Tootfinder

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu, Yuchuan Wu, Fan Shi, Lei Liao, Jinghui Lu, Xiaodong Ge, Han Wang, Minghan Zhuo, Xuecheng Wu, Xiang Fei, Hao Feng, Guozhi Tang, An-Lan Wang, Hanshen Zhu, Yangfan He, Quanhuan Liang, Liyuan Meng, Chao Feng, Can Huang, Jingqun Tang, Bin Li
https://

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we p…

Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
Sahil Sethi, Kai Sundmacher, Caroline Ganzer
https://arxiv.org/abs/2509.10273

Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
Ionic liquids (ILs) have emerged as versatile replacements for traditional solvents because their physicochemical properties can be precisely tailored to various applications. However, accurately predicting key thermophysical properties remains challenging due to the vast chemical design space and the limited availability of experimental data. In this study, we present a data-driven transfer learning framework that leverages a neural recommender system (NRS) to enable reliable property predicti…

KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments
Walid Abdela
https://arxiv.org/abs/2510.10325 https://

KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments
The seamless integration of physical and digital environments in Cyber-Physical Systems(CPS), particularly within Industry 4.0, presents significant challenges stemming from system heterogeneity and complexity. Traditional approaches often rely on rigid, data-centric solutions like co-simulation frameworks or brittle point-to-point middleware bridges, which lack the semantic richness and flexibility required for intelligent, autonomous coordination. This report introduces the Knowledge Graph-En…

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…

Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
Mohanakrishnan Hariharan, Satish Arvapalli, Seshu Barma, Evangeline Sheela
https://arxiv.org/abs/2510.10824

Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
We present an approach to software testing automation using Agentic Retrieval-Augmented Generation (RAG) systems for Quality Engineering (QE) artifact creation. We combine autonomous AI agents with hybrid vector-graph knowledge systems to automate test plan, case, and QE metric generation. Our approach addresses traditional software testing limitations by leveraging LLMs such as Gemini and Mistral, multi-agent orchestration, and enhanced contextualization. The system achieves remarkable accurac…

Demonstrating Narrative Pattern Discovery from Biomedical Literature
Hermann Kroll, Pascal Sackhoff, Bill Matthias Thang, Christin Katharina Kreutz, Wolf-Tilo Balke
https://arxiv.org/abs/2509.09687

Demonstrating Narrative Pattern Discovery from Biomedical Literature
Digital libraries maintain extensive collections of knowledge and need to provide effective access paths for their users. For instance, PubPharm, the specialized information service for Pharmacy in Germany, provides and develops access paths to their underlying biomedical document collection. In brief, PubPharm supports traditional keyword-based search, search for chemical structures, as well as novel graph-based discovery workflows, e.g., listing or searching for interactions between different…

The Rise of the Knowledge Sculptor: A New Archetype for Knowledge Work in the Age of Generative AI
Cathal Doyle
https://arxiv.org/abs/2510.07829 https://ar…

The Rise of the Knowledge Sculptor: A New Archetype for Knowledge Work in the Age of Generative AI
In the Generative Age, the nature of knowledge work is transforming. Traditional models that emphasise the organisation and retrieval of pre-existing information are increasingly inadequate in the face of generative AI (GenAI) systems capable of autonomous content creation. This paper introduces the Knowledge Sculptor (KS), a new professional archetype for Human-GenAI collaboration that transforms raw AI output into trustworthy, actionable knowledge. Grounded in a socio-technical perspective, t…

LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation
Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
https://arxiv.org/abs/2510.11358

LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge. While traditional retrieval focuses on relevance, RAG's effectiveness depends on the utility of retrieved passages, i.e., the usefulness in facilitating the generation of an accurate and comprehensive answer. Existing studies often treat utility as a generic attribute, ignoring the fact that different LLMs may benefit differently from the same passage due to variations in internal kno…

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing
Wuyuao Mai, Geng Hong, Qi Liu, Jinsong Chen, Jiarun Dai, Xudong Pan, Yuan Zhang, Min Yang
https://arxiv.org/abs/2509.09207

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing
Penetration testing is critical for identifying and mitigating security vulnerabilities, yet traditional approaches remain expensive, time-consuming, and dependent on expert human labor. Recent work has explored AI-driven pentesting agents, but their evaluation relies on oversimplified capture-the-flag (CTF) settings that embed prior knowledge and reduce complexity, leading to performance estimates far from real-world practice. We close this gap by introducing the first real-world, agent-orient…

MultiCNKG: Integrating Cognitive Neuroscience, Gene, and Disease Knowledge Graphs Using Large Language Models
Ali Sarabadani, Kheirolah Rahsepar Fard
https://arxiv.org/abs/2510.06742

MultiCNKG: Integrating Cognitive Neuroscience, Gene, and Disease Knowledge Graphs Using Large Language Models
The advent of large language models (LLMs) has revolutionized the integration of knowledge graphs (KGs) in biomedical and cognitive sciences, overcoming limitations in traditional machine learning methods for capturing intricate semantic links among genes, diseases, and cognitive processes. We introduce MultiCNKG, an innovative framework that merges three key knowledge sources: the Cognitive Neuroscience Knowledge Graph (CNKG) with 2.9K nodes and 4.3K edges across 9 node types and 20 edge types…

Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks
Kevin Saad, Vincenzo Petrone, Enrico Ferrentino, Pasquale Chiacchio, Francesco Braghin, Loris Roveda
https://arxiv.org/abs/2509.08440

Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks
As robotics gains popularity, interaction control becomes crucial for ensuring force tracking in manipulator-based tasks. Typically, traditional interaction controllers either require extensive tuning, or demand expert knowledge of the environment, which is often impractical in real-world applications. This work proposes a novel control strategy leveraging Neural Networks (NNs) to enhance the force-tracking behavior of a Direct Force Controller (DFC). Unlike similar previous approaches, it acco…

Good Morning #Canada
If you haven't been living in a cave this week, you know that the #NorthernLights were putting on a show across Canada. As you know, a solar eruption sends billions of tons of superheated plasma into space and traveling at more than 45 million miles per hour it can reach Earth in less than a day. That plasma, drawn towards the magnetic pole, interacts with our atmosphere, and we get a spectacular light show. The Aurora Borealis, named by Italian astronomer Galileo di Vincenzo Bonaiuti de' Galilei, is not unique to Canada, but so much of our land is in the Northern Hemisphere that most Canadians have the opportunity to experience it. This is particularly true in the Northwest Territories, where the Northern Lights are visible for 240 days every year on average. The phenomenon has a special meaning for Indigenous Canadians, some of whom believe it shows them ancestors dancing in the sky.
#CanadaIsAwesome #GetOutside
https://www.cbc.ca/radio/unreserved/how-indigenous-traditional-knowledge-is-improving-our-understanding-of-aurora-borealis-1.7414899

KLIPA: A Knowledge Graph and LLM-Driven QA Framework for IP Analysis
Guanzhi Deng, Yi Xie, Yu-Keung Ng, Mingyang Liu, Peijun Zheng, Jie Liu, Dapeng Wu, Yinqiao Li, Linqi Song
https://arxiv.org/abs/2509.07860

KLIPA: A Knowledge Graph and LLM-Driven QA Framework for IP Analysis
Effectively managing intellectual property is a significant challenge. Traditional methods for patent analysis depend on labor-intensive manual searches and rigid keyword matching. These approaches are often inefficient and struggle to reveal the complex relationships hidden within large patent datasets, hindering strategic decision-making. To overcome these limitations, we introduce KLIPA, a novel framework that leverages a knowledge graph and a large language model (LLM) to significantly adva…

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
Yushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen
https://arxiv.org/abs/2509.04716

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing, which typically retrieves knowledge strictly necessary for answer generation, thus often suffer from low coverage due to rigid schema requirements and semantic ambiguity. We present KERAG, a novel KG-based…

Conversational AI increases political knowledge as effectively as self-directed internet search
Lennart Luettgau, Hannah Rose Kirk, Kobi Hackenburg, Jessica Bergs, Henry Davidson, Henry Ogden, Divya Siddarth, Saffron Huang, Christopher Summerfield
https://arxiv.org/abs/2509.05219

Conversational AI increases political knowledge as effectively as self-directed internet search
Conversational AI systems are increasingly being used in place of traditional search engines to help users complete information-seeking tasks. This has raised concerns in the political domain, where biased or hallucinated outputs could misinform voters or distort public opinion. However, in spite of these concerns, the extent to which conversational AI is used for political information-seeking, as well the potential impact of this use on users' political knowledge, remains uncertain. Here, we a…

Comparing unsupervised learning methods for local structural identification in colloidal systems
Alptu\u{g} Ulug\"ol, Jessi B\"uckmann, Ruizhi Yang, Roy Hoitink, Alfons van Blaaderen, Frank Smallenburg, Laura Filion
https://arxiv.org/abs/2509.07186

Comparing unsupervised learning methods for local structural identification in colloidal systems
Quantifying local structures in self-assembled systems is a central challenge in soft matter and materials science. When no a priori knowledge of the relevant structures is available, traditional order parameters often fall short. Unsupervised machine learning provides a convenient route to autonomously uncover structural motifs directly from particle configurations. In this work, we systematically compare three popular dimensionality reduction techniques; Principal Component Analysis (PCA), Au…

ALPHA: LLM-Enabled Active Learning for Human-Free Network Anomaly Detection
Xuanhao Luo, Shivesh Madan Nath Jha, Akruti Sinha, Zhizhen Li, Yuchen Liu
https://arxiv.org/abs/2509.05936

ALPHA: LLM-Enabled Active Learning for Human-Free Network Anomaly Detection
Network log data analysis plays a critical role in detecting security threats and operational anomalies. Traditional log analysis methods for anomaly detection and root cause analysis rely heavily on expert knowledge or fully supervised learning models, both of which require extensive labeled data and significant human effort. To address these challenges, we propose ALPHA, the first Active Learning Pipeline for Human-free log Analysis. ALPHA integrates semantic embedding, clustering-based repre…

QAgent: A modular Search Agent with Interactive Query Understanding
Yi Jiang, Lei Shen, Lujie Niu, Sendong Zhao, Wenbo Su, Bo Zheng
https://arxiv.org/abs/2510.08383 https://

QAgent: A modular Search Agent with Interactive Query Understanding
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external information. However, (1) traditional RAG struggles with complex query understanding, and (2) even search agents trained with reinforcement learning (RL), despite their promise, still face generalization and deployment challenges. To address these limitations, we prop…

Interactive Graph Visualization and TeamingRecommendation in an Interdisciplinary Project'sTalent Knowledge Graph
Jiawei Xu, Juichien Chen, Yilin Ye, Zhandos Sembay, Swathi Thaker, Pamela Payne-Foster, Jake Chen, Ying Ding
https://arxiv.org/abs/2508.19489

Interactive Graph Visualization and TeamingRecommendation in an Interdisciplinary Project'sTalent Knowledge Graph
Interactive visualization of large scholarly knowledge graphs combined with LLM reasoning shows promise butremains under-explored. We address this gap by developing an interactive visualization system for the Cell Map forAI Talent Knowledge Graph (28,000 experts and 1,179 biomedical datasets). Our approach integrates WebGLvisualization with LLM agents to overcome limitations of traditional tools such as Gephi, particularly for large-scaleinteractive node handling. Key functionalities include re…

Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face Recognition
Durgesh Mishra, Rishabh Uikey
https://arxiv.org/abs/2508.11376

Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face Recognition
Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Consistency loss, often fail to capture both fine-grained instance-level details and complex relational structures, leading to suboptimal performance. We propose a unified approach that integrates two novel loss functions, Instance-Level Embedding Distillation and Relation-Based P…

Prompting the Market? A Large-Scale Meta-Analysis of GenAI in Finance NLP (2022-2025)
Paolo Pedinotti, Peter Baumann, Nathan Jessurun, Leslie Barrett, Enrico Santus
https://arxiv.org/abs/2509.09544

Prompting the Market? A Large-Scale Meta-Analysis of GenAI in Finance NLP (2022-2025)
Large Language Models (LLMs) have rapidly reshaped financial NLP, enabling new tasks and driving a proliferation of datasets and diversification of data sources. Yet, this transformation has outpaced traditional surveys. In this paper, we present MetaGraph, a generalizable methodology for extracting knowledge graphs from scientific literature and analyzing them to obtain a structured, queryable view of research trends. We define an ontology for financial NLP research and apply an LLM-based extr…

SETrLUSI: Stochastic Ensemble Multi-Source Transfer Learning Using Statistical Invariant
Chunna Li, Yiwei Song, Yuanhai Shao
https://arxiv.org/abs/2509.15593 https://

SETrLUSI: Stochastic Ensemble Multi-Source Transfer Learning Using Statistical Invariant
In transfer learning, a source domain often carries diverse knowledge, and different domains usually emphasize different types of knowledge. Different from handling only a single type of knowledge from all domains in traditional transfer learning methods, we introduce an ensemble learning framework with a weak mode of convergence in the form of Statistical Invariant (SI) for multi-source transfer learning, formulated as Stochastic Ensemble Multi-Source Transfer Learning Using Statistical Invari…

Surrogate-based Bayesian calibration methods for climate models: a comparison of traditional and non-traditional approaches
Maike F. Holthuijzen, Atlanta Chakraborty, Elizabeth Krath, Tommie Catanach
https://arxiv.org/abs/2508.13071

Surrogate-based Bayesian calibration methods for climate models: a comparison of traditional and non-traditional approaches
Parameter calibration is crucial for reducing uncertainty and improving simulation accuracy in physics-based models, yet computational constraints pose significant challenges. Bayesian calibration methods offer a principled framework for combining prior knowledge with data while rigorously quantifying uncertainty. In this work, we compare four emulator-based Bayesian calibration methods: Calibrate-Emulate-Sample (CES), History Matching (HM), Bayesian Optimal Experimental Design (BOED), and a no…

Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
Xiaoming Zhai
https://arxiv.org/abs/2509.14554 https://

Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
The rise of generative large language models (LLMs) has opened new opportunities for automating knowledge representation through concept maps, a long-standing pedagogical tool valued for fostering meaningful learning and higher-order thinking. Traditional construction of concept maps is labor-intensive, requiring significant expertise and time, limiting their scalability in education. This review systematically synthesizes the emerging body of research on LLM-enabled concept map generation, foc…

Automated Program Repair of Uncompilable Student Code
Griffin Pitts, Aum Pandya, Darsh Rank, Tirth Bhatt, Muntasir Hoq, Bita Akram
https://arxiv.org/abs/2510.06187 https://

Automated Program Repair of Uncompilable Student Code
A significant portion of student programming submissions in CS1 learning environments are uncompilable, limiting their use in student modeling and downstream knowledge tracing. Traditional modeling pipelines often exclude these cases, discarding observations of student learning. This study investigates automated program repair as a strategy to recover uncompilable code while preserving students' structural intent for use in student modeling. Within this framework, we assess large language model…

Beyond Traditional Surveillance: Harnessing Expert Knowledge for Public Health Forecasting
Garrik Hoyt, Eleanor Bergren, Gabrielle String, Thomas McAndrew
https://arxiv.org/abs/2508.15623

Beyond Traditional Surveillance: Harnessing Expert Knowledge for Public Health Forecasting
Downsizing the US public health workforce throughout 2025 amplifies potential risks during public health crises. Expert judgment from public health officials represents a vital information source, distinct from traditional surveillance infrastructure, that should be valued -- not discarded. Understanding how expert knowledge functions under constraints is essential for understanding the potential impact of reduced capacity. To explore expert forecasting capabilities, 114 public health officials…

Crosslisted article(s) found for physics.chem-ph. https://arxiv.org/list/physics.chem-ph/new
[1/1]:
- Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers
Robert MacKnight, Jose Emilio Regio, Jeffrey G. Ethier, Luke A. Baldwi…

NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
Huhong Xian, Rui Liu, Berrak Sisman, Haizhou Li
https://arxiv.org/abs/2509.03829

NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
Different from traditional sentence-level audio deepfake detection (ADD), partial audio deepfake detection (PADD) requires frame-level positioning of the location of fake speech. While some progress has been made in this area, leveraging semantic information from audio, especially named entities, remains an underexplored aspect. To this end, we propose NE-PADD, a novel method for Partial Audio Deepfake Detection (PADD) that leverages named entity knowledge through two parallel branches: Speech …

Socially Interactive Agents for Preserving and Transferring Tacit Knowledge in Organizations
Martin Benderoth, Patrick Gebhard, Christian Keller, C. Benjamin Nakhosteen, Stefan Schaffer, Tanja Schneeberger
https://arxiv.org/abs/2508.19942

Socially Interactive Agents for Preserving and Transferring Tacit Knowledge in Organizations
This paper introduces a novel approach to tackle the challenges of preserving and transferring tacit knowledge--deep, experience-based insights that are hard to articulate but vital for decision-making, innovation, and problem-solving. Traditional methods rely heavily on human facilitators, which, while effective, are resource-intensive and lack scalability. A promising alternative is the use of Socially Interactive Agents (SIAs) as AI-driven knowledge transfer facilitators. These agents intera…

Augmenting LLMs for General Time Series Understanding and Prediction
Felix Parker, Nimeesha Chan, Chi Zhang, Kimia Ghobadi
https://arxiv.org/abs/2510.01111 https://

Augmenting LLMs for General Time Series Understanding and Prediction
Time series data is fundamental to decision-making in many crucial domains including healthcare, finance, and environmental science. However, analyzing this data often requires incorporating unstructured contextual information, answering domain-specific questions, and generating natural language explanations -- capabilities that traditional time series models lack due to their inability to process text. While Large Language Models (LLMs) excel at contextual reasoning and knowledge integration, …

CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
Zhe Li, Zhiwei Lin, Yongtao Wang
https://arxiv.org/abs/2509.26037 https:…

CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
The integration of Large Language Models (LLMs) with Neural Architecture Search (NAS) has introduced new possibilities for automating the design of neural architectures. However, most existing methods face critical limitations, including architectural invalidity, computational inefficiency, and inferior performance compared to traditional NAS. In this work, we present Collaborative LLM-based NAS (CoLLM-NAS), a two-stage NAS framework with knowledge-guided search driven by two complementary LLMs…

Knowledge-Graph Based RAG System Evaluation Framework
Sicheng Dong, Vahid Zolfaghari, Nenad Petrovic, Alois Knoll
https://arxiv.org/abs/2510.02549 https://…

Knowledge-Graph Based RAG System Evaluation Framework
Large language models (LLMs) has become a significant research focus and is utilized in various fields, such as text generation and dialog systems. One of the most essential applications of LLM is Retrieval Augmented Generation (RAG), which greatly enhances generated content's reliability and relevance. However, evaluating RAG systems remains a challenging task. Traditional evaluation metrics struggle to effectively capture the key features of modern LLM-generated content that often exhibits hi…

From Documents to Database: Failure Modes for Industrial Assets
Duygu Kabakci-Zorlu, Fabio Lorenzi, John Sheehan, Karol Lynch, Bradley Eck
https://arxiv.org/abs/2509.17834 https…

From Documents to Database: Failure Modes for Industrial Assets
We propose an interactive system using foundation models and user-provided technical documents to generate Failure Mode and Effects Analyses (FMEA) for industrial equipment. Our system aggregates unstructured content across documents to generate an FMEA and stores it in a relational database. Leveraging this tool, the time required for creation of this knowledge-intensive content is reduced, outperforming traditional manual approaches. This demonstration showcases the potential of foundation mo…

Real-Time, Population-Based Reconstruction of 3D Bone Models via Very-Low-Dose Protocols
Yiqun Lin, Haoran Sun, Yongqing Li, Rabia Aslam, Lung Fung Tse, Tiange Cheng, Chun Sing Chui, Wing Fung Yau, Victorine R. Le Meur, Meruyert Amangeldy, Kiho Cho, Yinyu Ye, James Zou, Wei Zhao, Xiaomeng Li
https://arxiv.org/abs/2508.13947

Real-Time, Population-Based Reconstruction of 3D Bone Models via Very-Low-Dose Protocols
Patient-specific bone models are essential for designing surgical guides and preoperative planning, as they enable the visualization of intricate anatomical structures. However, traditional CT-based approaches for creating bone models are limited to preoperative use due to the low flexibility and high radiation exposure of CT and time-consuming manual delineation. Here, we introduce Semi-Supervised Reconstruction with Knowledge Distillation (SSR-KD), a fast and accurate AI framework to reconstr…

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Yi Liao, Yu Gu, Yuan Sui, Zining Zhu, Yifan Lu, Guohua Tang, Zhongqian Sun, Wei Yang
https://arxiv.org/abs/2508.21365

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform effortlessly. This discrepancy highlights a critical gap between declarative knowledge (knowing about something) and procedural knowledge (knowing how to do something). Although traditional reinforcement learning (RL) agents can acquire procedural knowledge through environmental interaction, they often operate as bla…

DSRAG: A Domain-Specific Retrieval Framework Based on Document-derived Multimodal Knowledge Graph
Mengzheng Yang, Yanfei Ren, David Osei Opoku, Ruochang Li, Peng Ren, Chunxiao Xing
https://arxiv.org/abs/2509.10467

DSRAG: A Domain-Specific Retrieval Framework Based on Document-derived Multimodal Knowledge Graph
Current general-purpose large language models (LLMs) commonly exhibit knowledge hallucination and insufficient domain-specific adaptability in domain-specific tasks, limiting their effectiveness in specialized question answering scenarios. Retrieval-augmented generation (RAG) effectively tackles these challenges by integrating external knowledge to enhance accuracy and relevance. However, traditional RAG still faces limitations in domain knowledge accuracy and context modeling.To enhance domain…

FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction
Ravi Shankar Prasad, Dinesh Singh
https://arxiv.org/abs/2508.18031 https://

FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction
Craniofacial reconstruction in forensics is one of the processes to identify victims of crime and natural disasters. Identifying an individual from their remains plays a crucial role when all other identification methods fail. Traditional methods for this task, such as clay-based craniofacial reconstruction, require expert domain knowledge and are a time-consuming process. At the same time, other probabilistic generative models like the statistical shape model or the Basel face model fail to ca…

ATLAS: A Self-Supervised and Cross-Stage Netlist Power Model for Fine-Grained Time-Based Layout Power Analysis
Wenkai Li, Yao Lu, Wenji Fang, Jing Wang, Qijun Zhang, Zhiyao Xie
https://arxiv.org/abs/2508.12433

ATLAS: A Self-Supervised and Cross-Stage Netlist Power Model for Fine-Grained Time-Based Layout Power Analysis
Accurate power prediction in VLSI design is crucial for effective power optimization, especially as designs get transformed from gate-level netlist to layout stages. However, traditional accurate power simulation requires time-consuming back-end processing and simulation steps, which significantly impede design optimization. To address this, we propose ATLAS, which can predict the ultimate time-based layout power for any new design in the gate-level netlist. To the best of our knowledge, ATLAS …

In Numeris Veritas: An Empirical Measurement of Wi-Fi Integration in Industry
Vyron Kampourakis, Christos Smiliotopoulos, Vasileios Gkioulos, Sokratis Katsikas
https://arxiv.org/abs/2509.16987

In Numeris Veritas: An Empirical Measurement of Wi-Fi Integration in Industry
Traditional air gaps in industrial systems are disappearing as IT technologies permeate the OT domain, accelerating the integration of wireless solutions like Wi-Fi. Next-generation Wi-Fi standards (IEEE 802.11ax/be) meet performance demands for industrial use cases, yet their introduction raises significant security concerns. A critical knowledge gap exists regarding the empirical prevalence and security configuration of Wi-Fi in real-world industrial settings. This work addresses this by mini…

A Modular KDN-Based Framework for IT/OT Autonomy in Industrial Systems
Tu\u{g}\c{c}e Bilen, Mehmet Ozdem
https://arxiv.org/abs/2509.23389 https://arxiv.org…

A Modular KDN-Based Framework for IT/OT Autonomy in Industrial Systems
The convergence of Information Technology (IT) and Operational Technology (OT) is a critical enabler for achieving autonomous and intelligent industrial systems. However, the increasing complexity, heterogeneity, and real-time demands of industrial environments render traditional rule-based or static management approaches insufficient. In this paper, we present a modular framework based on the Knowledge-Defined Networking (KDN) paradigm, enabling adaptive and autonomous control across IT-OT inf…

SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
Yifei Li, Lingling Zhang, Hang Yan, Tianzhe Zhao, Zihan Ma, Muye Huang, Jun Liu
https://arxiv.org/abs/2508.11347

SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
Traditional knowledge graph (KG) embedding methods aim to represent entities and relations in a low-dimensional space, primarily focusing on static graphs. However, real-world KGs are dynamically evolving with the constant addition of entities, relations and facts. To address such dynamic nature of KGs, several continual knowledge graph embedding (CKGE) methods have been developed to efficiently update KG embeddings to accommodate new facts while maintaining learned knowledge. As KGs grow at di…

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Ziming Wei, Zichen Kong, Yuan Wang, David Z. Pan, Xiyuan Tang
https://arxiv.org/abs/2509.14169

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language m…

Domain Translation of a Soft Robotic Arm using Conditional Cycle Generative Adversarial Network
Nilay Kushawaha, Carlo Alessi, Lorenzo Fruzzetti, Egidio Falotico
https://arxiv.org/abs/2508.14100

Domain Translation of a Soft Robotic Arm using Conditional Cycle Generative Adversarial Network
Deep learning provides a powerful method for modeling the dynamics of soft robots, offering advantages over traditional analytical approaches that require precise knowledge of the robot's structure, material properties, and other physical characteristics. Given the inherent complexity and non-linearity of these systems, extracting such details can be challenging. The mappings learned in one domain cannot be directly transferred to another domain with different physical properties. This challeng…

Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
Akshay Govind Srinivasan, Ryan Jacob George, Jayden Koshy Joe, Hrushikesh Kant, Harshith M R, Sachin Sundar, Sudharshan Suresh, Rahul Vimalkanth, Vijayavallabh
https://arxiv.org/abs/2509.16369

Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
Accurate and reliable knowledge retrieval is vital for financial question-answering, where continually updated data sources and complex, high-stakes contexts demand precision. Traditional retrieval systems rely on a single database and retriever, but financial applications require more sophisticated approaches to handle intricate regulatory filings, market analyses, and extensive multi-year reports. We introduce a framework for financial Retrieval Augmented Generation (RAG) that leverages agent…

An Interactive Google Earth Engine Application for Global Multi-Scale Vegetation Analysis Using NDVI Thresholding
Md. Moktader Moula, Israt Jahan Shonom, Azharul Islam, Mohammad Mosharraf Hossain
https://arxiv.org/abs/2509.01628

An Interactive Google Earth Engine Application for Global Multi-Scale Vegetation Analysis Using NDVI Thresholding
Monitoring vegetation dynamics is crucial for addressing global environmental challenges like degradation and deforestation, but traditional remote sensing methods are often complex and resource-intensive. To overcome these barriers, we developed an interactive, cloud-based application on the Google Earth Engine (GEE) platform for few clicks on-demand global vegetation analysis without complex technical knowledge. The application automates the calculation of vegetated areas using the Normalized…

Fence off Anomaly Interference: Cross-Domain Distillation for Fully Unsupervised Anomaly Detection
Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang
https://arxiv.org/abs/2508.18007

Fence off Anomaly Interference: Cross-Domain Distillation for Fully Unsupervised Anomaly Detection
Fully Unsupervised Anomaly Detection (FUAD) is a practical extension of Unsupervised Anomaly Detection (UAD), aiming to detect anomalies without any labels even when the training set may contain anomalous samples. To achieve FUAD, we pioneer the introduction of Knowledge Distillation (KD) paradigm based on teacher-student framework into the FUAD setting. However, due to the presence of anomalies in the training data, traditional KD methods risk enabling the student to learn the teacher's repres…

Benchmarking LLM-based Agents for Single-cell Omics Analysis
Yang Liu, Lu Zhou, Ruikun He, Rongbo Shen, Yixue Li
https://arxiv.org/abs/2508.13201 https://a…

Benchmarking LLM-based Agents for Single-cell Omics Analysis
The surge in multimodal single-cell omics data exposes limitations in traditional, manually defined analysis workflows. AI agents offer a paradigm shift, enabling adaptive planning, executable code generation, traceable decisions, and real-time knowledge fusion. However, the lack of a comprehensive benchmark critically hinders progress. We introduce a novel benchmarking evaluation system to rigorously assess agent capabilities in single-cell omics analysis. This system comprises: a unified plat…

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-…

An LLM-based Agentic Framework for Accessible Network Control
Samuel Lin, Jiawei Zhou, Minlan Yu
https://arxiv.org/abs/2509.20600 https://arxiv.org/pdf/250…

An LLM-based Agentic Framework for Accessible Network Control
Traditional approaches to network management have been accessible only to a handful of highly-trained network operators with significant expert knowledge. This creates barriers for lay users to easily manage their networks without resorting to experts. With recent development of powerful large language models (LLMs) for language comprehension, we design a system to make network management accessible to a broader audience of non-experts by allowing users to converse with networks in natural lang…

Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach
Jisu Kim, Jinhee Park, Changhyun Jeon, Jungwoo Choi, Keonwoo Kim, Minji Hong, Sehyun Kim
https://arxiv.org/abs/2509.15658

Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach
Traditional query expansion techniques for addressing vocabulary mismatch problems in information retrieval are context-sensitive and may lead to performance degradation. As an alternative, document expansion research has gained attention, but existing methods such as Doc2Query have limitations including excessive preprocessing costs, increased index size, and reliability issues with generated content. To mitigate these problems and seek more structured and efficient alternatives, this study pr…

Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
Ahmed Mujtaba, Gleb Radchenko, Radu Prodan, Marc Masana
https://arxiv.org/abs/2508.14769

Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
Federated distillation has emerged as a promising collaborative machine learning approach, offering enhanced privacy protection and reduced communication compared to traditional federated learning by exchanging model outputs (soft logits) rather than full model parameters. However, existing methods employ complex selective knowledge-sharing strategies that require clients to identify in-distribution proxy data through computationally expensive statistical density ratio estimators. Additionally,…

TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios
Ji Yin, Menglan He, Yujie Zhang, Linshuai Zhang, Tingting Ma, Ce Tian, Jie Wu, Lin Xu, Tao Jiang
https://arxiv.org/abs/2509.19834

TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios
Domain-specific LLMs in TCM face limitations in research settings due to constrained adaptability, insufficient evaluation datasets, and limited computational resources. This study presents TianHui, a specialized TCM LLM built through contextual data integration and domain knowledge fusion. We constructed a large-scale TCM corpus (0.97GB unsupervised data + 611,312 QA pairs) and employed a two-stage training strategy with QLoRA, DeepSpeed Stage 2, and Flash Attention 2. Evaluation on 12 benchma…

Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering
Changjian Wang, Weihong Deng, Weili Guan, Quan Lu, Ning Jiang
https://arxiv.org/abs/2508.11247

Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering
Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer. Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic similarity and ignore structural associations among dispersed knowledge, which limits their effectiveness in MHQA tasks. GraphRAG methods address this by leveraging knowledge graphs (KGs) to capture structural associations, but they tend to overly rely on str…

DiaCDM: Cognitive Diagnosis in Teacher-Student Dialogues using the Initiation-Response-Evaluation Framework
Rui Jia, Yuang Wei, Ruijia Li, Yuang-Hao Jiang, Xinyu Xie, Yaomin Shen, Min Zhang, Bo Jiang
https://arxiv.org/abs/2509.24821

DiaCDM: Cognitive Diagnosis in Teacher-Student Dialogues using the Initiation-Response-Evaluation Framework
While cognitive diagnosis (CD) effectively assesses students' knowledge mastery from structured test data, applying it to real-world teacher-student dialogues presents two fundamental challenges. Traditional CD models lack a suitable framework for handling dynamic, unstructured dialogues, and it's difficult to accurately extract diagnostic semantics from lengthy dialogues. To overcome these hurdles, we propose DiaCDM, an innovative model. We've adapted the initiation-response-evaluation (IRE) f…

Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Bihao Zhan, Jie Zhou, Junsong Li, Yutao Yang, Shilian Chen, Qianjun Pan, Xin Li, Wen Wu, Xingjiao Wu, Qin Chen, Hang Yan, Liang He
https://arxiv.org/abs/2509.12958

Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. Traditional privacy methods, like a uniform Differential Privacy (DP) budget, indiscriminately protect all data, leading to substantial model utility degradation and hindering CL deployment in privacy-sensitive areas. To overcome this, we propose a privacy-enhanced continual learning (PeCL) framework that forgets what'…

FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
Chanyeol Choi, Jihoon Kwon, Alejandro Lopez-Lira, Chaewoon Kim, Minjae Kim, Juneha Hwang, Jaeseon Ha, Hojun Choi, Suyeol Yun, Yongjin Kim, Yongjae Lee
https://arxiv.org/abs/2508.14052

FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
Accurate information retrieval (IR) is critical in the financial domain, where investors must identify relevant information from large collections of documents. Traditional IR methods-whether sparse or dense-often fall short in retrieval accuracy, as it requires not only capturing semantic similarity but also performing fine-grained reasoning over document structure and domain-specific knowledge. Recent advances in large language models (LLMs) have opened up new opportunities for retrieval with…

Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation
Hongyu Cao, Yuxuan Wu, Yucheng Cai, Xianyu Zhao, Zhijian Ou
https://arxiv.org/abs/2508.18168

Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation
Retrieval-augmented generation (RAG) has become a widely recognized paradigm to combine parametric memory with non-parametric memories. An RAG model consists of two serial connecting components (retriever and generator). A major challenge in end-to-end optimization of the RAG model is that marginalization over relevant passages (modeled as discrete latent variables) from a knowledge base is required. Traditional top-K marginalization and variational RAG (VRAG) suffer from biased or high-varianc…

ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER
Jielong Tang, Shuang Wang, Zhenxing Wang, Jianxing Yu, Jian Yin
https://arxiv.org/abs/2509.10975

ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER
Grounded Multimodal Named Entity Recognition (GMNER) extends traditional NER by jointly detecting textual mentions and grounding them to visual regions. While existing supervised methods achieve strong performance, they rely on costly multimodal annotations and often underperform in low-resource domains. Multimodal Large Language Models (MLLMs) show strong generalization but suffer from Domain Knowledge Conflict, producing redundant or incorrect mentions for domain-specific entities. To address…

Principle Methods of Rendering Non-equivalent Words from Uzbek and Dari to Russian and English
Mohammad Ibrahim Qani
https://arxiv.org/abs/2508.15453 https://

Principle Methods of Rendering Non-equivalent Words from Uzbek and Dari to Russian and English
These pure languages understanding directly relates to translation knowledge where linguists and translators need to work and research to eradicate misunderstanding. Misunderstandings mostly appear in non-equivalent words because there are different local and internal words like food, garment, cultural and traditional words and others in every notion. Truly, most of these words do not have equivalent in the target language and these words need to be worked and find their equivalent in the targe…

Transplant Then Regenerate: A New Paradigm for Text Data Augmentation
Guangzhan Wang, Hongyu Zhang, Beijun Shen, Xiaodong Gu
https://arxiv.org/abs/2508.14723 https://

Transplant Then Regenerate: A New Paradigm for Text Data Augmentation
Data augmentation is a critical technique in deep learning. Traditional methods like Back-translation typically focus on lexical-level rephrasing, which primarily produces variations with the same semantics. While large language models (LLMs) have enhanced text augmentation by their "knowledge emergence" capability, controlling the style and structure of these outputs remains challenging and requires meticulous prompt engineering. In this paper, we propose LMTransplant, a novel text augmentatio…