❌

Normal view

Received — 15 September 2026 ⏭

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dawei Liu · Zongxia Li · Hongyang Du · Xiyang Wu · Shihang Gui · Yongbei Kuang · Lichao Sun
14 September 2026 at 12:00
arXiv:2604.05333v4 Announce Type: replace Abstract: As LLM agents act across personal applications, web browsers, and other interfaces, their reusable skill libraries can scale to thousands of skills. This scale introduces two challenges. First, loading the full library saturates the context window, driving up token costs, hallucination, and latency. Second, semantic retrieval surfaces topically relevant skills but can miss upstream and downstream prerequisite skills, creating a prerequisite gap that leaves the retrieved bundle insufficient for execution. We present Graph-of-Skills (GoS), an inference-time structural retrieval layer for large skill libraries. GoS constructs an executable skill graph offline from skill packages, then retrieves a bounded, dependency-aware bundle through hybrid semantic-lexical seeding, reverse-aware Personalized PageRank, and context-budgeted hydration. Across SkillsBench and ALFWorld, with three model families (Claude Sonnet 4.5, MiniMax M2.7, and GPT-5.2 Codex), GoS attains the highest average reward in all six model-benchmark blocks, at a fraction of the token cost of loading the full library. On SkillsBench with GPT-5.2 Codex it raises average reward by 7.0 absolute points over full skill loading, a 25.6% relative gain, while cutting total tokens by 56.7%. Ablations isolate the mechanism: replacing reverse traversal with forward propagation costs 9.1 reward points, a larger loss than removing the graph altogether. The gain thus comes from traversing dependencies backwards, not from graph diffusion as such. A budget-matched retrieval study holding seeding, reranking, hydration, and context budget fixed reproduces the same ordering, with dependency-pair co-recovery falling from 0.654 to 0.362. Code is available at https://github.com/davidliuk/graph-of-skills
Received — 13 September 2026 ⏭

Fibronectin 1 mediated histone lactylation promotes malignant progression of GIST regulated by m<sup>6</sup>A modification

✇Cell Death Discovery nature.com science feeds
By: Ge Zhang · Jiehan Li · Yuhan Yin · Wunan Mi · Hao Liu · Zhao Sun · Jiahao Liu · Yizheng Zhang · Meimei Jiang · Nannan Liu · Guiyun Jia · Yingjie Zhang · Yang Fu
11 September 2026 at 08:00

Cell Death Discovery, Published online: 11 September 2026; doi:10.1038/s41420-026-03338-x

Fibronectin 1 mediated histone lactylation promotes malignant progression of GIST regulated by m6A modification
Received — 27 May 2026 ⏭

NPSolver: Neural Poisson Solver with Iterative Physics Supervision

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bocheng Zeng · Rui Zhang · Runze Mao · Mengtao Yan · Xuan Bai · Yang Liu · Zhi X. Chen · Hao Sun
26 May 2026 at 12:00
arXiv:2605.25786v1 Announce Type: cross Abstract: Efficiently solving Poisson equations on complex, irregular domains remains a fundamental challenge in scientific computing, as classical iterative solvers often suffer from prohibitive runtime due to ill-conditioned systems. While neural operators offer a fast alternative, they typically rely on large-scale labeled datasets or struggle with unstable training dynamics when using physics-informed residual losses. We propose \textsc{NPSolver}, a neural Poisson solver trained without solution labels via iterative physics supervision. Instead of relying on fully converged numerical solutions or raw PDE residuals, \textsc{NPSolver} utilizes a small number of preconditioned conjugate gradient (PCG) steps to refine its own predictions, providing a more stable and well-scaled training signal. Theoretical analysis confirms that this iterative supervision serves as a well-conditioned error proxy and that a stop-gradient design is essential for optimization stability. To better capture boundary-driven features under mixed boundary conditions, we further introduce the Boundary-Aware Transolver (\textsc{BA-Transolver}) architecture that explicitly separates interior and boundary tokenization. Extensive evaluations on 2D and 3D irregular geometries demonstrate that \textsc{NPSolver} outperforms both physics-informed and data-driven baselines. Furthermore, a downstream thermal control task highlights the model's capability for conducting efficient and reliable gradient-based boundary control. We will release our codes and data at https://github.com/intell-sci-comput/NPSolver.

Auditing medical multi-agent AI reveals risks of false consensus

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yinghao Zhu · Lei Gu · Zixiang Wang · Haoran Sang · Dehao Sui · Wen Tang · Lan Mi · Yasha Wang · Junyi Gao · Liang Yao · Tianfan Fu · Ewen Harrison · Lequan Yu
26 May 2026 at 12:00
arXiv:2510.10185v2 Announce Type: replace-cross Abstract: Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through specialist roles, peer review and consensus formation. In clinical decision support, however, apparent consensus is not enough. Clinicians also need to know whether agents checked the evidence, addressed disagreement and kept uncertainty visible. Current evaluations largely score final accuracy, leaving the safety of the collaborative process untested. Here we introduce MedAgentAudit, a clinically grounded workflow audit framework for diagnosing and quantifying collaborative failure modes in medical multi-agent systems. From 3,600 execution logs, we derive an expert-validated taxonomy of ten recurrent failures spanning task comprehension, collaborative discussion, and synthesis and decision-making. We then deploy an expert-validated automated auditor as non-interventional probes across 14,400 cases, covering six multi-agent architectures, six medical text and vision datasets, and four large language model settings per modality. Across systems, collaboration yields uneven accuracy gains and frequent process failures. Unsupported observations affect 16.63% of cases and propagate downstream. In discussion, agents repeat initial views in 98.42% of cases rather than re-examining evidence, and fail to activate specialist reasoning in 42.73%. During synthesis, final answers often substitute authority or majority count for evidence checking, showing authority bias in 28.76% (rising from 35.30% to 68.75% across rounds), self-contradiction in 18.53%, contradiction neglect in 5.48% and minority suppression in 5.11%. MedAgentAudit reframes medical AI evaluation from output scoring to process-level safety and accountability, providing a practical foundation for transparent, auditable and clinician-supervised agentic systems in medicine.

SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenhao Sun · Rong-Cheng Tu · Yifu Ding · Zhao Jin · Jingyi Liao · Yongcheng Jing · Dacheng Tao
26 May 2026 at 12:00
arXiv:2602.02544v2 Announce Type: replace-cross Abstract: While Diffusion Language Models (DLMs) offer a flexible, arbitrary-order alternative to the autoregressive paradigm, their non-causal nature precludes standard KV caching, forcing costly hidden state recomputation at every decoding step. Existing DLM caching approaches reduce this cost by selective hidden state updates; however, they are still limited by (i) costly token-wise update identification heuristics and (ii) rigid, uniform budget allocation that fails to account for heterogeneous hidden state dynamics. To address these challenges, we present SPA-Cache that jointly optimizes update identification and budget allocation in DLM cache. First, we derive a low-dimensional singular proxy that enables the identification of update-critical tokens in a low-dimensional subspace, substantially reducing the overhead of update identification. Second, we introduce an adaptive strategy that allocates fewer updates to stable layers without degrading generation quality. Together, these contributions significantly improve the efficiency of DLMs, yielding up to an $8\times$ throughput improvement over vanilla decoding and a $2$--$4\times$ speedup over existing caching baselines.
Received — 13 April 2026 ⏭

Characterization and regulatory mechanism evaluation of C8orf33 in hepatocellular carcinoma through multiomics profiling

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Wei Gao · Siyi Xing · Mingjiang Liu · Xing Xie · Mei Feng · Zhipeng Quan · Housheng Wang · Zhilong He · Qianxin Hu · Huizhao Su · Shuiping Yu · Zeyuan Li
11 April 2026 at 18:00

Discov Oncol. 2026 Apr 11. doi: 10.1007/s12672-026-04951-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is a major cause of cancer-related mortality. Chromosome 8 open reading frame 33 (C8orf33) has been noted as a potential oncogenic factor in several cancers, but its biological roles and regulatory mechanism in HCC microenvironment remain unknown.

METHODS: We integrated bulk RNA sequencing, single-cell RNA sequencing (scRNA-seq), and spatial transcriptomics (ST) to characterize the expression landscape of C8orf33. We then performed C8orf33 loss-of-function studies in HCC cell lines, including in vitro phenotypic assays and subcutaneous xenografts.

RESULTS: C8orf33 was broadly overexpressed and associated with unfavorable prognosis across multiple Cancers. In HCC, higher C8orf33 aligned with advanced stage and shorter overall survival. C8orf33 knockdown reduced proliferation and migration, impaired tumorigenic capacity, and increased apoptosis. ScRNA-seq analyses identified a malignant population of Epi3 with high C8orf33 expression. Cell-cell communication analysis suggested that C8orf33-high Epi3 state was associated with an enriched MIF-CD74/CXCR4/CD44 signaling program toward macrophage populations with M2-like features. ST analyses further confirmed the colocalization of C8orf33 with malignant features in tumor cores. In Huh7 cells, C8orf33 knockdown was accompanied by reduced mRNA and protein levels of MIF and its receptor components. Consistently, xenografts derived from C8orf33-silenced cells showed lower expression of these MIF-axis components and reduced infiltration of CD163 and CD206-positive macrophages.

CONCLUSION: These results support a tumor-promoting association of C8orf33 in HCC and suggest a potential link to macrophage-associated immunomodulatory features, nominating C8orf33 as a candidate biomarker and therapeutic target.

PMID:41965457 | DOI:10.1007/s12672-026-04951-z

Characterization and regulatory mechanism evaluation of C8orf33 in hepatocellular carcinoma through multiomics profiling

✇Omics in Hepatocellular
By: Wei Gao · Siyi Xing · Mingjiang Liu · Xing Xie · Mei Feng · Zhipeng Quan · Housheng Wang · Zhilong He · Qianxin Hu · Huizhao Su · Shuiping Yu · Zeyuan Li
11 April 2026 at 18:00

Discov Oncol. 2026 Apr 11. doi: 10.1007/s12672-026-04951-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is a major cause of cancer-related mortality. Chromosome 8 open reading frame 33 (C8orf33) has been noted as a potential oncogenic factor in several cancers, but its biological roles and regulatory mechanism in HCC microenvironment remain unknown.

METHODS: We integrated bulk RNA sequencing, single-cell RNA sequencing (scRNA-seq), and spatial transcriptomics (ST) to characterize the expression landscape of C8orf33. We then performed C8orf33 loss-of-function studies in HCC cell lines, including in vitro phenotypic assays and subcutaneous xenografts.

RESULTS: C8orf33 was broadly overexpressed and associated with unfavorable prognosis across multiple Cancers. In HCC, higher C8orf33 aligned with advanced stage and shorter overall survival. C8orf33 knockdown reduced proliferation and migration, impaired tumorigenic capacity, and increased apoptosis. ScRNA-seq analyses identified a malignant population of Epi3 with high C8orf33 expression. Cell-cell communication analysis suggested that C8orf33-high Epi3 state was associated with an enriched MIF-CD74/CXCR4/CD44 signaling program toward macrophage populations with M2-like features. ST analyses further confirmed the colocalization of C8orf33 with malignant features in tumor cores. In Huh7 cells, C8orf33 knockdown was accompanied by reduced mRNA and protein levels of MIF and its receptor components. Consistently, xenografts derived from C8orf33-silenced cells showed lower expression of these MIF-axis components and reduced infiltration of CD163 and CD206-positive macrophages.

CONCLUSION: These results support a tumor-promoting association of C8orf33 in HCC and suggest a potential link to macrophage-associated immunomodulatory features, nominating C8orf33 as a candidate biomarker and therapeutic target.

PMID:41965457 | DOI:10.1007/s12672-026-04951-z

Received — 4 April 2026 ⏭

WFR-FM: Simulation-Free Dynamic Unbalanced Optimal Transport

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qiangwei Peng · Zihan Wang · Junda Ying · Yuhao Sun · Qing Nie · Lei Zhang · Tiejun Li · Peijie Zhou
3 April 2026 at 12:00
arXiv:2601.06810v2 Announce Type: replace-cross Abstract: The Wasserstein-Fisher-Rao (WFR) metric extends dynamic optimal transport (OT) by coupling displacement with change of mass, providing a principled geometry for modeling unbalanced snapshot dynamics. Existing WFR solvers, however, are often unstable, computationally expensive, and difficult to scale. Here we introduce WFR Flow Matching (WFR-FM), a simulation-free training algorithm that unifies flow matching with dynamic unbalanced OT. Unlike classical flow matching which regresses only a transport vector field, WFR-FM simultaneously regresses a vector field for displacement and a scalar growth rate function for birth-death dynamics, yielding continuous flows under the WFR geometry. Theoretically, we show that minimizing the WFR-FM loss exactly recovers WFR geodesics. Empirically, WFR-FM yields more accurate and robust trajectory inference in single-cell biology, reconstructing consistent dynamics with proliferation and apoptosis, estimating time-varying growth fields, and applying to generative dynamics under imbalanced data. It outperforms state-of-the-art baselines in efficiency, stability, and reconstruction accuracy. Overall, WFR-FM establishes a unified and efficient paradigm for learning dynamical systems from unbalanced snapshots, where not only states but also mass evolve over time. The Python code is available at https://github.com/QiangweiPeng/WFR-FM.
Received — 2 April 2026 ⏭

Cellular Senescence in Gastric Cancer: Molecular Mechanisms, Microenvironment Remodeling and Therapeutic Implications

✇Omics in Gastric
By: Zhiyuan Shi · Zhao Sun · Yuan Liu · Yuping Ge · Ning Jia · Yuwei Hua · Lin Zhao · Xiang Wang · Yi Ba
30 March 2026 at 18:00

Aging Dis. 2026 Mar 19. doi: 10.14336/AD.2025.1571. Online ahead of print.

ABSTRACT

Gastric cancer (GC) remains a leading cause of cancer-related morbidity and mortality worldwide, with poor prognosis for advanced-stage patients. Therefore, in-depth exploration of the mechanisms underlying GC initiation and progression, as well as the development of novel therapeutic strategies, is of crucial importance. Cellular senescence is a stable cell cycle arrest program that plays a dual role in GC. It exerts tumor-suppressive effects via growth arrest but also promotes tumor progression and immune evasion by remodeling the tumor microenvironment (TME) through senescence-associated secretory phenotype (SASP). This review comprehensively elucidates the molecular mechanisms of cellular senescence in GC and the core regulatory networks involving gene regulation, epigenetic modifications, metabolic reprogramming, and cell cycle arrest. Additionally, the review highlights how senescent cells foster an immunosuppressive microenvironment via SASP, forming a self-reinforcing feed-forward loop. Regarding therapeutic strategies, we summarize potential approaches targeting cellular senescence, including senescence induction, senescent cell clearance, SASP modulation, and multi-target synergistic therapy by integrating epigenetic regulation, metabolic intervention, and immune microenvironment modulation. Despite progress, numerous challenges remain. Future studies should leverage multi-omics technologies, novel models' development, and large-scale clinical trials to advance the clinical translation of GC cellular senescence research, providing new insights for improving prognosis.

PMID:41910653 | DOI:10.14336/AD.2025.1571

Received — 17 March 2026 ⏭

One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shaolong Li · Lichao Sun · Yongchao Chen
16 March 2026 at 12:00
arXiv:2603.12480v1 Announce Type: cross Abstract: Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic policies. However, their reliance on iterative sampling introduces severe inference latency, degrading control frequency and harming performance in time-sensitive manipulation. To address this problem, we propose the One-Step Flow Policy (OFP), a from-scratch self-distillation framework for high-fidelity, single-step action generation without a pre-trained teacher. OFP unifies a self-consistency loss to enforce coherent transport across time intervals, and a self-guided regularization to sharpen predictions toward high-density expert modes. In addition, a warm-start mechanism leverages temporal action correlations to minimize the generative transport distance. Evaluations across 56 diverse simulated manipulation tasks demonstrate that a one-step OFP achieves state-of-the-art results, outperforming 100-step diffusion and flow policies while accelerating action generation by over $100\times$. We further integrate OFP into the $\pi_{0.5}$ model on RoboTwin 2.0, where one-step OFP surpasses the original 10-step policy. These results establish OFP as a practical, scalable solution for highly accurate and low-latency robot control.
Received — 11 March 2026 ⏭

Dual Randomized Smoothing: Beyond Global Noise Variance

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenhao Sun · Yuhao Mao · Martin Vechev
10 March 2026 at 12:00
arXiv:2512.01782v3 Announce Type: replace-cross Abstract: Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With RS, achieving high accuracy at small radii requires a small noise variance, while achieving high accuracy at large radii requires a large noise variance. However, the global noise variance used in the standard RS formulation leads to a fundamental limitation: there exists no global noise variance that simultaneously achieves strong performance at both small and large radii. To break through the global variance limitation, we propose a dual RS framework which enables input-dependent noise variances. To achieve that, we first prove that RS remains valid with input-dependent noise variances, provided the variance is locally constant around each input. Building on this result, we introduce two components: (i) a variance estimator predicts an optimal noise variance for each input, (ii) this estimated variance is then used by a standard RS classifier. The variance estimator is independently smoothed via RS to ensure local constancy, enabling flexible design. We also introduce training strategies to iteratively optimize the two components. Experiments on CIFAR-10 demonstrate that our dual RS method provides strong performance for both small and large radii-unattainable with global noise variance-while incurring only a 60% computational overhead at inference. Moreover, it outperforms prior input-dependent noise approaches across most radii, with gains at radii 0.5, 0.75, and 1.0 of 15.6%, 20.0%, and 15.7%. On ImageNet, dual RS remains effective across all radii, with advantages of 8.6%, 17.1%, and 9.1% at radii 0.5, 1.0, and 1.5. Additionally, the dual RS framework provides a routing perspective for certified robustness, improving the accuracy-robustness trade-off with off-the-shelf expert RS models.

CRTAM inhibition mitigates toxicity of immune checkpoint inhibitors without antitumor efficacy trade-off

✇Nature Cancer
By: Si-Cong Ma · Zi-Xuan Rong · Zi-Peng Xu · Yan-Pei Zhang · Kui-Mao Zhuang · Hao Sun · Chuan-Hui Cao · Ze-Nan Wu · Hai-Peng Zhang · Qiang Zuo · Jia-Run Lin · Jia-Xin Cheng · Hua-Ting Qu · Duan-Duan Han · Wei Wei · Ke Liu · Xiao-Ting Cai · Ze-Qin Guo · Xue Bai · Li Liu · De-Hua Wu · Zhong-Yi Dong
5 March 2026 at 08:00

Nature Cancer, Published online: 05 March 2026; doi:10.1038/s43018-026-01135-0

Dong and colleagues report that blockade of T cell-expressed cytotoxic and regulatory T cell molecule results in selective mitigation of immune-related toxicities without affecting antitumor efficacy of immune checkpoint inhibitors.
Received — 5 March 2026 ⏭

Learning Physical Principles from Interaction: Self-Evolving Planning via Test-Time Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haoyang Li · Yang You · Hao Su · Leonidas Guibas
5 March 2026 at 13:00
arXiv:2602.20323v2 Announce Type: replace-cross Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about friction and stability in general terms; however, they often cannot predict how a specific ball will roll on a particular surface or which stone will provide a stable foundation without direct experience. We present PhysMem, a memory framework that enables VLM robot planners to learn physical principles from interaction at test time, without updating model parameters. The system records experiences, generates candidate hypotheses, and verifies them through targeted interaction before promoting validated knowledge to guide future decisions. A central design choice is verification before application: the system tests hypotheses against new observations rather than applying retrieved experience directly, reducing rigid reliance on prior experience when physical conditions change. We evaluate PhysMem on three real-world manipulation tasks and simulation benchmarks across four VLM backbones. On a controlled brick insertion task, principled abstraction achieves 76% success compared to 23% for direct experience retrieval, and real-world experiments show consistent improvement over 30-minute deployment sessions.

Dual Randomized Smoothing: Beyond Global Noise Variance

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenhao Sun · Yuhao Mao · Martin Vechev
4 March 2026 at 13:00
arXiv:2512.01782v2 Announce Type: replace-cross Abstract: Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With RS, achieving high accuracy at small radii requires a small noise variance, while achieving high accuracy at large radii requires a large noise variance. However, the global noise variance used in the standard RS formulation leads to a fundamental limitation: there exists no global noise variance that simultaneously achieves strong performance at both small and large radii. To break through the global variance limitation, we propose a dual RS framework which enables input-dependent noise variances. To achieve that, we first prove that RS remains valid with input-dependent noise variances, provided the variance is locally constant around each input. Building on this result, we introduce two components: (i) a variance estimator predicts an optimal noise variance for each input, (ii) this estimated variance is then used by a standard RS classifier. The variance estimator is independently smoothed via RS to ensure local constancy, enabling flexible design. We also introduce training strategies to iteratively optimize the two components. Experiments on CIFAR-10 demonstrate that our dual RS method provides strong performance for both small and large radii-unattainable with global noise variance-while incurring only a 60% computational overhead at inference. Moreover, it outperforms prior input-dependent noise approaches across most radii, with gains at radii 0.5, 0.75, and 1.0 of 15.6%, 20.0%, and 15.7%. On ImageNet, dual RS remains effective across all radii, with advantages of 8.6%, 17.1%, and 9.1% at radii 0.5, 1.0, and 1.5. Additionally, the dual RS framework provides a routing perspective for certified robustness, improving the accuracy-robustness trade-off with off-the-shelf expert RS models.

IDER: IDempotent Experience Replay for Reliable Continual Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhanwang Liu · Yuting Li · Haoyuan Gao · Yexin Li · Linghe Kong · Lichao Sun · Weiran Huang
4 March 2026 at 13:00
arXiv:2603.00624v2 Announce Type: replace-cross Abstract: Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and shown to reduce forgetting. Furthermore, CL models deployed in mission-critical settings can benefit from uncertainty awareness by calibrating their predictions to reliably assess their confidences. However, existing uncertainty-aware continual learning methods suffer from high computational overhead and incompatibility with mainstream replay methods. To address this, we propose idempotent experience replay (IDER), a novel approach based on the idempotent property where repeated function applications yield the same output. Specifically, we first adapt the training loss to make model idempotent on current data streams. In addition, we introduce an idempotence distillation loss. We feed the output of the current model back into the old checkpoint and then minimize the distance between this reprocessed output and the original output of the current model. This yields a simple and effective new baseline for building reliable continual learners, which can be seamlessly integrated with other CL approaches. Extensive experiments on different CL benchmarks demonstrate that IDER consistently improves prediction reliability while simultaneously boosting accuracy and reducing forgetting. Our results suggest the potential of idempotence as a promising principle for deploying efficient and trustworthy continual learning systems in real-world applications.Our code is available at https://github.com/YutingLi0606/Idempotent-Continual-Learning.
Received — 25 February 2026 ⏭

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kai Ruan · Xuan Wang · Jixiang Hong · Peng Wang · Yang Liu · Hao Sun
24 February 2026 at 13:00
arXiv:2412.17596v4 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately extracting key findings from papers or generating coherent experimental procedures), existing evaluation benchmarks primarily assess performance using rich contextual inputs. We introduce LiveIdeaBench, a comprehensive benchmark evaluating LLMs' scientific idea generation by assessing divergent thinking capabilities using single-keyword prompts. Drawing from Guilford's creativity theory, our benchmark employs a dynamic panel of state-of-the-art LLMs to assess generated ideas across five key dimensions: originality, feasibility, fluency, flexibility, and clarity. Through extensive experimentation with over 40 leading models across 1,180 keywords spanning 22 scientific domains, we reveal that the scientific idea generation capabilities measured by our benchmark, are poorly predicted by standard metrics of general intelligence. Our results demonstrate that models like QwQ-32B-preview achieve creative performance comparable to top-tier models such as claude-3.7-sonnet:thinking, despite significant gaps in their general intelligence scores. These findings highlight the need for specialized evaluation benchmarks for scientific idea generation and suggest that enhancing these idea generation capabilities in LLMs may require different training strategies than those used for improving general problem-solving abilities, potentially enabling a wider range of AI tools tailored for different stages of the scientific process.

STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinhao Sun · Huaijin Zhao · Maoliang Li · Zihao Zheng · Jiayu Chen · Yun Liang · Xiang Chen
24 February 2026 at 13:00
arXiv:2601.04205v2 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence thresholds, overlooking the spatial-temporal dynamics of token confidence, causing unnecessary remasking. We propose Spatial-Temporal Token-Dynamics-Aware Responsive Remasking (STaRR), a training-free framework that dynamically adapts remasking decisions based on token confidence evolution. STaRR introduces two metrics, temporal variance and spatial deviance, to guide fine-grained, step-wise dynamic thresholding. We further introduce a step-wise dynamic thresholding strategy, further enhanced with responsiveness optimizations for scalability and robustness. Experiments show that STaRR achieves an average speedup of 4.1 and up to 8.9 while maintaining comparable accuracy.

DesignAsCode: Bridging Structural Editability and Visual Fidelity in Graphic Design Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziyuan Liu · Shizhao Sun · Danqing Huang · Yingdong Shi · Meisheng Zhang · Ji Li · Jingsong Yu · Jiang Bian
24 February 2026 at 13:00
arXiv:2602.17690v2 Announce Type: replace-cross Abstract: Graphic design generation demands a delicate balance between high visual fidelity and fine-grained structural editability. However, existing approaches typically bifurcate into either non-editable raster image synthesis or abstract layout generation devoid of visual content. Recent combinations of these two approaches attempt to bridge this gap but often suffer from rigid composition schemas and unresolvable visual dissonances (e.g., text-background conflicts) due to their inexpressive representation and open-loop nature. To address these challenges, we propose DesignAsCode, a novel framework that reimagines graphic design as a programmatic synthesis task using HTML/CSS. Specifically, we introduce a Plan-Implement-Reflect pipeline, incorporating a Semantic Planner to construct dynamic, variable-depth element hierarchies and a Visual-Aware Reflection mechanism that iteratively optimizes the code to rectify rendering artifacts. Extensive experiments demonstrate that DesignAsCode significantly outperforms state-of-the-art baselines in both structural validity and aesthetic quality. Furthermore, our code-native representation unlocks advanced capabilities, including automatic layout retargeting, complex document generation (e.g., resumes), and CSS-based animation. Our project page is available at https://liuziyuan1109.github.io/design-as-code/.
There are no more articles
❌