❌

Normal view

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.

Integration of multi-omics and machine learning to identify core genes in PANoptosisof lung adenocarcinoma and their mechanisms in the tumor microenvironment and therapeutic potential

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Zhi Chen · Xuehua Deng · Yiyong Yu · Ting Zhang · Cui Liu
5 April 2026 at 18:00

Naunyn Schmiedebergs Arch Pharmacol. 2026 Apr 5. doi: 10.1007/s00210-026-05251-7. Online ahead of print.

ABSTRACT

Lung adenocarcinoma (LUAD) is one of the leading causes of cancer-related deaths worldwide, and its complex tumor microenvironment (TME) is a key barrier to treatment. PANoptosis is a novel programmed cell death mechanism that integrates features of pyroptosis, apoptosis, and necroptosis. However, its core regulatory network and cell specific role in LUAD are still unclear. This study integrated three LUAD transcriptome datasets, screened differentially expressed genes through bioinformatics analysis, and intersected with PANoptosis-related genes to construct a protein interaction network, using a combination of 113 machine learning algorithms to screen and validate core genes and using CIBERSORT and single-cell transcriptome data to analyze the spatial expression characteristics of immune cell infiltration and core genes. Finally, the intervention mechanism of core targets and ginsenosides was validated through molecular docking, immunohistochemistry, and cell experiments (CCK-8, Western Blot). Six core genes of LUAD PANoptosis, including IRF1, NLRP3, CASP1, TIMP1, S100A8, and TLR4, were identified in the study. Single-cell analysis revealed that these genes were significantly enriched in M2 macrophages. Functional enrichment indicates that they jointly regulate death- and inflammation-related pathways such as NF-κB signaling and NOD-like receptor signaling. In vitro experiments have confirmed that ginsenosides can induce PANoptosis, promote tumor cell death, or inhibit LUAD cell proliferation by upregulating the ZBP1/AIM2/RIPK3/CASP1 death complex and inhibiting the TLR4/NLRP3 survival signaling axis. This study systematically revealed a PANoptosis core gene network centered on M2 macrophages in LUAD, elucidating a new mechanism by which ginsenosides induce integrated cell death by regulating this network. This provides new potential targets and theoretical basis for the immunotherapy of LUAD and the development of traditional Chinese medicine monomers.

PMID:41935997 | DOI:10.1007/s00210-026-05251-7

Integration of multi-omics and machine learning to identify core genes in PANoptosisof lung adenocarcinoma and their mechanisms in the tumor microenvironment and therapeutic potential

✇Omics In Lung
By: Zhi Chen · Xuehua Deng · Yiyong Yu · Ting Zhang · Cui Liu
5 April 2026 at 18:00

Naunyn Schmiedebergs Arch Pharmacol. 2026 Apr 5. doi: 10.1007/s00210-026-05251-7. Online ahead of print.

ABSTRACT

Lung adenocarcinoma (LUAD) is one of the leading causes of cancer-related deaths worldwide, and its complex tumor microenvironment (TME) is a key barrier to treatment. PANoptosis is a novel programmed cell death mechanism that integrates features of pyroptosis, apoptosis, and necroptosis. However, its core regulatory network and cell specific role in LUAD are still unclear. This study integrated three LUAD transcriptome datasets, screened differentially expressed genes through bioinformatics analysis, and intersected with PANoptosis-related genes to construct a protein interaction network, using a combination of 113 machine learning algorithms to screen and validate core genes and using CIBERSORT and single-cell transcriptome data to analyze the spatial expression characteristics of immune cell infiltration and core genes. Finally, the intervention mechanism of core targets and ginsenosides was validated through molecular docking, immunohistochemistry, and cell experiments (CCK-8, Western Blot). Six core genes of LUAD PANoptosis, including IRF1, NLRP3, CASP1, TIMP1, S100A8, and TLR4, were identified in the study. Single-cell analysis revealed that these genes were significantly enriched in M2 macrophages. Functional enrichment indicates that they jointly regulate death- and inflammation-related pathways such as NF-κB signaling and NOD-like receptor signaling. In vitro experiments have confirmed that ginsenosides can induce PANoptosis, promote tumor cell death, or inhibit LUAD cell proliferation by upregulating the ZBP1/AIM2/RIPK3/CASP1 death complex and inhibiting the TLR4/NLRP3 survival signaling axis. This study systematically revealed a PANoptosis core gene network centered on M2 macrophages in LUAD, elucidating a new mechanism by which ginsenosides induce integrated cell death by regulating this network. This provides new potential targets and theoretical basis for the immunotherapy of LUAD and the development of traditional Chinese medicine monomers.

PMID:41935997 | DOI:10.1007/s00210-026-05251-7

Received — 17 March 2026 ⏭

CarPLAN: Context-Adaptive and Robust Planning with Dynamic Scene Awareness for Autonomous Driving

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junyong Yun · Jungho Kim · ByungHyun Lee · Dongyoung Lee · Sehwan Choi · Seunghyeop Nam · Kichun Jo · Jun Won Choi
16 March 2026 at 12:00
arXiv:2603.12607v1 Announce Type: cross Abstract: Imitation learning (IL) is widely used for motion planning in autonomous driving due to its data efficiency and access to real-world driving data. For safe and robust real-world driving, IL-based planning requires capturing the complex driving contexts inherent in real-world data and enabling context-adaptive decision-making, rather than relying solely on expert trajectory imitation. In this paper, we propose CarPLAN, a novel IL-based motion planning framework that explicitly enhances driving context understanding and enables adaptive planning across diverse traffic scenarios. Our contributions are twofold: We introduce Displacement-Aware Predictive Encoding (DPE) to improve the model's spatial awareness by predicting future displacement vectors between the Autonomous Vehicle (AV) and surrounding scene elements. This allows the planner to account for relational spacing when generating trajectories. In addition to the standard imitation loss, we incorporate an augmented loss term that captures displacement prediction errors, ensuring planning decisions consider relative distances from other agents. To improve the model's ability to handle diverse driving contexts, we propose Context-Adaptive Multi-Expert Decoder (CMD), which leverages the Mixture of Experts (MoE) framework. CMD dynamically selects the most suitable expert decoders based on scene structure at each Transformer layer, enabling adaptive and context-aware planning in dynamic environments. We evaluate CarPLAN on the nuPlan benchmark and demonstrate state-of-the-art performance across all closed-loop simulation metrics. In particular, CarPLAN exhibits robust performance on challenging scenarios such as Test14-Hard, validating its effectiveness in complex driving conditions. Additional experiments on the Waymax benchmark further demonstrate its generalization capability across different benchmark settings.
Received — 5 March 2026 ⏭

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jaemin Son · Sujin Choi · Inyong Yun
5 March 2026 at 13:00
arXiv:2509.06415v2 Announce Type: replace-cross Abstract: Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning framework that filters out non-informative background regions from document images prior to VLM processing. A binary patch-level classifier removes non-text areas, and a max-pooling refinement step recovers fragmented text regions to enhance spatial coherence. Experiments on real-world document datasets demonstrate that our approach substantially lowers computational costs, while maintaining comparable accuracy.
There are no more articles
❌