❌

Normal view

Received — 8 April 2026 ⏭

TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingbin You · Zehao Li · Hao Jiang · Xinzhu Ma · Shuqin Gao · Honglong Zhao · Congcong Zheng · Tianlu Mao · Feng Dai · Yucheng Zhang · Zhaoqi Wang
7 April 2026 at 12:00
arXiv:2604.03309v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in suboptimal segmentation. To address these limitations, we introduce TreeGaussian, a tree-guided cascaded contrastive learning framework that explicitly models hierarchical semantic relationships and reduces redundancy in contrastive supervision. By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies. In addition, we propose a two-stage cascaded contrastive learning strategy that progressively refines feature representations from global to local, mitigating saturation and stabilizing training. A Consistent Segmentation Detection (CSD) mechanism and a graph-based denoising module are further introduced to align segmentation modes across views while suppressing unstable Gaussian points, enhancing segmentation consistency and quality. Extensive experiments, including open-vocabulary 3D object selection, 3D point cloud understanding, and ablation studies, demonstrate the effectiveness and robustness of our approach.

DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ke Li · Maoliang Li · Jialiang Chen · Jiayu Chen · Zihao Zheng · Shaoqi Wang · Xiang Chen
7 April 2026 at 12:00
arXiv:2604.04875v1 Announce Type: cross Abstract: Video mashup creation represents a complex video editing paradigm that recomposes existing footage to craft engaging audio-visual experiences, demanding intricate orchestration across semantic, visual, and auditory dimensions and multiple levels. However, existing automated editing frameworks often overlook the cross-level multimodal orchestration to achieve professional-grade fluidity, resulting in disjointed sequences with abrupt visual transitions and musical misalignment. To address this, we formulate video mashup creation as a Multimodal Coherency Satisfaction Problem (MMCSP) and propose the DIRECT framework. Simulating a professional production pipeline, our hierarchical multi-agent framework decomposes the challenge into three cascade levels: the Screenwriter for source-aware global structural anchoring, the Director for instantiating adaptive editing intent and guidance, and the Editor for intent-guided shot sequence editing with fine-grained optimization. We further introduce Mashup-Bench, a comprehensive benchmark with tailored metrics for visual continuity and auditory alignment. Extensive experiments demonstrate that DIRECT significantly outperforms state-of-the-art baselines in both objective metrics and human subjective evaluation. Project page and code: https://github.com/AK-DREAM/DIRECT

Multi-omics integration and machine learning reveal gut-immune signatures in idiopathic pulmonary fibrosis: insights from bulk RNA-seq, single-cell profiles, spatial transcriptomics, and experimental validation

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Zhengyu Hu · Jiaqi Wang · Jialin Yu · Zheqing Hu · Jing Xue · Zhanbing Ma · Miaomiao Nian · Ruixin Qi · Tingting Zhao · Xia Cao · Hongxia Xin · Xiuyan Wang · Guilan Yang · Zhenzhen Gui · Xiaoming Liu · Juan Chen
6 April 2026 at 18:00

Front Immunol. 2026 Mar 19;17:1730289. doi: 10.3389/fimmu.2026.1730289. eCollection 2026.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive, fatal lung disease with limited treatment options and a poor prognosis. Recent studies suggest a critical role for the gut-immune-lung axis in IPF, yet the underlying molecular mechanisms remain unclear.

METHODS: The current study performed in silico multi-omics integration of publicly available datasets, including bulk RNA-seq, single-cell and spatial transcriptomics, as well as peripheral blood multi-omics data to uncover key molecular signatures in IPF. Furthermore, machine learning techniques were utilized to identify core genes, whereas functional analyses and Mendelian randomization were conducted to evaluate the causal relationships among gut microbiota, immune cells, and IPF. Additionally, experimental validation using qPCR and ELISA assays was conducted in vitro, in vivo, and in patient plasma to confirm the expression patterns of key genes.

RESULTS: Across integrated public bulk, single-cell, spatial, and blood multi-omics, CXCL13, IL33, TLR4, and IGF1 were identified as core IPF genes consistently linked to immune infiltration and fibrotic remodeling. Deconvolution, scRNA-seq, and spatial mapping localized their dysregulation to fibroblasts and immune compartments (notably B-cell, macrophage, and mast-cell axes), highlighting fibroblast-immune crosstalk in fibrotic foci. A four-gene model robustly distinguished IPF from controls across cohorts. Mendelian randomization supported a gut-immune-lung axis, indicating causal effects of specific gut taxa on IPF risk via immune phenotypes. qPCR/ELISA in TGF-β1-stimulated fibroblasts, bleomycin mouse lungs, and patient plasma corroborated upregulation of IL33, CXCL13, IGF1 and downregulation of TLR4. Drug-signature reversal nominated cucurbitacin I and temsirolimus; molecular docking was performed as a preliminary in silico, computer-simulation-based assessment of potential ligand-protein interactions between these compounds and the four core targets.

CONCLUSION: This study provides new insights into the importance of gut-immune-lung axis in IPF and identifies CXCL13, IL33, TLR4, and IGF1 as diagnostic signatures and therapeutic targets. By integrating public multi-omics resources with experimental validation, our findings offer a foundation for future diagnostic and treatment strategies aimed at modulating the gut microbiota and immune system in IPF.

PMID:41939867 | PMC:PMC13043422 | DOI:10.3389/fimmu.2026.1730289

Multi-omics integration and machine learning reveal gut-immune signatures in idiopathic pulmonary fibrosis: insights from bulk RNA-seq, single-cell profiles, spatial transcriptomics, and experimental validation

✇Omics In Lung
By: Zhengyu Hu · Jiaqi Wang · Jialin Yu · Zheqing Hu · Jing Xue · Zhanbing Ma · Miaomiao Nian · Ruixin Qi · Tingting Zhao · Xia Cao · Hongxia Xin · Xiuyan Wang · Guilan Yang · Zhenzhen Gui · Xiaoming Liu · Juan Chen
6 April 2026 at 18:00

Front Immunol. 2026 Mar 19;17:1730289. doi: 10.3389/fimmu.2026.1730289. eCollection 2026.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive, fatal lung disease with limited treatment options and a poor prognosis. Recent studies suggest a critical role for the gut-immune-lung axis in IPF, yet the underlying molecular mechanisms remain unclear.

METHODS: The current study performed in silico multi-omics integration of publicly available datasets, including bulk RNA-seq, single-cell and spatial transcriptomics, as well as peripheral blood multi-omics data to uncover key molecular signatures in IPF. Furthermore, machine learning techniques were utilized to identify core genes, whereas functional analyses and Mendelian randomization were conducted to evaluate the causal relationships among gut microbiota, immune cells, and IPF. Additionally, experimental validation using qPCR and ELISA assays was conducted in vitro, in vivo, and in patient plasma to confirm the expression patterns of key genes.

RESULTS: Across integrated public bulk, single-cell, spatial, and blood multi-omics, CXCL13, IL33, TLR4, and IGF1 were identified as core IPF genes consistently linked to immune infiltration and fibrotic remodeling. Deconvolution, scRNA-seq, and spatial mapping localized their dysregulation to fibroblasts and immune compartments (notably B-cell, macrophage, and mast-cell axes), highlighting fibroblast-immune crosstalk in fibrotic foci. A four-gene model robustly distinguished IPF from controls across cohorts. Mendelian randomization supported a gut-immune-lung axis, indicating causal effects of specific gut taxa on IPF risk via immune phenotypes. qPCR/ELISA in TGF-β1-stimulated fibroblasts, bleomycin mouse lungs, and patient plasma corroborated upregulation of IL33, CXCL13, IGF1 and downregulation of TLR4. Drug-signature reversal nominated cucurbitacin I and temsirolimus; molecular docking was performed as a preliminary in silico, computer-simulation-based assessment of potential ligand-protein interactions between these compounds and the four core targets.

CONCLUSION: This study provides new insights into the importance of gut-immune-lung axis in IPF and identifies CXCL13, IL33, TLR4, and IGF1 as diagnostic signatures and therapeutic targets. By integrating public multi-omics resources with experimental validation, our findings offer a foundation for future diagnostic and treatment strategies aimed at modulating the gut microbiota and immune system in IPF.

PMID:41939867 | PMC:PMC13043422 | DOI:10.3389/fimmu.2026.1730289

Received — 4 April 2026 ⏭

SenseMath: Do LLMs Have Number Sense? Evaluating Shortcut Use, Judgment, and Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haomin Zhuang · Xiangqi Wang · Yili Shen · Ying Cheng · Xiangliang Zhang
3 April 2026 at 12:00
arXiv:2604.01988v1 Announce Type: new Abstract: Large language models often default to step-by-step computation even when efficient numerical shortcuts are available. This raises a basic question: do they exhibit number sense in a human-like behavioral sense, i.e., the ability to recognize numerical structure, apply shortcuts when appropriate, and avoid them when they are not? We introduce SenseMath, a controlled benchmark for evaluating structure-sensitive numerical reasoning in LLMs. SenseMath contains 4,800 items spanning eight shortcut categories and four digit scales, with matched strong-shortcut, weak-shortcut, and control variants. It supports three evaluation settings of increasing cognitive demand: Shortcut Use (whether models can apply shortcuts on shortcut-amenable problems); Applicability Judgment (whether they can recognize when a shortcut is appropriate or misleading); and Problem Generation (whether they can generate new problem items that correctly admit a given type of shortcut). Our evaluation across five LLMs, ranging from GPT-4o-mini to Llama-3.1-8B, shows a consistent pattern: when explicitly prompted, models readily adopt shortcut strategies and achieve substantial accuracy gains on shortcut-amenable items (up to 15%), yet under standard chain-of-thought prompting they spontaneously employ such strategies in fewer than 40% of cases, even when they demonstrably possess the requisite capability. Moreover, this competence is confined to the Use level; models systematically over-generalise shortcuts to problems where they do not apply, and fail to generate valid shortcut-bearing problems from scratch. Together, these results suggest that current LLMs exhibit procedural shortcut fluency without the structural understanding of when and why shortcuts work that underlies human number sense.

Dual Optimal: Make Your LLM Peer-like with Dignity

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiangqi Wang · Yue Huang · Haomin Zhuang · Kehan Guo · Xiangliang Zhang
3 April 2026 at 12:00
arXiv:2604.00979v2 Announce Type: replace-cross Abstract: Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boilerplate disclaimers. We propose the Dignified Peer framework, which counters servility with anti-sycophancy and trustworthiness, and mitigates evasiveness through empathy and creativity. Realizing this agent requires overcoming significant challenges in data supervision, objective collapse, and evaluation bias. We address these issues by introducing the PersonaKnob dataset which features a compositional partial order structure of multiple persona preference. This data is utilized alongside a tolerant constrained Lagrangian DPO algorithm that dynamically balances all persona dimensions to prevent behavioral collapse. Additionally, we employ a psychometrically calibrated Item Response Theory evaluation protocol to disentangle latent model persona capability from confounders like judge biases. Extensive empirical studies demonstrate that our approach successfully build a LLM agent with both dignity and peer.
Received — 26 March 2026 ⏭

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiuqi Wang · Shangtong Zhang
25 March 2026 at 12:00
arXiv:2409.12135v3 Announce Type: replace-cross Abstract: Temporal difference (TD) learning with linear function approximation (linear TD) is a classic and powerful prediction algorithm in reinforcement learning. While it is well-understood that linear TD converges almost surely to a unique point, this convergence traditionally requires the assumption that the features used by the approximator are linearly independent. However, this linear independence assumption does not hold in many practical scenarios. This work is the first to establish the almost sure convergence of linear TD without requiring linearly independent features. We prove that the weight iterates of linear TD converge to a bounded set, and that the value estimates derived from the weights in that set are the same almost everywhere. We also establish a notion of local stability of the weight iterates. Importantly, we do not impose assumptions tailored to feature dependence and do not modify the linear TD algorithm. Key to our analysis is a novel characterization of bounded invariant sets of the mean ODE of linear TD.

VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guanyuan Pan · Shuai Wang · Yugui Lin · Tiansheng Zhou · Pietro Li\`o · Zhenxin Zhao · Yaqi Wang
25 March 2026 at 12:00
arXiv:2601.07315v4 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning, yet they inherently suffer from spatial blindness and logical hallucinations when interpreting densely structured engineering content, such as analog circuit schematics. To address these challenges, we propose a Vision Language Model-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing (VLM-CAD) designed for robust, step-by-step reasoning over multimodal evidence. VLM-CAD bridges the modality gap by integrating a neuro-symbolic structural parsing module, Image2Net, which transforms raw pixels into explicit topological graphs and structured JSON representations to anchor VLM interpretation in deterministic facts. To ensure the reliability required for engineering decisions, we further propose ExTuRBO, an Explainable Trust Region Bayesian Optimization method. ExTuRBO serves as an explainable grounding engine, employing agent-generated semantic seeds to warm-start local searches and utilizing Automatic Relevance Determination to provide quantified evidence for the VLM's decisions. Experimental results on two complex circuit benchmarks demonstrate that VLM-CAD significantly enhances spatial reasoning accuracy and maintains physics-based explainability. VLM-CAD consistently satisfies complex specification requirements while achieving low power consumption, with a total runtime under 66 minutes, marking a significant step toward robust, explainable multimodal reasoning in specialized technical domains.
Received — 17 March 2026 ⏭

Visual-ERM: Reward Modeling for Visual Equivalence

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziyu Liu · Shengyuan Ding · Xinyu Fang · Xuanlang Dai · Penghui Yang · Jianze Liang · Jiaqi Wang · Kai Chen · Dahua Lin · Yuhang Zang
16 March 2026 at 12:00
arXiv:2603.13224v1 Announce Type: cross Abstract: Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B decisively outperforms Qwen3-VL-235B-Instruct and approaches leading closed-source models. Our results suggest that fine-grained visual reward supervision is both necessary and sufficient for vision-to-code RL, regardless of task specificity.
Received — 14 March 2026 ⏭
Received — 5 March 2026 ⏭

Discriminative Perception via Anchored Description for Reasoning Segmentation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tao Yang · Qing Zhou · Yanliang Li · Qi Wang
5 March 2026 at 13:00
arXiv:2603.04002v1 Announce Type: cross Abstract: Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization, they are incapable of discriminating whether the reasoning process remains anchored on the referred region or strays into irrelevant context. Lacking this discriminative guidance, the model's reasoning often devolves into unfocused and verbose chains that ultimately fail to disambiguate and perceive the target in complex scenes. This suggests a need to complement the RL objective with Discriminative Perception, an ability to actively distinguish a target from its context. To realize this, we propose DPAD to compel the model to generate a descriptive caption of the referred object, which is then used to explicitly discriminate by contrasting the caption's semantic relevance to the referred object against the wider context. By optimizing for this discriminative capability, the model is forced to focus on the unique attributes of the target, leading to a more converged and efficient reasoning chain. The descriptive caption also serves as an interpretability rationale that aligns with the segmentation. Experiments on the benchmarks confirm the validity of our approach, delivering substantial performance gains, with the cIoU on ReasonSeg increasing by 3.09% and the reasoning chain length decreasing by approximately 42%. Code is available at https://github.com/mrazhou/DPAD

Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yaoteng Zhang · Zhou Qing · Junyu Gao · Qi Wang
4 March 2026 at 13:00
arXiv:2603.02286v1 Announce Type: cross Abstract: Incremental Object Detection (IOD) aims to continuously learn new object categories without forgetting previously learned ones. Recently, prompt-based methods have gained popularity for their replay-free design and parameter efficiency. However, due to prompt coupling and prompt drift, these methods often suffer from prompt degradation during continual adaptation. To address these issues, we propose a novel prompt-decoupled framework called PDP. PDP innovatively designs a dual-pool prompt decoupling paradigm, which consists of a shared pool used to capture task-general knowledge for forward transfer, and a private pool used to learn task-specific discriminative features. This paradigm explicitly separates task-general and task-specific prompts, preventing interference between prompts and mitigating prompt coupling. In addition, to counteract prompt drift resulting from inconsistent supervision where old foreground objects are treated as background in subsequent tasks, PDP introduces a Prototypical Pseudo-Label Generation (PPG) module. PPG can dynamically update the class prototype space during training and use the class prototypes to further filter valuable pseudo-labels, maintaining supervisory signal consistency throughout the incremental process. PDP achieves state-of-the-art performance on MS-COCO (with a 9.2\% AP improvement) and PASCAL VOC (with a 3.3\% AP improvement) benchmarks, highlighting its potential in balancing stability and plasticity. The code and dataset are released at: https://github.com/zyt95579/PDP\_IOD/tree/main

Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiaqi Wang · Zhiguang Cao · Peng Zhao · Rui Cao · Yubin Xiao · Yuan Jiang · You Zhou
4 March 2026 at 13:00
arXiv:2603.02846v1 Announce Type: cross Abstract: The rise of smart manufacturing under Industry 4.0 introduces mass customization and dynamic production, demanding more advanced and flexible scheduling techniques. The flexible job-shop scheduling problem (FJSP) has attracted significant attention due to its complex constraints and strong alignment with real-world production scenarios. Current deep reinforcement learning (DRL)-based approaches to FJSP predominantly employ constructive methods. While effective, they often fall short of reaching (near-)optimal solutions. In contrast, improvement-based methods iteratively explore the neighborhood of initial solutions and are more effective in approaching optimality. However, the flexible machine allocation in FJSP poses significant challenges to the application of this framework, including accurate state representation, effective policy learning, and efficient search strategies. To address these challenges, this paper proposes a Memory-enhanced Improvement Search framework with heterogeneous graph representation--MIStar. It employs a novel heterogeneous disjunctive graph that explicitly models the operation sequences on machines to accurately represent scheduling solutions. Moreover, a memoryenhanced heterogeneous graph neural network (MHGNN) is designed for feature extraction, leveraging historical trajectories to enhance the decision-making capability of the policy network. Finally, a parallel greedy search strategy is adopted to explore the solution space, enabling superior solutions with fewer iterations. Extensive experiments on synthetic data and public benchmarks demonstrate that MIStar significantly outperforms both traditional handcrafted improvement heuristics and state-of-the-art DRL-based constructive methods.

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhiyu Mou · Yiqin Lv · Miao Xu · Qi Wang · Yixiu Mao · Jinghao Chen · Qichen Ye · Chao Li · Rongquan Bai · Chuan Yu · Jian Xu · Bo Zheng
4 March 2026 at 13:00
arXiv:2509.15927v4 Announce Type: replace-cross Abstract: Auto-bidding is a critical tool for advertisers to improve advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still face a performance bottleneck due to their inherent inability to explore beyond the static dataset with feedback. To address this, we propose \textbf{AIGB-Pearl} (\emph{\textbf{P}lanning with \textbf{E}valu\textbf{A}tor via \textbf{RL}}), a novel method that integrates generative planning and policy optimization. The core of AIGB-Pearl lies in constructing a trajectory evaluator to assess the quality of generated scores and designing a provably sound KL-Lipschitz-constrained score-maximization scheme to ensure safe and efficient exploration beyond the offline dataset. A practical algorithm that incorporates the synchronous coupling technique is further developed to ensure the model regularity required by the proposed scheme. Extensive experiments on both simulated and real-world advertising systems demonstrate the state-of-the-art performance of our approach.

xLLM Technical Report

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tongxuan Liu · Tao Peng · Peijun Yang · Xiaoyang Zhao · Xiusheng Lu · Weizhe Huang · Zirui Liu · Xiaoyu Chen · Zhiwei Liang · Jun Xiong · Donghe Jin · Minchao Zhang · Jinrong Guo · Yingxu Deng · Xu Zhang · Xianzhe Dong · Siqi Wang · Siyu Wu · Yu Wu · Zihan Tang · Yuting Zeng · Yanshu Wang · Jinguang Liu · Meng Kang · Menxin Li · Yunlong Wang · Yiming Liu · Xiaolong Ma · Yifan Wang · Yichen Zhang · Jinrun Yin · Keyang Zheng · Jiawei Yin · Jun Zhang · Ziyue Wang · Xiaobo Lin · Liangyu Liu · Liwei Lan · Yang Liu · Chunhua Peng · Han Liu · Songcheng Ren · Xuezhu Wang · Yunheng Shen · Yi Wang · Guyue Liu · Yitao Hu · Hui Chen · Tong Yang · Hailong Yang · Jing Li · Guiguang Ding · Ke Zhang
4 March 2026 at 13:00
arXiv:2510.14686v2 Announce Type: replace-cross Abstract: We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.
Received — 25 February 2026 ⏭

VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingbo Zhou · Jun Xia · Siyuan Li · Yunfan Liu · Wenjun Wang · Yufei Huang · Changxi Chi · Mutian Hong · Zhuoli Ouyang · Shu Wang · Zhongqi Wang · Xingyu Wu · Chang Yu · Stan Z. Li
24 February 2026 at 13:00
arXiv:2602.19622v1 Announce Type: cross Abstract: Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models suffer from exponentially increasing computational complexity, making it difficult to scale to large graphs; (2) attention mechanisms based on node-level operations limit the flexibility of the model and result in poor generalization performance in out-of-distribution (OOD) scenarios. To address these issues, we propose \textbf{VecFormer} (the \textbf{Vec}tor Quantized Graph Trans\textbf{former}), an efficient and highly generalizable model for node classification, particularly under OOD settings. VecFormer adopts a two-stage training paradigm. In the first stage, two codebooks are used to reconstruct the node features and the graph structure, aiming to learn the rich semantic \texttt{Graph Codes}. In the second stage, attention mechanisms are performed at the \texttt{Graph Token} level based on the transformed cross codebook, reducing computational complexity while enhancing the model's generalization capability. Extensive experiments on datasets of various sizes demonstrate that VecFormer outperforms the existing Graph Transformer in both performance and speed.

MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jin Jia · Zhiling Deng · Zhuangbin Chen · Yingqi Wang · Zibin Zheng
24 February 2026 at 13:00
arXiv:2602.19843v1 Announce Type: cross Abstract: As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstructured natural language rather than rigid protocols, they are prone to semantic failures (e.g., hallucinations, misinterpreted instructions, and reasoning drift) that propagate silently without raising runtime exceptions. Prevailing evaluation approaches, which measure only end-to-end task success, offer limited insight into how these failures arise or how effectively agents recover from them. To bridge this gap, we propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of MAS. We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures, and inject them via three non-invasive mechanisms: prompt modification, response rewriting, and message routing manipulation. Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors that we organize into four tiers: mechanism, rule, prompt, and reasoning. This tiered view enables fine-grained diagnosis of where and why systems succeed or fail. Our findings reveal that stronger foundation models do not uniformly improve robustness. We further show that architectural topology plays an equally decisive role, with iterative, closed-loop designs neutralizing over 40% of faults that cause catastrophic collapse in linear workflows. MAS-FIRE provides the process-level observability and actionable guidance needed to systematically improve multi-agent systems.

Rethinking the Design of Reinforcement Learning-Based Deep Research Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Wan · Jiuqi Wang · Liam Li · Jinsong Liu · Ruihao Zhu · Zheqing Zhu
24 February 2026 at 13:00
arXiv:2510.15862v4 Announce Type: replace Abstract: Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve strong empirical performance via reinforcement learning from web interactions, the impact of key design choices remains under-explored. We formalize deep research as reinforcement learning in an episodic finite Markov decision process and construct a competitive baseline agent grounded in this formulation. Building on this foundation, we systematically examine critical design decisions at both training and inference time and identify four factors that substantially improve performance: replacing rule-based rewards with AI feedback from an LLM judge, fine-tuning with the on-policy RLOO algorithm instead of the off-policy GRPO algorithm, filtering low-quality training samples, and employing an error-tolerant test-time rollout strategy. Together, these design choices yield a deep research agent that establishes state-of-the-art performance among 7B-scale agents when evaluated across ten widely used benchmarks.
There are no more articles
❌