Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

7 April 2026 at 12:00

arXiv:2604.04190v1 Announce Type: new Abstract: Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.

The Topology of Multimodal Fusion: Why Current Architectures Fail at Creative Cognition

cs.AI, q-bio.NC updates on arXiv.org

By: Xiujiang Tan (Guangzhou Academy of Fine Arts · Guangzhou · China)

7 April 2026 at 12:00

arXiv:2604.04465v1 Announce Type: new Abstract: This paper identifies a structural limitation in current multimodal AI architectures that is topological rather than parametric. Contrastive alignment (CLIP), cross-attention fusion (GPT-4V/Gemini), and diffusion-based generation share a common geometric prior -- modal separability -- which we term contact topology. The argument rests on three pillars with philosophy as the generative center. The philosophical pillar reinterprets Wittgenstein's saying/showing distinction as a problem rather than a conclusion: where Wittgenstein chose silence, the Chinese craft epistemology tradition responded with xiang (operative schema) -- the third state emerging when saying and showing interpenetrate. A cruciform framework (dao/qi x saying/showing) positions xiang at the intersection, executing dual huacai (transformation-and-cutting) along both axes. This generates a dual-layer dynamics: chuanghua (creative transformation as spontaneous event) and huacai (its institutionalization into repeatable form). The cognitive science pillar reinterprets DMN/ECN/SN tripartite co-activation through the pathological mirror: overlap isomorphism vs. superimposition collapse in a 2D parameter space (coupling intensity x regulatory capacity). The mathematical pillar formalizes these via fiber bundles and Yang-Mills curvature, with the cruciform structure mapped to fiber bundle language. We propose UOO implementation via Neural ODEs with topological regularization, the ANALOGY-MM benchmark with error-type-ratio metric, and the META-TOP three-tier benchmark testing cross-civilizational topological isomorphism across seven archetypes. A phased experimental roadmap with explicit termination criteria ensures clean exit if falsified.

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents

cs.AI, q-bio.NC updates on arXiv.org

By: Mohammad Hossein Chinaei

7 April 2026 at 12:00

arXiv:2604.04035v1 Announce Type: cross Abstract: Tool-calling LLM agents can read private data, invoke external services, and trigger real-world actions, creating a security problem at the point of tool execution. We identify a denial-feedback leakage pattern, which we term causality laundering, in which an adversary probes a protected action, learns from the denial outcome, and exfiltrates the inferred information through a later seemingly benign tool call. This attack is not captured by flat provenance tracking alone because the leaked information arises from causal influence of the denied action, not direct data flow. We present the Agentic Reference Monitor (ARM), a runtime enforcement layer that mediates every tool invocation by consulting a provenance graph over tool calls, returned data, field-level provenance, and denied actions. ARM propagates trust through an integrity lattice and augments the graph with counterfactual edges from denied-action nodes, enabling enforcement over both transitive data dependencies and denial-induced causal influence. In a controlled evaluation on three representative attack scenarios, ARM blocks causality laundering, transitive taint propagation, and mixed-provenance field misuse that a flat provenance baseline misses, while adding sub-millisecond policy evaluation overhead. These results suggest that denial-aware causal provenance is a useful abstraction for securing tool-calling agent systems.

Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation

16 March 2026 at 12:00

arXiv:2603.12581v1 Announce Type: cross Abstract: Although diffusion models have achieved remarkable progress in multi-modal magnetic resonance imaging (MRI) translation tasks, existing methods still tend to suffer from anatomical inconsistencies or degraded texture details when handling arbitrary missing-modality scenarios. To address these issues, we propose a latent diffusion-based multi-modal MRI translation framework, termed MSG-LDM. By leveraging the available modalities, the proposed method infers complete structural information, which preserves reliable boundary details. Specifically, we introduce a style--structure disentanglement mechanism in the latent space, which explicitly separates modality-specific style features from shared structural representations, and jointly models low-frequency anatomical layouts and high-frequency boundary details in a multi-scale feature space. During the structure disentanglement stage, high-frequency structural information is explicitly incorporated to enhance feature representations, guiding the model to focus on fine-grained structural cues while learning modality-invariant low-frequency anatomical representations. Furthermore, to reduce interference from modality-specific styles and improve the stability of structure representations, we design a style consistency loss and a structure-aware loss. Extensive experiments on the BraTS2020 and WMH datasets demonstrate that the proposed method outperforms existing MRI synthesis approaches, particularly in reconstructing complete structures. The source code is publicly available at https://github.com/ziyi-start/MSG-LDM.

Induced Sputum Multi-Omics Reveals Airway Signatures of COPD in Smokers: A Pilot Study

(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)

By: Kaja Pulik · Piotr Korczyński · Katarzyna Mycroft-Rzeszotarska · Iga Ciesielska-Markowska · Magdalena Kucia · Magdalena Paplińska-Goryca · Diana Wierzbicka · Kannathasan Thetchinamoorthy · Zofia Wicik · Katarzyna Górska

14 March 2026 at 18:00

Int J Mol Sci. 2026 Feb 28;27(5):2271. doi: 10.3390/ijms27052271.

ABSTRACT

Chronic obstructive pulmonary disease (COPD) is a leading cause of mortality worldwide, yet only a fraction of smokers develops the disease, suggesting protective mechanisms in resilient individuals. Identifying airway-localized molecular signatures may improve our understanding of disease pathomechanisms and support hypothesis generation for biomarker research. In this pilot study, induced sputum from smokers with COPD (n = 28) and smokers without COPD (n = 16; Global Initiative for Chronic Obstructive Lung Disease (GOLD)-defined pre-COPD) was analyzed by untargeted proteomics, metabolomics, and lipidomics. After quality control, 1180 proteins, 187 metabolites, and 1234 lipids were retained. Analyses included univariate models with false discovery rate adjustment and multivariate analyses (PCA, PLS-DA), followed by pathway enrichment and protein interaction network analysis. While few features remained significant after FDR correction, consistent cross-omics patterns were observed. COPD was characterized by ↑ glutathione, creatine, and L-arginine; ↓ CCDC88A and ↑ STAT3 and SYDE2; and broad lipid remodeling involving phosphatidylcholines, sphingolipids, and eicosanoids. Network analysis highlighted STAT3 as a highly connected node linking COPD-related genes. These findings suggest that the multi-omic profiling of induced sputum can capture coherent airway-localized molecular signatures such as oxidative stress, cytoskeletal remodeling, and Rho-family GTPase signaling. However, the results should be interpreted as exploratory and require validation in functional studies.

PMID:41828494 | PMC:PMC12984585 | DOI:10.3390/ijms27052271

Induced Sputum Multi-Omics Reveals Airway Signatures of COPD in Smokers: A Pilot Study

Omics In Lung

By: Kaja Pulik · Piotr Korczyński · Katarzyna Mycroft-Rzeszotarska · Iga Ciesielska-Markowska · Magdalena Kucia · Magdalena Paplińska-Goryca · Diana Wierzbicka · Kannathasan Thetchinamoorthy · Zofia Wicik · Katarzyna Górska

14 March 2026 at 18:00

Int J Mol Sci. 2026 Feb 28;27(5):2271. doi: 10.3390/ijms27052271.

ABSTRACT

Chronic obstructive pulmonary disease (COPD) is a leading cause of mortality worldwide, yet only a fraction of smokers develops the disease, suggesting protective mechanisms in resilient individuals. Identifying airway-localized molecular signatures may improve our understanding of disease pathomechanisms and support hypothesis generation for biomarker research. In this pilot study, induced sputum from smokers with COPD (n = 28) and smokers without COPD (n = 16; Global Initiative for Chronic Obstructive Lung Disease (GOLD)-defined pre-COPD) was analyzed by untargeted proteomics, metabolomics, and lipidomics. After quality control, 1180 proteins, 187 metabolites, and 1234 lipids were retained. Analyses included univariate models with false discovery rate adjustment and multivariate analyses (PCA, PLS-DA), followed by pathway enrichment and protein interaction network analysis. While few features remained significant after FDR correction, consistent cross-omics patterns were observed. COPD was characterized by ↑ glutathione, creatine, and L-arginine; ↓ CCDC88A and ↑ STAT3 and SYDE2; and broad lipid remodeling involving phosphatidylcholines, sphingolipids, and eicosanoids. Network analysis highlighted STAT3 as a highly connected node linking COPD-related genes. These findings suggest that the multi-omic profiling of induced sputum can capture coherent airway-localized molecular signatures such as oxidative stress, cytoskeletal remodeling, and Rho-family GTPase signaling. However, the results should be interpreted as exploratory and require validation in functional studies.

PMID:41828494 | PMC:PMC12984585 | DOI:10.3390/ijms27052271

Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems?

cs.AI, q-bio.NC updates on arXiv.org

By: Lve Meng (University of Science · Technology of China · Zhongguancun Academy) · Weilong Zhao (Universit\'e Paris Cit\'e) · Yanzhi Zhang (Zhongguancun Academy) · Haoxiang Guan (Zhongguancun Academy) · Jiyan He (Zhongguancun Academy)

10 March 2026 at 12:00

arXiv:2602.13695v2 Announce Type: replace Abstract: Large language models (LLMs) have recently achieved remarkable success in generating rigorous mathematical proofs, with "AI for Math" emerging as a vibrant field of research (Ju et al., 2026). While these models have mastered competition-level benchmarks like the International Mathematical Olympiad (Huang et al., 2025; Duan et al., 2025) and show promise in research applications through auto-formalization (Wang et al., 2025), their deployment via lightweight, natural-language pipelines for research problems remains underexplored. In this work, we demonstrate that next-generation models (e.g., Gemini 3 Pro, GPT-5.2 Pro), when integrated into a streamlined automated pipeline optimized for citation-based verification, can solve sophisticated research-grade problems. We evaluate our pipeline on two novel datasets: (1) the ICCM (2025) problem sets (comparable to the S.-T. Yau College Student Mathematics Contest) proposed by leading mathematicians (Shanghai Math Challenge, 2026), and (2) the "First Proof" problem set (Abouzaid et al., 2026), consisting of previously unpublished research questions. Our pipeline generated candidate proofs for all problems in the first two ICCM sets and the "First Proof" set. The solutions for the first two ICCM sets and Problem 4 of the "First Proof" set have been fully verified by our team. All generated proofs have been submitted to the official organization, and our generated results are publicly available at https://github.com/ml1301215/question_sets-test_results. We have open-sourced the code and developed a user-friendly UI for this workflow, accessible at https://github.com/ml1301215/research-math-assistant.

Reading view