhu

Res Sq [Preprint]. 2026 Mar 18:rs.3.rs-8913641. doi: 10.21203/rs.3.rs-8913641/v1.

ABSTRACT

Extracellular vesicles (EVs) represent a promising liquid biopsy platform in multiple myeloma (MM). We developed an MM EV Surface Protein Assay to quantify and dynamically monitor four MM EV subpopulations defined by targetable MM surface proteins (BCMA, CD38, GPRC5D, and CD319) across 336 serial blood samples from 45 relapsed/refractory MM (RRMM) patients treated with anti-BCMA chimeric antigen receptor (CAR) T-cell therapy. All four MM EV subpopulations significantly decreased in 43 patients with initial response, while BCMA+, GPRC5D+, and CD319+ MM EVs increased in 19 patients with progression, and antigen escape was detected by BCMA+ MM EVs. MM EV subpopulations differentiated minimal residual disease (MRD) status and complemented MRD for detecting early relapse before clinical progression. Notably, CD319+ MM EVs were early predictors of progression-free and overall survival in MRD-negative patients. This assay enables noninvasive monitoring of deep response, progression, and antigen escape, and stratifies survival in MRD-negative patients with RRMM.

PMID:41890853 | PMC:PMC13015583 | DOI:10.21203/rs.3.rs-8913641/v1

  •  
  • ↗️
↗️

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenyu Chen · Xiangtao Meng · Chuanchao Zang · Li Wang · Xinyu Gao · Jianing Wang · Peng Zhan · Zheng Li · Shanqing Guo
arXiv:2603.23269v1 Announce Type: cross Abstract: Large Language Models(LLMs) are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all tokens as equally important during prompt mutation, overlooking the varying contributions of individual tokens to triggering model refusals. Consequently, these attacks introduce substantial redundant searching under query-constrained scenarios, reducing attack efficiency and hindering comprehensive vulnerability assessment. In this work, we conduct a token-level analysis of refusal behavior and observe that token contributions are highly skewed rather than uniform. Moreover, we find strong cross-model consistency in refusal tendencies, enabling the use of a surrogate model to estimate token-level contributions to the target model's refusals. Motivated by these findings, we propose TriageFuzz, a token-aware jailbreak fuzzing framework that adapts the fuzz testing approach with a series of customized designs. TriageFuzz leverages a surrogate model to estimate the contribution of individual tokens to refusal behaviors, enabling the identification of sensitive regions within the prompt. Furthermore, it incorporates a refusal-guided evolutionary strategy that adaptively weights candidate prompts with a lightweight scorer to steer the evolution toward bypassing safety constraints. Extensive experiments on six open-source LLMs and three commercial APIs demonstrate that TriageFuzz achieves comparable attack success rates (ASR) with significantly reduced query costs. Notably, it attains a 90% ASR with over 70% fewer queries compared to baselines. Even under an extremely restrictive budget of 25 queries, TriageFuzz outperforms existing methods, improving ASR by 20-40%.
  •  
  • ↗️
↗️

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiangyi Li · Wenbo Chen · Yimin Liu · Shenghan Zheng · Xiaokun Chen · Yifeng He · Yubo Li · Bingran You · Haotian Shen · Jiankai Sun · Shuyi Wang · Binxu Li · Qunhong Zeng · Di Wang · Xuandong Zhao · Yuanli Wang · Roey Ben Chaim · Zonglin Di · Yipeng Gao · Junwei He · Yizhuo He · Liqiang Jing · Luyang Kong · Xin Lan · Jiachen Li · Songlin Li · Yijiang Li · Yueqian Lin · Xinyi Liu · Xuanqing Liu · Haoran Lyu · Ze Ma · Bowei Wang · Runhui Wang · Tianyu Wang · Wengao Ye · Yue Zhang · Hanwen Xing · Yiqi Xue · Steven Dillmann · Han-chung Lee
arXiv:2602.12670v3 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.
  •  
  • ↗️
↗️

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuang Ai · Jiaming Han · Shaobin Zhuang · Weijia Mao · Xuefeng Hu · Ziyan Yang · Zhenheng Yang · Yali Wang · Huaibo Huang · Xiangyu Yue · Hao Chen
arXiv:2602.14041v2 Announce Type: replace-cross Abstract: We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a compact yet highly expressive discrete representation. Sampling from such a huge token space is difficult with standard classification. To resolve this, BitDance uses a binary diffusion head: instead of predicting an index with softmax, it employs continuous-space diffusion to generate the binary tokens. Furthermore, we propose next-patch diffusion, a new decoding method that predicts multiple tokens in parallel with high accuracy, greatly speeding up inference. On ImageNet 256x256, BitDance achieves an FID of 1.24, the best among AR models. With next-patch diffusion, BitDance beats state-of-the-art parallel AR models that use 1.4B parameters, while using 5.4x fewer parameters (260M) and achieving 8.7x speedup. For text-to-image generation, BitDance trains on large-scale multimodal tokens and generates high-resolution, photorealistic images efficiently, showing strong performance and favorable scaling. When generating 1024x1024 images, BitDance achieves a speedup of over 30x compared to prior AR models. We release code and models to facilitate further research on AR foundation models. Code and models are available at: https://github.com/shallowdream204/BitDance.
  •  
  • ↗️
↗️

Integrated Multi-Omics Analysis Reveals Modulation of the Ras Pathway by Siji Kangbingdu Mixture in Acute Lung Injury

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Bo Han · Fei Luan · Xiaofei Zhang · Dongyan Guo · Bingtao Zhai · Jing Sun · Changli Wang · Chunli Cui · Junbo Zou · Yajun Shi

Comb Chem High Throughput Screen. 2026 Mar 11. doi: 10.2174/0113862073398293251205055042. Online ahead of print.

ABSTRACT

INTRODUCTION: This study aimed to investigate the protective effects of Siji Kangbingdu Mixture (SKM) against acute lung injury (ALI) in mice and to elucidate its underlying mechanisms.

METHODS: ALI was induced in Kunming mice via intranasal administration of LPS (5 mg/kg), followed by oral SKM treatment for 7 days. Lung wet-to-dry (W/D) ratio, histopathology, multiomics analysis, and network pharmacology were performed. Key targets and pathways were identified through dynamic KEGG analysis and validated by Western blotting.

RESULTS: SKM treatment ameliorated alveolar hemorrhage, alveolar wall disruption, septal thickening, edema, and inflammatory cell infiltration. Integrated multi-omics analysis revealed that SKM primarily modulated the Ras signaling pathway, reducing the protein expression of Phospho- MEK1/2, Raf1, Phospho-ERK1/2, and RASH/RASK/RASN, thereby contributing to the treatment of ALI.

DISCUSSION: SKM alleviated LPS-induced ALI in mice by inhibiting the Ras pathway, highlighting the pathway's role in ALI pathogenesis. However, due to limitations of the animal model and incomplete validation, further studies combining clinical research and in vitro experiments are needed to confirm its efficacy and mechanism.

CONCLUSIONS: SKM shows potential to ameliorate ALI by suppressing inflammatory responses and reducing local tissue fibrosis. The combination of metabolomics, transcriptomics, and network pharmacology elucidated its mechanism, while Western blot analysis suggested that its therapeutic effect is associated with downregulation of the Ras signaling pathway.

PMID:41830142 | DOI:10.2174/0113862073398293251205055042

  •  
  • ↗️
↗️

Integrated Multi-Omics Analysis Reveals Modulation of the Ras Pathway by Siji Kangbingdu Mixture in Acute Lung Injury

✇Omics In Lung
By: Bo Han · Fei Luan · Xiaofei Zhang · Dongyan Guo · Bingtao Zhai · Jing Sun · Changli Wang · Chunli Cui · Junbo Zou · Yajun Shi

Comb Chem High Throughput Screen. 2026 Mar 11. doi: 10.2174/0113862073398293251205055042. Online ahead of print.

ABSTRACT

INTRODUCTION: This study aimed to investigate the protective effects of Siji Kangbingdu Mixture (SKM) against acute lung injury (ALI) in mice and to elucidate its underlying mechanisms.

METHODS: ALI was induced in Kunming mice via intranasal administration of LPS (5 mg/kg), followed by oral SKM treatment for 7 days. Lung wet-to-dry (W/D) ratio, histopathology, multiomics analysis, and network pharmacology were performed. Key targets and pathways were identified through dynamic KEGG analysis and validated by Western blotting.

RESULTS: SKM treatment ameliorated alveolar hemorrhage, alveolar wall disruption, septal thickening, edema, and inflammatory cell infiltration. Integrated multi-omics analysis revealed that SKM primarily modulated the Ras signaling pathway, reducing the protein expression of Phospho- MEK1/2, Raf1, Phospho-ERK1/2, and RASH/RASK/RASN, thereby contributing to the treatment of ALI.

DISCUSSION: SKM alleviated LPS-induced ALI in mice by inhibiting the Ras pathway, highlighting the pathway's role in ALI pathogenesis. However, due to limitations of the animal model and incomplete validation, further studies combining clinical research and in vitro experiments are needed to confirm its efficacy and mechanism.

CONCLUSIONS: SKM shows potential to ameliorate ALI by suppressing inflammatory responses and reducing local tissue fibrosis. The combination of metabolomics, transcriptomics, and network pharmacology elucidated its mechanism, while Western blot analysis suggested that its therapeutic effect is associated with downregulation of the Ras signaling pathway.

PMID:41830142 | DOI:10.2174/0113862073398293251205055042

  •  
  • ↗️
↗️

Effect of a Digital-Driven Physician-Pharmacist Collaborative Model for Diabetes in Primary Health Care: Cluster Randomized Trial

✇Journal of Medical Internet Research
By: Jie Xiao · Qing Wang · Shenglan Tan · Lei Chen · Daxiong Xiang · Haiyan Yuan · Xia Li · Shuting Huang · Bingjie Tang · Yan Guo · Haiying Huang · Danhui Zhao · Yue Li · Li Wang · Qun Li · Juan Liu · Ping Xu
Background: Evidence-based physician-pharmacist collaborative clinics have demonstrated significant short-term benefits for patients with type 2 diabetes (T2D), but their long-term effectiveness remains unclear, especially in primary health care settings. Objective: This study aimed to explore the long-term effectiveness and cost-effectiveness of a novel, digital-driven, multifaceted physician-pharmacist collaborative model for managing patients with T2D in underresourced settings. Methods: We conducted a 12-month cluster randomized controlled trial from May 2021 to December 2022 across 6 primary health care settings in China. Guided by the theory of planned behavior, the intervention involved routine therapy from physicians along with pharmaceutical interventions from pharmacists. These were delivered through a combination of face-to-face visits and mobile health care. The intervention group received 4 face-to-face visits and biweekly remote education sessions over the 12 months. We conducted intention-to-treat analyses to estimate differences in clinical and behavior indicators between the intervention and control groups. Primary outcomes included glycosylated hemoglobin and 10-year atherosclerotic cardiovascular risk. Data were analyzed using adjusted generalized estimation equations. Results: This study included 574 patients (291 in the intervention group and 283 in the control group). Over 12 months, patients in the intervention group had significant reductions in hemoglobin A1c (–2.57 vs –1.96, respectively; P<.001; 95% CI –1.027 to –0.238) and 10-year atherosclerotic cardiovascular risk (–1.35 vs 0.01, respectively; P<.001; 95% CI –1.690 to –0.630) compared with the control group. Substantial improvements were also observed in several secondary outcomes, including fasting blood glucose, 2-hour postprandial blood glucose, waist circumference, waist-to-hip ratio, blood pressure, triglyceride, and total cholesterol. Total diabetes-related costs decreased, and patient satisfaction improved significantly in the intervention group. There were no significant differences in BMI, high-density lipoprotein, or low-density lipoprotein. Conclusions: These findings suggest that the physician-pharmacist collaborative model could improve the long-term quality and efficiency of T2D management and reduce medical costs in underresourced areas globally. Patients with T2D, especially those with central obesity or high cardiovascular risk, may benefit more from collaborative clinics. Trial Registration: Chinese Clinical Trial Registry ChiCTR2000031839; https://www.chictr.org.cn/showproj.html?proj=51910
  •  
  • ↗️
↗️

METTL16 enhances proteasome inhibitor resistance in multiple myeloma by inhibiting eIF2α-PERK interaction and promoting PSMB5 translation

✇Oncogene - Issue - nature.com science feeds
By: Guanli Wang · Xuejie Gao · Hui Zhang · Ke Hu · Qilin Feng · Yujie Liu · Chaolu Hu · Shushan Guo · Dandan Yu · Shuaikang Chang · Xiaosong Wu · Xinyan Jia · Dong An · Yu Peng · Yi Tao · Haiyan Cai · Gege Chen · Li Zhang · Jumei Shi

Oncogene, Published online: 13 March 2026; doi:10.1038/s41388-026-03706-y

METTL16 enhances proteasome inhibitor resistance in multiple myeloma by inhibiting eIF2α-PERK interaction and promoting PSMB5 translation
  •  
  • ↗️
↗️

FNDC1 Competitively Binds Gbeta2 to Suppress the beta-Catenin-Destruction Complex and Promote Gastric Cancer Malignancy

✇Omics in Gastric
By: Wenyu Gao · Hao Chen · Fangyu Lin · Jialin Liu · Tingxuan Huang · Han Wang · Xiaojiao Weng · Xinli Wang · Xiaoyan Lin · Tao Jiang

FASEB J. 2026 Mar 31;40(6):e71634. doi: 10.1096/fj.202503587R.

ABSTRACT

Gastric cancer (GC) is a leading cause of cancer-related deaths and has high recurrence rate. Although fibronectin domain-containing protein 1 (FNDC1) is implicated in GC progression, its molecular mechanisms remain unclear. Multi-omics analyses (TCGA, GEO datasets) were used to assess FNDC1 expression and clinical correlation. In vitro (cell proliferation, invasion, EMT markers) and in vivo (xenograft) experiments, combined with molecular assays (Co-IP, WB, ChIP), explored FNDC1's function and mechanism. FNDC1 was significantly upregulated in GC, correlating with advanced clinicopathological features and poor prognosis. Knockdown of FNDC1 suppressed GC cell proliferation, invasion, and metastasis by inhibiting EMT and Wnt/β-catenin signaling. Mechanistically, FNDC1 competitively bound the WD5 domain (residues 224-254) of Gβ2, disrupting Gβγ-Dvl1 interaction. This prevented Dvl1 degradation, promoted Axin1 ubiquitination, and destabilized the β-catenin-destruction complex (GSK3 β-APC-Axin1), leading to β-catenin accumulation and Wnt pathway activation. FNDC1 drives GC malignancy by targeting the Gβ2-Dvl1 axis to activate Wnt/β-catenin signaling, suggesting FNDC1 as a novel prognostic biomarker and therapeutic target.

PMID:41808415 | PMC:PMC12976582 | DOI:10.1096/fj.202503587R

  •  
  • ↗️
↗️

GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fali Wang · Chenglin Weng · Xianren Zhang · Siyuan Hong · Hui Liu · Suhang Wang
arXiv:2603.06620v1 Announce Type: cross Abstract: The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data, generate executable code augmented by retrieval from technical documentation, and refine the code through debugging. However, we identify two key limitations in existing approaches: (i) they treat technical documentation as flat text collections and ignore its hierarchical structure, leading to noisy retrieval that degrades code generation quality; and (ii) their debugging mechanisms focus primarily on runtime errors, yet ignore more critical logical errors. To address them, we propose {\method}, an \textit{agentic hierarchical retrieval-augmented coding framework} that exploits the document hierarchy through top-down traversal and early pruning, together with a \textit{self-debugging coding agent} that iteratively refines code using automatically generated small-scale test cases. To enable comprehensive evaluation of complex graph reasoning, we introduce a new dataset, {\dataset}, covering small-scale, large-scale, and composite graph reasoning tasks. Extensive experiments demonstrate that our method achieves higher task accuracy and lower inference cost compared to baselines\footnote{The code is available at \href{https://github.com/FairyFali/GraphSkill}{\textcolor{blue}{https://github.com/FairyFali/GraphSkill}}.}.
  •  
  • ↗️
↗️

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiangyi Li · Wenbo Chen · Yimin Liu · Shenghan Zheng · Xiaokun Chen · Yifeng He · Yubo Li · Bingran You · Haotian Shen · Jiankai Sun · Shuyi Wang · Binxu Li · Qunhong Zeng · Di Wang · Xuandong Zhao · Yuanli Wang · Roey Ben Chaim · Zonglin Di · Yipeng Gao · Junwei He · Yizhuo He · Liqiang Jing · Luyang Kong · Xin Lan · Jiachen Li · Songlin Li · Yijiang Li · Yueqian Lin · Xinyi Liu · Xuanqing Liu · Haoran Lyu · Ze Ma · Bowei Wang · Runhui Wang · Tianyu Wang · Wengao Ye · Yue Zhang · Hanwen Xing · Yiqi Xue · Steven Dillmann · Han-chung Lee
arXiv:2602.12670v2 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.
  •  
  • ↗️
↗️

Taming Modality Entanglement in Continual Audio-Visual Segmentation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuyang Hong · Qi Yang · Tao Zhang · Zili Wang · Zhaojin Fu · Kun Ding · Bin Fan · Shiming Xiang
arXiv:2510.17234v2 Announce Type: replace-cross Abstract: Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previously learned ones. However, existing methods mainly focus on coarse-grained tasks, with limitations in addressing modality entanglement in fine-grained continual learning settings. To bridge this gap, we introduce a novel Continual Audio-Visual Segmentation (CAVS) task, aiming to continuously segment new classes guided by audio. Through comprehensive analysis, two critical challenges are identified: 1) multi-modal semantic drift, where a sounding objects is labeled as background in sequential tasks; 2) co-occurrence confusion, where frequent co-occurring classes tend to be confused. In this work, a Collision-based Multi-modal Rehearsal (CMR) framework is designed to address these challenges. Specifically, for multi-modal semantic drift, a Multi-modal Sample Selection (MSS) strategy is proposed to select samples with high modal consistency for rehearsal. Meanwhile, for co-occurence confusion, a Collision-based Sample Rehearsal (CSR) mechanism is designed, allowing for the increase of rehearsal sample frequency of those confusable classes during training process. Moreover, we construct three audio-visual incremental scenarios to verify effectiveness of our method. Comprehensive experiments demonstrate that our method significantly outperforms single-modal continual learning methods.
  •  
  • ↗️
↗️

Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guanfeng Tang · Hongbo Zhao · Ziwei Long · Jiayao Li · Bohong Xiao · Wei Ye · Hanli Wang · Rui Fan
arXiv:2602.13588v1 Announce Type: cross Abstract: Inspired by the human visual system, which operates on two parallel yet interactive streams for contextual and spatial understanding, this article presents Two Interactive Streams (TwInS), a novel bio-inspired joint learning framework capable of simultaneously performing scene parsing and geometric vision tasks. TwInS adopts a unified, general-purpose architecture in which multi-level contextual features from the scene parsing stream are infused into the geometric vision stream to guide its iterative refinement. In the reverse direction, decoded geometric features are projected into the contextual feature space for selective heterogeneous feature fusion via a novel cross-task adapter, which leverages rich cross-view geometric cues to enhance scene parsing. To eliminate the dependence on costly human-annotated correspondence ground truth, TwInS is further equipped with a tailored semi-supervised training strategy, which unleashes the potential of large-scale multi-view data and enables continuous self-evolution without requiring ground-truth correspondences. Extensive experiments conducted on three public datasets validate the effectiveness of TwInS's core components and demonstrate its superior performance over existing state-of-the-art approaches. The source code will be made publicly available upon publication.
  •  
  • ↗️
↗️

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shaobin Zhuang · Yuang Ai · Jiaming Han · Weijia Mao · Xiaohui Li · Fangyikang Wang · Xiao Wang · Yan Li · Shanchuan Lin · Kun Xu · Zhenheng Yang · Huaibo Huang · Xiangyu Yue · Hao Chen · Yali Wang
arXiv:2602.14178v1 Announce Type: cross Abstract: Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers typically struggle to satisfy these conflicting objectives within a single framework. In this paper, we introduce UniWeTok, a unified discrete tokenizer designed to bridge this gap using a massive binary codebook ($\mathit{2^{128}}$). For training framework, we introduce Pre-Post Distillation and a Generative-Aware Prior to enhance the semantic extraction and generative prior of the discrete tokens. In terms of model architecture, we propose a convolution-attention hybrid architecture with the SigLu activation function. SigLu activation not only bounds the encoder output and stabilizes the semantic distillation process but also effectively addresses the optimization conflict between token entropy loss and commitment loss. We further propose a three-stage training framework designed to enhance UniWeTok's adaptability cross various image resolutions and perception-sensitive scenarios, such as those involving human faces and textual content. On ImageNet, UniWeTok achieves state-of-the-art image generation performance (FID: UniWeTok 1.38 vs. REPA 1.42) while requiring a remarkably low training compute (Training Tokens: UniWeTok 33B vs. REPA 262B). On general-domain, UniWeTok demonstrates highly competitive capabilities across a broad range of tasks, including multimodal understanding, image generation (DPG Score: UniWeTok 86.63 vs. FLUX.1 [Dev] 83.84), and editing (GEdit Overall Score: UniWeTok 5.09 vs. OmniGen 5.06). We release code and models to facilitate community exploration of unified tokenizer and MLLM.
  •  
  • ↗️
❌