❌

Normal view

Received today — 7 October 2026 ⏭

SPTLC2-driven sphingolipid reprogramming of neutrophils impairs anti-tumour immunity and drives liver cancer progression

✇Oncogene - Issue - nature.com science feeds
By: Zhe Yang · Yun Wang · Jianhao Li · Zishuo Wang · Jianan Chen · Ding Zhang · Guorui Zhao · Liwen Liu · Zhibo Liu · Ning Wang · Ranran Sun
28 September 2026 at 08:00

Oncogene, Published online: 28 September 2026; doi:10.1038/s41388-026-03996-2

SPTLC2-driven sphingolipid reprogramming of neutrophils impairs anti-tumour immunity and drives liver cancer progression
Received — 10 September 2026 ⏭

MITF-SCD1 Lipid Metabolic Axis Prevents Ouabain-Induced Spiral Ganglion Neuron Ferroptosis and Hearing Loss

✇Molecular Therapy
By: Xue Wang · Fang Chen · Ziji Zhang · Man Zhang · Man Wang · Lei Chen · Anqi Suo · Xugang Zhuang · Tenghan Ling · Renjie Chai · Haibo Wang · Bo Chu · Lei Xu · Wenwen Liu
31 August 2026 at 08:00
Ouabain triggers cochlear spiral ganglion neuron (SGN) ferroptosis and hearing loss via SCD1 downregulation. MITF directly activates Scd1 transcription, and the MITF–SCD1 axis mitigates SGN ferroptosis and hearing impairment in ototoxic ouabain and cisplatin models, revealing a lipid metabolic vulnerability and therapeutic target for sensorineural hearing loss.
Received — 27 May 2026 ⏭

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Arash Akbari · Arman Akbari · Masih Eskandar · Qitao Tan · Yixiao Chen · Jingwu Luo · Bertha Pangaribuan · Liyun Zhang · Jennifer Dy · Geng Yuan · Xue Lin · Gaowen Liu · Stratis Ioannidis · Yanzhi Wang
26 May 2026 at 12:00
arXiv:2605.24011v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: (1) an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; (2) an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce OmniModel.cpp, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through OmniModel.cpp. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on $\pi_{0.5}$. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB (5.3$\times$). On the physical UR3 arm, $\pi_{0.5}$ quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5$\times$.

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity

✇cs.AI, q-bio.NC updates on arXiv.org
By: Samuel Jacob Chacko · James Hugglestone · Chashi Mahiul Islam · Xiuwen Liu
26 May 2026 at 12:00
arXiv:2605.20023v2 Announce Type: replace Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks show wide variance, with 16 of 84 tasks suffering negative deltas when Skills are introduced. The community has not yet articulated a clean mechanism for \emph{when} Skills help and when they are merely redundant overhead. We re-analyze a recently published 180-run controlled study of an MCP-grounded autonomous Capture-the-Flag (CTF) agent under four documentation conditions of increasing richness (591, 12865, 17253, and 36001 tokens) and show that these conditions correspond almost exactly to a No-Skills, Experiential-Skills, Curated-Skills, and Comprehensive-Skills ablation. In offensive cybersecurity, a domain not deeply covered by existing Skills benchmarks, the marginal benefit of Skills collapses. The spread between the no-Skills and full-Skills conditions is only 8.9~pp ($p = 0.71$, $\chi^2$; $p = 0.25$, Cochran--Armitage trend test; five of six pairwise Cohen's $h$ values fall below the $0.2$ small-effect threshold). We argue that the missing variable is \emph{environment-feedback bandwidth}. When an agent's tool layer returns strict, schema-validated, low-latency observations, the environment itself supplies the procedural correction signal that Skills are normally needed to provide. As a result, the marginal benefit of curated Skills diminishes substantially, and, in some cases (e.g., our timing side-channel setting), actively degrades performance. We articulate a falsifiable hypothesis, sketch its design implications for compound AI systems, and will release the reanalysis pipeline to support replication.

Data-driven precision: artificial intelligence redefining immunoradiotherapy in advanced pancreatic cancer

✇(Multiomics OR Omics) AND (Pancreatic)
By: Yao-Wen Liu · Xiao-Ding Men · Bin-Ru Di · Yu-Lin Lei · Li Xiang · Yu-Hao Luo
25 May 2026 at 18:00

Front Pharmacol. 2026 May 8;17:1804673. doi: 10.3389/fphar.2026.1804673. eCollection 2026.

ABSTRACT

Advanced pancreatic ductal adenocarcinoma (PDAC) remains among the most formidable challenges in oncology, driven by a profoundly immunosuppressive tumor microenvironment (TME) and pervasive resistance to systemic and local therapies. Although immune checkpoint inhibitors (ICIs) can synergize with radiotherapy (RT) in several malignancies, the clinical benefit of immunoradiotherapy (iRT) in PDAC has been modest, highlighting the limitations of population-averaged paradigms that fail to capture extensive inter- and intratumoral heterogeneity. Here, we synthesize an artificial intelligence (AI)-enabled framework to refine both the biological rationale and clinical implementation of iRT for advanced PDAC through integrative analysis of multimodal data (clinical variables, imaging, RT dose distributions, and multi-omics). We highlight advances in three domains. First, AI-based deconvolution of TME heterogeneity can delineate clinically relevant molecular subtypes and spatial immune architectures that may be therapeutically tractable. Second, AI-driven modeling can optimize spatiotemporal RT-immunotherapy interactions, informing individualized dose, fractionation, and biologically guided target definition. Third, AI-supported predictive modeling and adaptive feedback can enable response-guided treatment adjustment beyond static planning. We also discuss unresolved clinical questions and key translational barriers, including data scarcity, lack of standardization, and limited interpretability. Finally, we outline priorities for translation-prospective digital biobanks, hybrid mechanistic-data-driven modeling, and adaptive trial designs-to enable rigorous validation and clinical deployment. Collectively, these developments position AI as a catalyst to move iRT for PDAC from empiricism toward real-time, individualized precision medicine.

PMID:42181887 | PMC:PMC13194001 | DOI:10.3389/fphar.2026.1804673

Explainable multi-omics modeling for risk stratification in pancreatic ductal adenocarcinoma

✇(Multiomics OR Omics) AND (Pancreatic)
By: Bingrong Chen · Jianuo Chen · Zhen Cao · Qiyao Zhang · Shangcheng Yan · Hongtao Cao · Jia Yu · Fang Wang · Ziwen Liu
21 May 2026 at 18:00

Gland Surg. 2026 Apr 30;15(4):91. doi: 10.21037/gs-2025-396. Epub 2026 Mar 27.

ABSTRACT

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) remains one of the most lethal malignancies due to a lack of reliable tools for individualized risk stratification. A comprehensive understanding of the multi-omics landscape may uncover clinically applicable biomarkers and inform precision prognostic assessment. This study aims to establish a prognostic model directly from the complete omics landscape and extract biomarkers.

METHODS: We developed prognostic models using multi-omics data from a PDAC proteogenomic cohort comprising 75 deceased tumor samples. An independent cohort of 63 deceased PDAC cases from The Cancer Genome Atlas (TCGA)-pancreatic adenocarcinoma (PAAD) was used for external validation. Logistic regression models with least absolute shrinkage and selection operator (LASSO) regularization were constructed, and SHapley Additive exPlanations (SHAP) were applied to evaluate feature importance and identify signature genes. Model selection was based on the average area under the receiver operating characteristic curve (AUROC) across cross-validation folds. Functional validation was performed in PANC-1 cells by knockdown (KD) or overexpression (OE) of representative microRNA-, RNA-, and proteomics-derived signature genes, followed by Cell Counting Kit-8 (CCK-8) proliferation and Transwell migration assays.

RESULTS: Systematic evaluation of 120 multi-omics combinations identified a top-performing prognostic model integrating RNA, microRNA, proteomics, and mutation features. This model achieved a mean AUROC of 0.92±0.11 and accuracy of 0.87±0.01 on internal validation, and 0.99±0.00 and 0.98±0.01 on the TCGA test set. The sensitivity, specificity, precision, recall and F1 scores on the TCGA test set were 0.98±0.01, 0.97±0.02, 0.98±0.02, 0.98±0.01, 0.98±0.01, respectively. SHAP analysis revealed interpretable and clinically relevant prognostic biomarkers, many of which are implicated in immune signaling, metabolic regulation, and cell cycle control. Importantly, modulation of representative signature genes in PANC-1 cells significantly altered proliferation and migration in directions consistent with model-predicted risk associations.

CONCLUSIONS: Our findings demonstrate that explainable multi-omics machine learning frameworks can identify robust prognostic biomarkers and achieve highly accurate survival prediction in PDAC. Functional validation further supports the biological relevance of these signatures, underscoring their translational potential for personalized risk assessment.

PMID:42164702 | PMC:PMC13184197 | DOI:10.21037/gs-2025-396

A review of organoid-immune co-culture platforms to model the immune microenvironment of hepatocellular carcinoma and guide immunotherapy

✇Omics in Hepatocellular
By: Wen-Wen Liu · Xi-Shuai Xie · Xiao-Jun Yang
21 May 2026 at 18:00

J Transl Med. 2026 May 20. doi: 10.1186/s12967-026-08278-9. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is characterized by a highly immunosuppressive and heterogeneous tumor microenvironment that limits the effectiveness of current immunotherapies. Conventional two-dimensional cultures and animal models fail to fully capture patient-specific tumor-immune interactions, creating an urgent need for more physiologically relevant platforms.

MAIN BODY: This review summarizes recent advances in co-culture systems integrating patient-derived HCC organoids with defined immune cell populations to reconstruct essential features of the tumor microenvironment. We describe strategies for organoid establishment and validation, outline immune cell integration approaches, and compare static three-dimensional cultures, microfluidic organ-on-chip systems, and bioengineered multicellular platforms. We further highlight key tumor-immune interaction mechanisms that have been functionally interrogated in these systems, including immune checkpoint-mediated T-cell dysfunction, adenosine-driven metabolic suppression, and chemokine-regulated immune recruitment. Importantly, we critically evaluate current limitations, including immune cell exhaustion artifacts, lack of stromal and vascular complexity, and variability across protocols, which may affect the reproducibility and translational interpretation of these models. While emerging studies suggest potential for predicting immunotherapy responses, robust clinical validation in HCC remains limited.

CONCLUSIONS: Organoid-immune co-culture platforms represent an emerging translational framework that bridges mechanistic tumor immunology with functional precision oncology. With improved standardization and integration of multicellular bioengineering and multi-omics technologies, these systems have strong potential to guide personalized immunotherapy strategies, although further clinical validation is required.

PMID:42163357 | DOI:10.1186/s12967-026-08278-9

Spatial multi-omics defines cancer-associated fibroblasts subtype gradients driving metabolic support and immune remodeling in pancreatic ductal adenocarcinoma

✇(Multiomics OR Omics) AND (Pancreatic)
By: Qiyao Zhang · Zhen Cao · Shangcheng Yan · Bingrong Chen · Bohan Huang · Ziwen Liu · Yupei Zhao
17 May 2026 at 18:00

Cancer Lett. 2026 May 16;653:218585. doi: 10.1016/j.canlet.2026.218585. Online ahead of print.

ABSTRACT

Pancreatic ductal adenocarcinoma is characterized by a fibrotic and metabolically active tumor microenvironment where cancer-associated fibroblasts (CAFs) mediate metabolic crosstalk, extracellular matrix (ECM) remodeling, and immune regulation. However, the metabolic and spatial heterogeneity of CAFs remains incompletely understood. We integrated spatial transcriptomics and spatial metabolomics data from PDAC tissues and performed SpatialGlue-based multimodal clustering to define CAF subtypes. To characterize metabolic communication, we developed an optimal transport (OT)-based metabolic inference framework to quantitatively model metabolite association between CAFs and tumor cells. Subtype-specific features were independently validated using an independent spatial metabolomics cohort and multiplex immunofluorescence (mIHC) staining. Furthermore, these features were correlated with clinical outcomes via TCGA-PAAD deconvolution. Spatial multi-omics integration identified three robust CAF subtypes with distinct signatures. OT analysis revealed differential metabolic interactions: CAF_C0 mediated amino acid/peptide transfer, CAF_C1 was the primary source of lipids, while CAF_C2 exhibited limited metabolic association but stronger immune and ECM signaling activity. Deconvolution confirmed that CAF composition was strongly associated with prognosis; CAF_C2 enrichment predicted poorer survival and gemcitabine resistance, whereas a higher CAF_C0/CAF_C1 balance correlated with improved outcomes. By combining spatial multi-omics with OT-based modeling, this study delineates metabolically and spatially distinct CAF states with clinical relevance. Our findings suggest CAFs act as both metabolic donors and immune-ECM regulators, providing new insights into stromal reprogramming and potential subtype-specific therapeutic targets in PDAC.

PMID:42144098 | DOI:10.1016/j.canlet.2026.218585

Spatial multi-omics technologies in gastric cancer: applications and advances

✇Omics in Gastric
By: Qianqian Liu · Haowen Liu · Jing Lv · Jiashuo Li · Guangtan Du · Wensheng Qiu · Shasha Wang
30 April 2026 at 18:00

Front Immunol. 2026 Apr 14;17:1767512. doi: 10.3389/fimmu.2026.1767512. eCollection 2026.

ABSTRACT

Gastric cancer (GC) is plagued by profound intratumoral heterogeneity and a complex tumor microenvironment (TME), which are the core obstacles to precise diagnosis and treatment. Conventional bulk multi-omics technologies average molecular signals across tissues, thus masking cellular heterogeneity; single-cell multi-omics resolves cellular diversity but dissociates cells from their native spatial context, leading to the loss of critical information on intercellular crosstalk and molecular spatial distribution. These limitations result in an incomplete understanding of GC pathogenesis and TME regulatory networks. Spatial multi-omics technologies, integrating genomics, transcriptomics, proteomics, and metabolomics with high-resolution spatial localization, address these key scientific problems by preserving the native tissue architecture and elucidating the spatiotemporal dynamics of molecular and cellular events in GC. This review systematically synthesizes the latest advances in the application of four major spatial multi-omics modalities in GC research over the past 15 years, with a critical evaluation of the technical performance, methodological shortcomings, and clinical translation potential of existing studies. Unlike previous reviews that only summarize research findings, this work uniquely integrates technical principles, mechanistic discoveries, and clinical translation of spatial multi-omics in GC, deeply analyzes the practical barriers to clinical application, and systematically elaborates the integration of spatial multi-omics with artificial intelligence (AI). We also identify unresolved challenges in the field and propose future development directions, providing a comprehensive and in-depth reference for the advancement of GC precision medicine based on spatial multi-omics.

PMID:42058209 | PMC:PMC13120937 | DOI:10.3389/fimmu.2026.1767512

Received — 8 April 2026 ⏭

Agentization of Digital Assets for the Agentic Web: Concepts, Techniques, and Benchmark

✇cs.AI, q-bio.NC updates on arXiv.org
By: Linyao Chen · Bo Huang · Qinlao Zhao · Shuai Shao · Zhi Han · Zicai Cui · Ziheng Zhang · Guangtao Zeng · Wenzheng Tang · Yikun Wang · Yuanjian Zhou · Zimian Peng · Yong Yu · Weiwen Liu · Hiroki Kobayashi · Weinan Zhang
7 April 2026 at 12:00
arXiv:2604.04226v1 Announce Type: cross Abstract: Agentic Web, as a new paradigm that redefines the internet through autonomous, goal-driven interactions, plays an important role in group intelligence. As the foundational semantic primitives of the Agentic Web, digital assets encapsulate interactive web elements into agents, which expand the capacities and coverage of agents in agentic web. The lack of automated methodologies for agent generation limits the wider usage of digital assets and the advancement of the Agentic Web. In this paper, we first formalize these challenges by strictly defining the A2A-Agentization process, decomposing it into critical stages and identifying key technical hurdles on top of the A2A protocol. Based on this framework, we develop an Agentization Agent to agentize digital assets for the Agentic Web. To rigorously evaluate this capability, we propose A2A-Agentization Bench, the first benchmark explicitly designed to evaluate agentization quality in terms of fidelity and interoperability. Our experiments demonstrate that our approach effectively activates the functional capabilities of digital assets and enables interoperable A2A multi-agent collaboration. We believe this work will further facilitate scalable and standardized integration of digital assets into the Agentic Web ecosystem.

Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bowen Liu · Zhi Wu · Runquan Xie · Zhanhui Kang · Jia Li
7 April 2026 at 12:00
arXiv:2602.13218v2 Announce Type: replace Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) is bottlenecked by data: existing synthesis pipelines rely on expert-written code or fixed templates, confining growth to instance-level perturbations. We shift the evolvable unit from problem instances to task-family specifications. SSLogic is an agentic meta-synthesis framework in which LLM agents iteratively author and refine executable Generator-Validator pairs inside a closed Generate-Validate-Refine loop, producing families with new rules and difficulty gradients rather than parameter variations of old ones. A Multi-Gate Validation Protocol -- multi-strategy consensus plus Adversarial Blind Review, where independent agents solve each instance by writing and executing code -- filters ill-posed tasks before they enter training. Starting from 400 seed families, two evolution rounds yield 953 families and 21,389 verifiable instances. Three converging comparisons (step-matched, token-matched, and size-controlled on external Enigmata data) consistently show higher training utility of evolved data, with gains of SynLogic +5.2, AIME25 +3.0, and BBH +5.5 on Enigmata. Fine-grained KORBench evaluation reveals selective improvements in logic (+13.2%) and operation (+9.6%), linking structural evolution to downstream gains. Code: https://github.com/AdAstraAbyssoque/Scaling-the-Scaling-Logic
Received — 4 April 2026 ⏭

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jun Liu · Pu Zhao · Zhenglun Kong · Xuan Shen · Peiyan Dong · Fan Yang · Lin Cui · Hao Tang · Geng Yuan · Wei Niu · Wenbin Zhang · Xue Lin · Gaowen Liu · Yanzhi Wang · Dong Huang
3 April 2026 at 12:00
arXiv:2603.16673v3 Announce Type: replace-cross Abstract: Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoning introduces substantial computational latency and resource overhead, which can interrupt action execution and reduce system reliability. Excessive reasoning may delay actions, while insufficient reasoning often leads to incorrect decisions and task failures. This raises a fundamental question for embodied agents: when should the agent reason, and when should it act? In this work, we propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents. Rather than learning low-level control policies, RARRL learns a high-level orchestration policy that operates at the agent's decision-making layer. This policy enables the agent to adaptively determine whether to invoke reasoning, which reasoning role to employ, and how much computational budget to allocate based on current observations, execution history, and remaining resources. Extensive experiments, including evaluations with empirical latency profiles derived from the ALFRED benchmark, show that RARRL consistently improves task success rates while reducing execution latency and enhancing robustness compared with fixed or heuristic reasoning strategies. These results demonstrate that adaptive reasoning control is essential for building reliable and efficient embodied robotic agents.
Received — 2 April 2026 ⏭

UniAI-GraphRAG: Synergizing Ontology-Guided Extraction, Multi-Dimensional Clustering, and Dual-Channel Fusion for Robust Multi-Hop Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jie Wang · Honghua Huang · Xi Ge · Jianhui Su · Wen Liu · Shiguo Lian
1 April 2026 at 12:00
arXiv:2603.25152v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge organization, they still have limitations in cross-industry adaptability, community report integrity, and retrieval performance. This paper proposes UniAI-GraphRAG, an enhanced framework built upon open-source GraphRAG. The framework introduces three core innovations: (1) Ontology-Guided Knowledge Extraction that uses predefined Schema to guide LLMs in accurately identifying domain-specific entities and relations; (2) Multi-Dimensional Community Clustering Strategy that improves community completeness through alignment completion, attribute-based clustering, and multi-hop relationship clustering; (3) Dual-Channel Graph Retrieval Fusion that balances QA accuracy and performance through hybrid graph and community retrieval. Evaluation results on MultiHopRAG benchmark show that UniAI-GraphRAG outperforms mainstream open source solutions (e.g.LightRAG) in comprehensive F1 scores, particularly in inference and temporal queries. The code is available at https://github.com/UnicomAI/wanwu/tree/main/rag/rag_open_source/rag_core/graph.
Received — 26 March 2026 ⏭

Ran Score: a LLM-based Evaluation Score for Radiology Report Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ran Zhang · Yucong Lin · Zhaoli Su · Bowen Liu · Danni Ai · Tianyu Fu · Deqiang Xiao · Jingfan Fan · Yuanyuan Wang · Mingwei Gao · Yuwan Hu · Shuya Gao · Jingtao Li · Jian Yang · Hong Song · Hongliang Sun
25 March 2026 at 12:00
arXiv:2603.22935v1 Announce Type: new Abstract: Chest X-ray report generation and automated evaluation are limited by poor recognition of low-prevalence abnormalities and inadequate handling of clinically important language, including negation and ambiguity. We develop a clinician-guided framework combining human expertise and large language models for multi-label finding extraction from free-text chest X-ray reports and use it to define Ran Score, a finding-level metric for report evaluation. Using three non-overlapping MIMIC-CXR-EN cohorts from a public chest X-ray dataset and an independent ChestX-CN validation cohort, we optimize prompts, establish radiologist-derived reference labels and evaluate report generation models. The optimized framework improves the macro-averaged score from 0.753 to 0.956 on the MIMIC-CXR-EN development cohort, exceeds the CheXbert benchmark by 15.7 percentage points on directly comparable labels, and shows robust generalization on the ChestX-CN validation cohort. Here we show that clinician-guided prompt optimization improves agreement with a radiologist-derived reference standard and that Ran Score enables finding-level evaluation of report fidelity, particularly for low-prevalence abnormalities.

STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving

✇cs.AI, q-bio.NC updates on arXiv.org
By: James Hugglestone · Samuel Jacob Chacko · Dawson Stoller · Ryan Schmidt · Xiuwen Liu
25 March 2026 at 12:00
arXiv:2603.22577v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity operations. Existing research often relies on static benchmarks that fail to capture the dynamic nature of real-world vulnerabilities. In this work, we introduce STRIATUM-CTF (A Search-based Test-time Reasoning Inference Agent for Tactical Utility Maximization in Cybersecurity), a modular agentic framework built upon the Model Context Protocol (MCP). By standardizing tool interfaces for system introspection, decompilation, and runtime debugging, STRIATUM-CTF enables the agent to maintain a coherent context window across extended exploit trajectories. We validate this approach not merely on synthetic datasets, but in a live competitive environment. Our system participated in a university-hosted Capture-the-Flag (CTF) competition in late 2025, where it operated autonomously to identify and exploit vulnerabilities in real-time. STRIATUM-CTF secured First Place, outperforming 21 human teams and demonstrating strong adaptability in a dynamic problem-solving setting. We analyze the agent's decision-making logs to show how MCP-based tool abstraction significantly reduces hallucination compared to naive prompting strategies. These results suggest that standardized context protocols are a critical path toward robust autonomous cyber-reasoning systems.

Boosting foundation models for rare eye disease diagnosis via a multimodal text-to-image generative framework

✇npj Digital Medicine
By: Ruoyu Chen · Weiyi Zhang · Bowen Liu · Xinyuan Wu · Xiaolan Chen · Pusheng Xu · Shunming Liu · Mingguang He · Danli Shi
24 March 2026 at 08:00

npj Digital Medicine, Published online: 24 March 2026; doi:10.1038/s41746-026-02560-2

Boosting foundation models for rare eye disease diagnosis via a multimodal text-to-image generative framework
Received — 14 March 2026 ⏭

The Effects of Digital Health Interventions on Motor Symptoms, Nonmotor Symptoms, and Quality of Life in Patients With Parkinson Disease: Systematic Review and Meta-Analysis of Randomized Controlled Trials

✇Journal of Medical Internet Research
By: Ruwen Liu · Sirui Zhang · Yi Xiao · Yangfan Cheng · Huifang Shang
13 March 2026 at 04:30
Background: Parkinson disease (PD) is a progressive neurodegenerative disorder with increasing global prevalence, necessitating innovative management. Digital health interventions (DHIs) offer potential advantages for PD care; yet, a comprehensive systematic review and synthesis across all DHI types and core outcomes is still lacking. Objective: This review aimed to assess the effectiveness of DHIs for improving motor symptoms, nonmotor symptoms, and quality of life in patients with PD and to summarize the reach, uptake, and feasibility. Methods: We searched PubMed, Ovid Embase, Web of Science, CINAHL, Cochrane Central Register of Controlled Trials, and APA PsycINFO up to November 2025. Pooled standardized mean differences (SMDs) were calculated using random-effects models. We calculated 95% prediction intervals (PIs) to estimate the true effects. The revised Cochrane Risk of Bias 2 tool was used to assess risk of bias. Heterogeneity was assessed using I2, τ2, and 95% PI. Subgroup analyses, meta-regression, and sensitivity analyses were conducted to address heterogeneity and potential bias. The quality of evidence was assessed using GRADE (Grading of Recommendations Assessment, Development, and Evaluation). Results: The review included 112 randomized controlled trials involving 5594 participants. Significant postintervention improvements were identified in motor symptoms (SMD=–0.39, 95% CI –0.60 to –0.18, 95% PI –1.75 to 0.99; I2=80.3%) and overall nonmotor symptoms (SMD=–0.26, 95% CI –0.49 to –0.03, 95% PI –0.56 to 0.03; I2=13.8%), including cognitive function (SMD=0.47, 95% CI 0.22 to 0.72, 95% PI –0.41 to 1.35; I2=63.5%) and psychiatric symptoms (SMD=–0.42, 95% CI –0.74 to –0.09, 95% PI –1.82 to –0.99; I2=85.4%); however, there was no significant enhancement in quality of life (SMD=–0.19, 95% CI –0.47 to 0.09, 95% PI –1.50 to 1.12; I2=81.2%). The certainty of evidence was very low for quality of life, motor, and psychiatric symptoms and low for cognitive function and overall nonmotor symptoms. Improvements in motor symptoms and cognitive function remained stable at follow-up. Meta-regression analysis indicated that age, percentage of female participants, and supervision mode were possible sources of heterogeneity. Overall, 94 studies reported reach (median 37.5%), 38 reported fidelity (95.7%), and 105 reported dropout rates (9.1%). Conclusions: In contrast to previous reviews focused on single technologies or outcomes, this review provided the first comprehensive synthesis across all DHI types on multiple outcomes and indicated their potential as nonpharmacological interventions for PD management. However, current evidence is of low to very low certainty, and wide 95% PIs, together with high risk of bias and substantial heterogeneity, indicate considerable uncertainty regarding the true effect in future implementations. Therefore, findings should be interpreted with caution. These findings provide integrated evidence to guide the design and prioritization of future research. The results have important real-world implications, supporting cautious implementation while underscoring the need for more robust trials, particularly in resource-limited settings. Trial Registration: PROSPERO CRD42023492123; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023492123
Received — 11 March 2026 ⏭

Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kai Cheng · Hao Wang · Wei Guo · Weiwen Liu · Yong Liu · Yawen Li · Enhong Chen
10 March 2026 at 12:00
arXiv:2603.07107v1 Announce Type: cross Abstract: Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two key challenges: (1) an inherent conflict between achieving high generation quality and ensuring low-latency inference, making it difficult to balance the two, and (2) insufficient interaction between user and item features in existing methods. To address these challenges, we propose a novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking. In this framework, the teacher model adopts a semi-autoregressive generator to balance generation quality and efficiency, while its ranking knowledge is distilled online into a lightweight scoring network during joint training, enabling real-time and efficient inference. Furthermore, we propose a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items. Extensive experiments conducted on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency.
Received — 5 March 2026 ⏭

Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bowen Yu · Maolin Wang · Sheng Zhang · Binhao Wang · Yi Wen · Jingtong Gao · Bowen Liu · Zimo Zhao · Wanyu Wang · Xiangyu Zhao
4 March 2026 at 13:00
arXiv:2602.17686v2 Announce Type: replace-cross Abstract: Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce. Existing approaches either compress reasoning into single-step, losing the interpretability that makes CoT valuable. We present a three-stage curriculum learning framework that addresses this capacity mismatch through progressive skill acquisition. First, we establish structural understanding via masked shuffled reconstruction. Second, we apply Group Relative Policy Optimization (GRPO) on masked completion tasks, enabling the model to discover its own balance between accuracy and brevity. Third, we identify persistent failure cases and guide the student to internalize teacher knowledge through targeted rewriting, again optimized with GRPO. Experiments on GSM8K demonstrate that our approach enables Qwen2.5-3B-Base to achieve an 11.29 percent accuracy improvement while reducing output length by 27.4 percent, surpassing both instruction-tuned variants and prior distillation methods.
Received — 25 February 2026 ⏭

CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hanwen Liu · Saierdaer Yusuyin · Hao Huang · Zhijian Ou
24 February 2026 at 13:00
arXiv:2602.19574v1 Announce Type: cross Abstract: Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-streaming synthesis. High-quality dual-streaming TTS depends on accurate text--speech alignment and well-designed training sequences that balance synthesis quality and latency. Prior work often relies on GMM-HMM based forced-alignment toolkits (e.g., MFA), which are pipeline-heavy and less flexible than neural aligners; fixed-ratio interleaving of text and speech tokens struggles to capture text--speech alignment regularities. We propose CTC-TTS, which replaces MFA with a CTC based aligner and introduces a bi-word based interleaving strategy. Two variants are designed: CTC-TTS-L (token concatenation along the sequence length) for higher quality and CTC-TTS-F (embedding stacking along the feature dimension) for lower latency. Experiments show that CTC-TTS outperforms fixed-ratio interleaving and MFA-based baselines on streaming synthesis and zero-shot tasks. Speech samples are available at https://ctctts.github.io/.
There are no more articles
❌