Tootfinder

Graph Fractional Hilbert Transform: Theory and Application
Daxiang Li, Zhichao Zhang
https://arxiv.org/abs/2509.16910 https://arxiv.org/pdf/2509.16910

Graph Fractional Hilbert Transform: Theory and Application
The graph Hilbert transform (GHT) is a key tool in constructing analytic signals and extracting envelope and phase information in graph signal processing. However, its utility is limited by confinement to the graph Fourier domain, a fixed phase shift, information loss for real-valued spectral components, and the absence of tunable parameters. The graph fractional Fourier transform introduces domain flexibility through a fractional order parameter $α$ but does not resolve the issues of phase ri…

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji
https://arxiv.org/abs/2508.15310

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect Prompt Injection (IPI). Existing defenses typically rely on advanced pro…

GTool: Graph Enhanced Tool Planning with Large Language Model
Wenjie Chen, Wenbin Li, Di Yao, Xuying Meng, Chang Gong, Jingping Bi
https://arxiv.org/abs/2508.12725 https://

GTool: Graph Enhanced Tool Planning with Large Language Model
Tool planning with large language models (LLMs), referring to selecting, organizing, and preparing the tools necessary to complete a user request, bridges the gap between natural language understanding and task execution. However, current works treat different tools as isolated components and fail to leverage the inherent dependencies of tools, leading to invalid planning results. Since tool dependencies are often incomplete, it becomes challenging for LLMs to accurately identify the appropriat…

Score Matching on Large Geometric Graphs for Cosmology Generation
Diana-Alexandra Onutu, Yue Zhao, Joaquin Vanschoren, Vlado Menkovski
https://arxiv.org/abs/2508.16990 https://

Score Matching on Large Geometric Graphs for Cosmology Generation
Generative models are a promising tool to produce cosmological simulations but face significant challenges in scalability, physical consistency, and adherence to domain symmetries, limiting their utility as alternatives to $N$-body simulations. To address these limitations, we introduce a score-based generative model with an equivariant graph neural network that simulates gravitational clustering of galaxies across cosmologies starting from an informed prior, respects periodic boundaries, and s…

Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models
Linfeng Gao, Yaoxiang Wang, Minlong Peng, Jialong Tang, Yuzhe Shang, Mingming Sun, Jinsong Su
https://arxiv.org/abs/2508.05152

Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models
With the remarkable advancement of AI agents, the number of their equipped tools is increasing rapidly. However, integrating all tool information into the limited model context becomes impractical, highlighting the need for efficient tool retrieval methods. In this regard, dominant methods primarily rely on semantic similarities between tool descriptions and user queries to retrieve relevant tools. However, they often consider each tool independently, overlooking dependencies between tools, whi…

as_skitter: Skitter IP graph (2005)
An aggregate snapshot of the Internet Protocol (IP) graph, as measured by the traceroute tool on CAIDA's skitter infrastructure, in 2005.
This network has 1696415 nodes and 11095298 edges.
Tags: Technological, Communication, Unweighted
https://networks.skewed.de/net/as_s…

Dynamic Graph-Based Forecasts of Bookmakers' Odds in Professional Tennis
Matthew J Penn, Jed Michael, Samir Bhatt
https://arxiv.org/abs/2508.15956 https://

Dynamic Graph-Based Forecasts of Bookmakers' Odds in Professional Tennis
Bookmakers' odds consistently provide one of the most accurate methods for predicting the results of professional tennis matches. However, these odds usually only become available shortly before a match takes place, limiting their usefulness as an analysis tool. To ameliorate this issue, we introduce a novel dynamic graph-based model which aims to forecast bookmaker odds for any match on any surface, allowing effective and detailed pre-tournament predictions to be made. By leveraging the high-q…

"Research on the construction and application of problem-method-oriented academic graph empowered by LLM" https://doi.org/10.1007/s10791-025-09675-2
"Nowadays, the volume of literature in each field is huge and is growing rapidly, which posts challenge to researchers’ lit…

A marking graph for finite-type Artin groups
Kaitlin Ragosta
https://arxiv.org/abs/2508.10394 https://arxiv.org/pdf/2508.10394

A marking graph for finite-type Artin groups
Clean markings on surfaces were a key component in Masur and Minsky's hierarchy machinery, which proved to be a powerful tool in the study of mapping class groups. We construct a marking graph for irreducible finite-type Artin groups which is quasi-isometric to the group modulo its center, i.e., an element of $A_Γ/Z(A_Γ)$ is determined up to finite error by its action on one of our markings. To construct this graph, we construct suitable collections of transverse parabolic subgroups which ext…

Lower Bounds on the Haraux Function
Patrick L. Combettes, Julien N. Mayrand
https://arxiv.org/abs/2508.15735 https://arxiv.org/pdf/2508.15735

Lower Bounds on the Haraux Function
The Haraux function is an important tool in monotone operator theory and its applications. One of its salient properties for maximally monotone operators is to be valued in $[0,+\infty]$ and to vanish only on the graph of the operator. Sharper lower bounds for this function were recently proposed in specific scenarios. We derive lower bounds in the general context of set-valued operators in reflexive Banach spaces. These bounds are new, even for maximally monotone operators acting on Euclidean …

Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
Chen Qian, Valdas Vitartas, James Kermode, Reinhard J. Maurer
https://arxiv.org/abs/2508.15108 https…

Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
Machine learning surrogates of Kohn-Sham Density Functional Theory Hamiltonians offer a powerful tool to accelerate the prediction of electronic properties of materials, such as electronic band structures and densities-of-states. For large-scale applications, an ideal model would exhibit high generalization ability and computational efficiency. Here, we introduce the MACE-H graph neural network, which combines high body-order message passing with a node-order expansion to efficiently obtain all…

Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planning
Sahil Bansal, Sai Shruthi Sistla, Aarti Arikatala, Sebastian Schreiber
https://arxiv.org/abs/2508.05888

Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planning
Effective tool retrieval is essential for AI agents to select from a vast array of tools when identifying and planning actions in the context of complex user queries. Despite its central role in planning, this aspect remains underexplored in the literature. Traditional approaches rely primarily on similarities between user queries and tool descriptions, which significantly limits retrieval accuracy, specifically when handling multi-step user requests. To address these limitations, we propose a …

Activated random walk on the comb
Matthew Junge, Josh Meisel, Aldo Morelli
https://arxiv.org/abs/2508.14977 https://arxiv.org/pdf/2508.14977

Activated random walk on the comb
The density conjecture for activated random walk on the interval was recently resolved using a new tool called layer percolation. As a step towards understanding how layer percolation extends to activated random walk on more complex graphs, we develop its analog for the comb graph and use it to prove bounds on the critical density. Additionally, we provide simulation evidence suggesting that the comb has different critical densities on its spine and teeth, both of which are smaller than the cri…

Hypothesis testing for the dimension of random geometric graph
Mingao Yuan, Feng Yu
https://arxiv.org/abs/2510.11844 https://arxiv.org/pdf/2510.11844

Hypothesis testing for the dimension of random geometric graph
Random geometric graphs (RGGs) offer a powerful tool for analyzing the geometric and dependence structures in real-world networks. For example, it has been observed that RGGs are a good model for protein-protein interaction networks. In RGGs, nodes are randomly distributed over an $m$-dimensional metric space, and edges connect the nodes if and only if their distance is less than some threshold. When fitting RGGs to real-world networks, the first step is probably to input or estimate the dimens…

Proof of a conjecture of Voss on bridges of longest cycles
Jie Ma, Rongxing Xu
https://arxiv.org/abs/2509.06345 https://arxiv.org/pdf/2509.06345

Proof of a conjecture of Voss on bridges of longest cycles
Bridges are a classical concept in structural graph theory and play a fundamental role in the study of cycles. A conjecture of Voss from 1991 asserts that if disjoint bridges $B_1, B_2, \ldots, B_k$ of a longest cycle $L$ in a $2$-connected graph overlap in a tree-like manner (i.e., induce a tree in the {\it overlap graph} of $L$), then the total {\it length} of these bridges is at most half the length of $L$. Voss established this for $k \leq 3$ and used it as a key tool in his 1991 monograph …

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
Siddhant Arora, Haidar Khan, Kai Sun, Xin Luna Dong, Sajal Choudhary, Seungwhan Moon, Xinyuan Zhang, Adithya Sagar, Surya Teja Appini, Kaushik Patnaik, Sanat Sharma, Shinji Watanabe, Anuj Kumar, Ahmed Aly, Yue Liu, Florian Metze, Zhaojiang Lin
https://arxiv.…

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain prone to hallucinations due to limited factual grounding. While text-based dialogue systems address this challenge by integrating tools such as web search and knowledge graph APIs, we introduce the first approach to extend tool use directly into speech-in speech-…

as_skitter: Skitter IP graph (2005)
An aggregate snapshot of the Internet Protocol (IP) graph, as measured by the traceroute tool on CAIDA's skitter infrastructure, in 2005.
This network has 1696415 nodes and 11095298 edges.
Tags: Technological, Communication, Unweighted
https://networks.skewed.de/net/as_s…

Temporal social network modeling of mobile connectivity data with graph neural networks
Joel Jaskari, Chandreyee Roy, Fumiko Ogushi, Mikko Saukkoriipi, Jaakko Sahlsten, Kimmo Kaski
https://arxiv.org/abs/2509.03319

Temporal social network modeling of mobile connectivity data with graph neural networks
Graph neural networks (GNNs) have emerged as a state-of-the-art data-driven tool for modeling connectivity data of graph-structured complex networks and integrating information of their nodes and edges in space and time. However, as of yet, the analysis of social networks using the time series of people's mobile connectivity data has not been extensively investigated. In the present study, we investigate four snapshot - based temporal GNNs in predicting the phone call and SMS activity between u…

DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
Jinxin Shi, Zongsheng Cao, Runmin Ma, Yusong Hu, Jie Zhou, Xin Li, Lei Bai, Liang He, Bo Zhang
https://arxiv.org/abs/2510.08959

DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
The deep-research framework orchestrates external tools to perform complex, multi-step scientific reasoning that exceeds the native limits of a single large language model. However, it still suffers from context pollution, weak evidentiary support, and brittle execution paths. To address these issues, we propose DualResearch, a retrieval and fusion framework that matches the epistemic structure of tool-intensive reasoning by jointly modeling two complementary graphs: a breadth semantic graph th…

MindGuard: Tracking, Detecting, and Attributing MCP Tool Poisoning Attack via Decision Dependence Graph
Zhiqiang Wang, Junyang Zhang, Guanquan Shi, HaoRan Cheng, Yunhao Yao, Kaiwen Guo, Haohua Du, Xiang-Yang Li
https://arxiv.org/abs/2508.20412

MindGuard: Tracking, Detecting, and Attributing MCP Tool Poisoning Attack via Decision Dependence Graph
The Model Context Protocol (MCP) is increasingly adopted to standardize the interaction between LLM agents and external tools. However, this trend introduces a new threat: Tool Poisoning Attacks (TPA), where tool metadata is poisoned to induce the agent to perform unauthorized operations. Existing defenses that primarily focus on behavior-level analysis are fundamentally ineffective against TPA, as poisoned tools need not be executed, leaving no behavioral trace to monitor. Thus, we propose M…

On Effectiveness of Graph Neural Network Architectures for Network Digital Twins (NDTs)
Iulisloi Zacarias, Oussama Ben Taarit, Admela Jukan
https://arxiv.org/abs/2508.02373 http…

On Effectiveness of Graph Neural Network Architectures for Network Digital Twins (NDTs)
Future networks, such as 6G, will need to support a vast and diverse range of interconnected devices and applications, each with its own set of requirements. While traditional network management approaches will suffice, an automated solutions are becoming a must. However, network automation frameworks are prone to errors, and often they employ ML-based techniques that require training to learn how the network can be optimized. In this sense, network digital twins are a useful tool that allows f…

as_skitter: Skitter IP graph (2005)
An aggregate snapshot of the Internet Protocol (IP) graph, as measured by the traceroute tool on CAIDA's skitter infrastructure, in 2005.
This network has 1696415 nodes and 11095298 edges.
Tags: Technological, Communication, Unweighted
https://networks.skewed.de/net/as_s…

Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
Molly Noel, Gabriel Mancino-Ball, Yangyang Xu
https://arxiv.org/abs/2508.00267 https://

Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
Graph convolutional networks (GCNs) are a powerful tool for graph representation learning. Due to the recursive neighborhood aggregations employed by GCNs, efficient training methods suffer from a lack of theoretical guarantees or are missing important practical elements from modern deep learning algorithms, such as adaptivity and momentum. In this paper, we present several neighbor-sampling (NS) based Adam-type stochastic methods for solving a nonconvex GCN training problem. We utilize the con…

PowerPlots: An Open Source Power Grid Visualization and Data Analysis Framework for Academic Research
Noah Rhodes
https://arxiv.org/abs/2510.05063 https://…

PowerPlots: An Open Source Power Grid Visualization and Data Analysis Framework for Academic Research
Data visualization is important for developing an understanding of a complex system. PowerPlots.jl is a data visualization tool for power grids, one of the most complex systems in the world. The design of PowerPlots.jl is intended to facilitate exploration of power grid data while performing research and to facilitate communication of research findings to an audience. Several tools created to support this software also facilitate analysis of power grid data by transforming the data into graph t…

GASP: A Gradient-Aware Shortest Path Algorithm for Boundary-Confined Visualization of 2-Manifold Reeb Graphs
Sefat Rahman, Tushar M. Athawale, Paul Rosen
https://arxiv.org/abs/2508.05524

GASP: A Gradient-Aware Shortest Path Algorithm for Boundary-Confined Visualization of 2-Manifold Reeb Graphs
Reeb graphs are an important tool for abstracting and representing the topological structure of a function defined on a manifold. We have identified three properties for faithfully representing Reeb graphs in a visualization. Namely, they should be constrained to the boundary, compact, and aligned with the function gradient. Existing algorithms for drawing Reeb graphs are agnostic to or violate these properties. In this paper, we introduce an algorithm to generate Reeb graph visualizations, cal…

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
Vaibhav Chaudhary, Neha Soni, Narotam Singh, Amita Kapoor
https://arxiv.org/abs/2509.09272

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
Knowledge graphs, a powerful tool for structuring information through relational triplets, have recently become the new front-runner in enhancing question-answering systems. While traditional Retrieval Augmented Generation (RAG) approaches are proficient in fact-based and local context-based extraction from concise texts, they encounter limitations when addressing the thematic and holistic understanding of complex, extensive texts, requiring a deeper analysis of both text and context. This pape…

Optimizing Geometry Problem Sets for Skill Development
Michael Bouzinier, Sergey Trifonov
https://arxiv.org/abs/2509.02758 https://arxiv.org/pdf/2509.02758…

Optimizing Geometry Problem Sets for Skill Development
This article describes an ontology and methodology for annotating and organizing Euclidean Geometry problems, developed in the early 1990s and implemented as a software tool. While the majority of this work -- including the ontology and solution graph paradigm -- was completed over thirty years ago, we argue that it has renewed relevance in the context of modern artificial intelligence. In particular, we explore the hypothesis that this established framework can facilitate automated solution va…

AI4DiTraRe: Building the BFO-Compliant Chemotion Knowledge Graph
Ebrahim Norouzi, Nicole Jung, Anna M. Jacyszyn, J\"org Waitelonis, Harald Sack
https://arxiv.org/abs/2509.01536

AI4DiTraRe: Building the BFO-Compliant Chemotion Knowledge Graph
Chemistry is an example of a discipline where the advancements of technology have led to multi-level and often tangled and tricky processes ongoing in the lab. The repeatedly complex workflows are combined with information from chemical structures, which are essential to understand the scientific process. An important tool for many chemists is Chemotion, which consists of an electronic lab notebook and a repository. This paper introduces a semantic pipeline for constructing the BFO-compliant Ch…

Automated Creation of the Legal Knowledge Graph Addressing Legislation on Violence Against Women: Resource, Methodology and Lessons Learned
Claudia dAmato, Giuseppe Rubini, Francesco Didio, Donato Francioso, Fatima Zahra Amara, Nicola Fanizzi
https://arxiv.org/abs/2508.06368

Automated Creation of the Legal Knowledge Graph Addressing Legislation on Violence Against Women: Resource, Methodology and Lessons Learned
Legal decision-making process requires the availability of comprehensive and detailed legislative background knowledge and up-to-date information on legal cases and related sentences/decisions. Legal Knowledge Graphs (KGs) would be a valuable tool to facilitate access to legal information, to be queried and exploited for the purpose, and to enable advanced reasoning and machine learning applications. Indeed, legal KGs may act as knowledge intensive component to be used by pre-dictive machine le…

Using Stochastic Block Models for Community Detection: The issue of edge-connectivity
The-Anh Vu-Le, Minhyuk Park, Ian Chen, George Chacko, Tandy Warnow
https://arxiv.org/abs/2508.03843

Using Stochastic Block Models for Community Detection: The issue of edge-connectivity
A relevant, sometimes overlooked, quality criterion for communities in graphs is that they should be well-connected in addition to being edge-dense. Prior work has shown that leading community detection methods can produce poorly-connected communities, and some even produce internally disconnected communities. A recent study by Park et al. in Complex Networks and their Applications 2024 showed that this problem is evident in clusterings from three Stochastic Block Models (SBMs) in graph-tool, a…

Higher-rank graphs and the graded $K$-theory of Kumjian-Pask Algebras
Roozbeh Hazrat, Promit Mukherjee, David Pask, Sujit Kumar Sardar
https://arxiv.org/abs/2507.19879 https://

Higher-rank graphs and the graded $K$-theory of Kumjian-Pask Algebras
This paper lays out the foundations of graded $K$-theory for Leavitt algebras associated with higher-rank graphs, also known as Kumjian-Pask algebras, establishing it as a potential tool for their classification. For a row-finite $k$-graph $Λ$ without sources, we show that there exists a $\mathbb{Z}[\mathbb{Z}^k]$-module isomorphism between the graded zeroth (integral) homology $H_0^{gr}(\mathcal{G}_Λ)$ of the infinite path groupoid $\mathcal{G}_Λ$ and the graded Grothendieck group $K_0^{g…

Improving atomic force microscopy structure discovery via style-translation
Jie Huang, Niko Oinonen, Fabio Priante, Filippo Federici Canova, Lauri Kurki, Chen Xu, Adam S. Foster
https://arxiv.org/abs/2509.02240

Improving atomic force microscopy structure discovery via style-translation
Atomic force microscopy (AFM) is a key tool for characterising nanoscale structures, with functionalised tips now offering detailed images of the atomic structure. In parallel, AFM simulations using the particle probe model provide a cost-effective approach for rapid AFM image generation. Using state-of-the-art machine learning models and substantial simulated datasets, properties such as molecular structure, electrostatic potential, and molecular graph can be predicted from AFM images. However…

Forecasting West Nile virus with deep graph encoders
Ethan Greiffenstein, Trevor Harris, Rebecca Smith
https://arxiv.org/abs/2509.22657 https://arxiv.org/p…

Forecasting West Nile virus with deep graph encoders
West Nile virus is a significant, and growing, public health issue in the United States. With no human vaccine, mosquito control programs rely on accurate forecasting to determine when and where WNV will emerge. Recently, spatial Graph neural networks (GNNs) were shown to be a powerful tool for WNV forecasting, significantly improving over traditional methods. Building on this work, we introduce a new GNN variant that linearly connects graph attention layers, allowing us to train much larger mo…

MC-GNNAS-Dock: Multi-criteria GNN-based Algorithm Selection for Molecular Docking
Siyuan Cao, Hongxuan Wu, Jiabao Brad Wang, Yiliang Yuan, Mustafa Misir
https://arxiv.org/abs/2509.26377

MC-GNNAS-Dock: Multi-criteria GNN-based Algorithm Selection for Molecular Docking
Molecular docking is a core tool in drug discovery for predicting ligand-target interactions. Despite the availability of diverse search-based and machine learning approaches, no single docking algorithm consistently dominates, as performance varies by context. To overcome this challenge, algorithm selection frameworks such as GNNAS-Dock, built on graph neural networks, have been proposed. This study introduces an enhanced system, MC-GNNAS-Dock, with three key advances. First, a multi-criteria …