Long Yuan

Triangle counting in hypergraph streams, including both hyper-vertex and hyper-edge triangles, is a fundamental problem in hypergraph analytics, with broad applications. However, existing methods face two key limitations: ( i ) an incomplete classification of hyper-vertex triangle structures, typically considering only inner or outer triangles; and ( ii ) inflexible sampling schemes that predefine the number of sampled hyperedges, which is impractical under strict memory constraints due to highly variable hyperedge sizes. To address these challenges, we first introduce a complete classification of hyper-vertex triangles, including inner, hybrid, and outer triangles. Based on this, we propose two complementary categories of streaming algorithms. For element-wise eviction, we develop HTCount, an algorithm that dynamically adjusts the sample size based on the available memory M , and HTCount-P, a partition-based variant that further improves memory utilization by partitioning unused memory into independent sample subsets. For batch eviction, we propose HTCount-B, which adopts a lazy maintenance strategy controlled by a decay parameter β , reducing per-update computational cost by operating with a smaller average sample set and naturally capturing temporal locality in triangle formation. We provide theoretical analysis of the unbiasedness and variance bounds of the proposed algorithms. Case studies demonstrate the expressiveness of our triangle structures in revealing meaningful interaction patterns. Extensive experiments on real-world hypergraphs show that our algorithms achieve highly accurate triangle count estimates under strict memory constraints, with relative errors 1–2 orders of magnitude lower than existing methods; HTCount-B further attains higher throughput with appropriate β settings, and practical guidelines are provided for different datasets.

Large language models (LLMs) have achieved remarkable performance, prompting the development of LLM-based agents to tackle complex, open-world tasks. Despite these advances, autonomous agents still face critical bottlenecks in environmental perception, multi-step reasoning, and long-term opera-tional consistency. Graphs provide a systematic solution to these challenges by explicitly modeling entities, relationships, and dependencies, thereby establishing a rigorous foundation for reasoning and interaction. While recent literature explores this integration, existing surveys primarily focus on operational workflows and architectures, lacking a systematic analysis of how graphs fundamentally elevate agent intelligence. To bridge this gap, this survey presents a comprehensive review of Graph-Augmented LLM-based Agents (GLAs). We systematically decompose agent architecture to distill five core capabilities required for advanced intelligence: perception, reasoning, memorization, generaliza-tion, and interaction. We explicitly address why graphs are uniquely suited to bolster these capabilities and how they are practically integrated, proposing a novel taxonomy that organizes existing studies along these five dimensions. Furthermore, we review representative real-world applications of GLAs across diverse domains and outline key challenges and promising directions for future research. A curated repository containing the literature reviewed in this survey, along with the latest advancements in this field, is maintained and regularly updated at https://github.com/sqs17/GLA.

In modern cloud-native systems, a single root cause can trigger cascading anomalies across multiple entities (e.g., microservices, databases, and hosts), generating alert storms with hundreds or thousands of heterogeneous alerts. Alert convergence (automatically grouping these alerts into actionable incident tickets) is critical for reducing operator burden and recovery time. Existing graph-based methods construct a topological graph from known entity dependencies and then leverage Graph Neural Networks (GNNs) for information propagation, but they rely on static physical topologies that fail to capture implicit fault propagation paths. Large Language Model (LLM)-based methods focus on reasoning about the textual information of alerts, yet they do not incorporate global topological structure and struggle with consistency at scale. Motivated by these limitations, we propose LLM-Guided Graph Structure Learning (LLM-GSL), a novel framework that combines the semantic reasoning ability of LLMs with the structural modeling power of GNNs for alert convergence. Specifically, LLM-GSL first leverages an LLM to evaluate pairwise entity relationships and discover implicit fault propagation paths that are absent from static topologies, thereby enhancing the physical-topology graph into a more complete structure. A Graph Attention Network (GAT) then refines alert representations over this enhanced graph via graph message passing, guided by a self-supervised graph affinity loss with continuous multi-modal supervision targets that fuse adjacency structure, textual affinity, and temporal affinity. Finally, density-based clustering groups the learned representations into incident tickets. Experiments on five public datasets, including four LogHub-derived datasets and one RCAEval microservice fault-injection subset, demonstrate that LLM-GSL achieves an average F1-score of 96.2%, outperforming six baselines including both traditional clustering and LLM-based methods by at least 14.0 percentage points.

Website Fingerprinting (WF) is an emerging traffic analysis technique that enables a passive adversary to infer which websites a user visits. However, most existing studies, whether in single-tab or multi-tab settings, rely on the unrealistic assumption that users only access website homepages, diverging significantly from real-world browsing behavior. Even recent works extending WF to subpages primarily focus on website-level identification, without distinguishing which specific subpages are visited, thereby limiting the attack's granularity and scope. In this paper, we propose HiFi-WF (Hierarchical Fine-grained Website Fingerprinting), a novel framework that breaks the homepage-only assumption and extends WF to multi-tab recognition and fine-grained subpage identification. We formulate the task as a hierarchical multi-label classification problem, jointly modeling the distinctions and correlations between homepages and subpages. To this end, HiFi-WF integrates a unified CNN-based extractor and layered encoder with a Feature Interaction Module based on multi-head cross-attention to capture inter-level dependencies. An Enhanced SubHead enforces hierarchical constraints to suppress invalid subpage predictions, while a cascaded channel–spatial attention mechanism refines discriminative features for precise hierarchical identification. Experimental results demonstrate that HiFi-WF achieves state-of-the-art performance at both hierarchical levels, attaining F1-scores of 92.1% (homepage) and 81.9% (subpage), thereby validating its effectiveness in advancing WF attacks toward realistic, fine-grained, and multi-tab browsing scenarios. Related codes and datasets can be found in https://github.com/wusongyang02-blip/HiFi-WF.

Root cause analysis (RCA), which leverages multi-modal observability data (including metrics, traces, and logs) to identify the fundamental source of system failures, is critical for ensuring the reliability of complex microservice systems. Traditionally, RCA has relied on human engineers to manually correlate these fragmented signals, which is a labor-intensive and error-prone process. Although recent AIOps advancements, particularly those leveraging Large Language Models (LLMs), aim to automate this workflow, they remain constrained by limitations. Existing methods often rely on single-modal data, restricting diagnostic comprehensiveness. Furthermore, approaches that utilize multi-modal data typically depend on simplistic temporal alignment, which fails to capture complex semantic relationships, or directly employ LLMs, which are prone to hallucinations and lack reliability. To address these issues, we propose a novel Graph-Augmented Multi-Agent Framework that synergizes the structural rigor of graph topology with the advanced semantic reasoning capabilities of LLMs. Our approach operates in two distinct phases designed to mimic human expert problem-solving. First, in the Anomaly Fusion Graph Construction phase, we employ a hybrid alignment strategy to bridge the gap between unstructured logs and structured traces. An LLM serves as a “semantic arbitrator” to resolve ambiguities in high-concurrency scenarios, creating a unified knowledge environment where each node is enriched with comprehensive health insights. Second, the Multi-Agent Collaborative Reasoning phase deploys a team of specialized agents to simulate human Site Reliability Engineering (SRE) workflows. A Navigator Agent efficiently guides the search space via calculated fault gradients, while a Diagnoser Agent performs deep semantic analysis. Crucially, a Verifier Agent enforces an Adversarial Validation Protocol to mitigate hallucinations through rigorous counterfactual reasoning. Extensive experiments conducted on five diverse datasets demonstrate the robustness and effectiveness of our approach. The results show that our framework achieves an average F1-score of 88.4%, significantly outperforming state-of-the-art baselines by 4.6%, proving its ability to synthesize multi-modal information into actionable diagnostic insights.

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet their application to graph structure analysis, particularly in community search, remains underexplored. Community search, a fundamental task in graph analysis, aims to identify groups of nodes with dense interconnections, which is crucial for understanding the macroscopic structure of graphs. In this paper, we propose GraphCS, a comprehensive benchmark designed to evaluate the performance of LLMs in community search tasks. Our experiments reveal that while LLMs exhibit preliminary potential, they frequently fail to return meaningful results and suffer from output bias. To address these limitations, we introduce CS-Agent, a dual-agent collaborative framework to enhance LLM-based community search. CS-Agent leverages the complementary strengths of two LLMs acting as Solver and Validator. Through iterative feedback and refinement, CS-Agent dynamically refines initial results without fine-tuning or additional training. After the multi-round dialogue, Decider module selects the optimal community. Extensive experiments demonstrate that CS-Agent significantly improves the quality and stability of identified communities compared to baseline methods. To our knowledge, this is the first work to apply LLMs to community search, bridging the gap between LLMs and graph analysis while providing a robust and adaptive solution for real-world applications.