Tootfinder

CryptPad: Zero-Knowledge Architecture
While Google Docs reads everything you type, CryptPad's XSalsa20-Poly1305 encryption and Nakamoto-style consensus protocol ensure the server never decrypts your documents.
https://www.sambent.com/cryptpad-zero-knowledge-architecture…

CryptPad: Zero-Knowledge Architecture
While Google Docs reads everything you type, CryptPad's XSalsa20-Poly1305 encryption and Nakamoto-style consensus protocol ensure the server never decrypts your documents.

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
Caglar Demir, Alkid Baci, N'Dah Jean Kouagou, Leonie Nora Sieger, Stefan Heindorf, Simon Bin, Lukas Bl\"ubaum, Alexander Bigerl, Axel-Cyrille Ngonga Ngomo
https://arxiv.org/abs/2510.11561

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
In this paper, we present Ontolearn-a framework for learning OWL class expressions over large knowledge graphs. Ontolearn contains efficient implementations of recent stateof-the-art symbolic and neuro-symbolic class expression learners including EvoLearner and DRILL. A learned OWL class expression can be used to classify instances in the knowledge graph. Furthermore, Ontolearn integrates a verbalization module based on an LLM to translate complex OWL class expressions into natural language sen…

AI Is Supercharging the War on Libraries, Education, and Human Knowledge https://www.404media.co/ai-is-supercharging-the-war-on-libraries-education-and-human-knowledge/

AI Is Supercharging the War on Libraries, Education, and Human Knowledge
"Fascism and AI, whether or not they have the same goals, they sure are working to accelerate one another."

Towards an AI-based knowledge assistant for goat farmers based on Retrieval-Augmented Generation
Nana Han, Dong Liu, Tomas Norton
https://arxiv.org/abs/2509.09848 https://

Towards an AI-based knowledge assistant for goat farmers based on Retrieval-Augmented Generation
Large language models (LLMs) are increasingly being recognised as valuable knowledge communication tools in many industries. However, their application in livestock farming remains limited, being constrained by several factors not least the availability, diversity and complexity of knowledge sources. This study introduces an intelligent knowledge assistant system designed to support health management in farmed goats. Leveraging the Retrieval-Augmented Generation (RAG), two structured knowledge …

SI-FACT: Mitigating Knowledge Conflict via Self-Improving Faithfulness-Aware Contrastive Tuning
Shengqiang Fu
https://arxiv.org/abs/2509.10208 https://arxi…

SI-FACT: Mitigating Knowledge Conflict via Self-Improving Faithfulness-Aware Contrastive Tuning
Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we propose a novel self improving framework,Self Improving Faithfulness Aware Contrastive Tuning.The framework uses a self instruct mechanism that allows the base LLM to automatically generate high quality,structured contrastive learning data,including anchor sampl…

Why your boss isn't worried about AI
When it comes to understanding the dangers of AI systems, the general public has the worst kind of knowledge: that what you know for sure that just ain’t so. […]
😒 https://boydkane.com/essays/boss

Why your boss isn't worried about AI
...

"How a New Data Platform Sheds Light on #OpenScience #Funding" @ Katina Magazine:

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
Yue Gu, Zhihao Du, Ying Shi, Jiqing Han, Yongjun He
https://arxiv.org/abs/2510.10401

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
Fine-tuning generic ASR models with large-scale synthetic personal data can enhance the personalization of ASR models, but it introduces challenges in adapting to synthetic personal data without forgetting real knowledge, and in adapting to personal data without forgetting generic knowledge. Considering that the functionally invariant path (FIP) framework enables model adaptation while preserving prior knowledge, in this letter, we introduce FIP into synthetic-data-augmented personalized ASR mo…

Efficient Learned Image Compression Through Knowledge Distillation
Fabien Allemand, Attilio Fiandrotti, Sumanta Chaudhuri, Alaa Eddine Mazouz
https://arxiv.org/abs/2509.10366 ht…

Efficient Learned Image Compression Through Knowledge Distillation
Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a low-dimensional latent space, which is then quantized, entropy-coded into a binary bitstream, and transmitted to the receiver. At the receiver end, the bitstream is entropy-decoded, and a decoder reconstructs an approximation of the original image. Recent research sugges…

Convergence analysis of inexact MBA method for constrained upper-$\mathcal{C}^2$ optimization problems
Ruyu Liu, Shaohua Pan
https://arxiv.org/abs/2511.09940 https://arxiv.org/pdf/2511.09940 https://arxiv.org/html/2511.09940
arXiv:2511.09940v1 Announce Type: new
Abstract: This paper concerns a class of constrained optimization problems in which, the objective and constraint functions are both upper-$\mathcal{C}^2$. For such nonconvex and nonsmooth optimization problems, we develop an inexact moving balls approximation (MBA) method by a workable inexactness criterion for the solving of subproblems. By leveraging a global error bound for the strongly convex program associated with parametric optimization problems, we establish the full convergence of the iterate sequence under the partial bounded multiplier property (BMP) and the Kurdyka-{\L}ojasiewicz (KL) property of the constructed potential function, and achieve the local convergence rate of the iterate and objective value sequences if the potential function satisfies the KL property of exponent $q\in[1/2,1)$. A verifiable condition is also provided to check whether the potential function satisfies the KL property of exponent $q\in[1/2,1)$ at the given critical point. To the best of our knowledge, this is the first implementable inexact MBA method with a full convergence certificate for the constrained nonconvex and nonsmooth optimization problem.
toXiv_bot_toot

MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables
Kausik Hira, Mohd Zaki, Mausam, N. M. Anoop Krishnan
https://arxiv.org/abs/2509.10448

MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables
Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systematic extraction and analysis. Here, we present MatSKRAFT, a computational framework that automatically extracts and integrates materials science knowledge from tabular data at unprecedented scale. Our approach transforms tables into graph-based representations processed by constraint-driven GNNs that encode scientific …

CTIArena: Benchmarking LLM Knowledge and Reasoning Across Heterogeneous Cyber Threat Intelligence
Yutong Cheng, Yang Liu, Changze Li, Dawn Song, Peng Gao
https://arxiv.org/abs/2510.11974

CTIArena: Benchmarking LLM Knowledge and Reasoning Across Heterogeneous Cyber Threat Intelligence
Cyber threat intelligence (CTI) is central to modern cybersecurity, providing critical insights for detecting and mitigating evolving threats. With the natural language understanding and reasoning capabilities of large language models (LLMs), there is increasing interest in applying them to CTI, which calls for benchmarks that can rigorously evaluate their performance. Several early efforts have studied LLMs on some CTI tasks but remain limited: (i) they adopt only closed-book settings, relying…

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Xu Yang, Jiayuan Zhou, Michael Pacheco, Wenhan Zhu, Pengfei He, Shaowei Wang, Kui Liu, Ruiqi Pan
https://arxiv.org/abs/2510.11838

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, repository-level issue resolution. Existing agent-based methods have two key limitations. First, they lack of procedural knowledge (i.e., how an issue is fixed step-by-step and rationales behind it) to learn and leverage for issue resolution. Second, they rely on massive computational power to blindly explore the solution sp…

TASC: Task-Aware Shared Control for Teleoperated Manipulation
Ze Fu, Pinhao Song, Yutong Hu, Renaud Detry
https://arxiv.org/abs/2509.10416 https://arxiv.or…

TASC: Task-Aware Shared Control for Teleoperated Manipulation
We present TASC, a Task-Aware Shared Control framework for teleoperated manipulation that infers task-level user intent and provides assistance throughout the task. To support everyday tasks without predefined knowledge, TASC constructs an open-vocabulary interaction graph from visual input to represent functional object relationships, and infers user intent accordingly. A shared control policy then provides rotation assistance during both grasping and object interaction, guided by spatial cons…

KnowledgeTrail: Generative Timeline for Exploration and Sensemaking of Historical Events and Knowledge Formation
Sangho Suh, Rahul Hingorani, Bryan Wang, Tovi Grossman
https://arxiv.org/abs/2510.12113 …

KnowledgeTrail: Generative Timeline for Exploration and Sensemaking of Historical Events and Knowledge Formation
The landscape of interactive systems is shifting toward dynamic, generative experiences that empower users to explore and construct knowledge in real time. Yet, timelines -- a fundamental tool for representing historical and conceptual development -- remain largely static, limiting user agency and curiosity. We introduce the concept of a generative timeline: an AI-powered timeline that adapts to users' evolving questions by expanding or contracting in response to input. We instantiate this conc…

'That sucks': Who said it? Test your knowledge in the NFL Week 6 quote quiz https://www.espn.com/nfl/story/_/id/46585863/browns-steelers-rams-ravens-chargers-dolphins-patriots-jaguars-jets-week-6-2025-…

Conformal prediction without knowledge of labeled calibration data
Jonas Flechsig, Maximilian Pilz
https://arxiv.org/abs/2509.10321 https://arxiv.org/pdf/2…

Conformal prediction without knowledge of labeled calibration data
We extend the method of conformal prediction beyond the case relying on labeled calibration data. Replacing the calibration scores by suitable estimates, we identify conformity sets $C$ for classification and regression models that rely on unlabeled calibration data. Given a classification model with accuracy $1-β$, we prove that the conformity sets guarantee a coverage of $P(Y \in C) \geq 1-α-β$ for an arbitrary parameter $α\in (0,1)$. The same coverage guarantee also holds for regression …

AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
Hongyu Lin, Haolin Pan, Haoran Luo, Yuchen Li, Kaichun Yao, Libo Zhang, Mingjie Xing, Yanjun Wu
https://arxiv.org/abs/2510.11759

AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software optimization, automating compiler optimization remains challenging due to: (1) semantic misalignment between abstract program representations and concrete optimization passes, (2) inefficient interaction mechanisms between agents and compiler environments, and…

Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis
https://arxiv.org/abs/2510.12615

Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
Knowledge distillation is often considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. In this work, we quantify the compression capacity of knowledge distillation and the resulting knowledge transfer from a functional perspective, decoupling compression from architectural reduction, which provides an improved understanding of knowledge distillation. We employ hypothesis testing, controls, and random control d…

LLM-Oriented Token-Adaptive Knowledge Distillation
Xurong Xie, Zhucun Xue, Jiafu Wu, Jian Li, Yabiao Wang, Xiaobin Hu, Yong Liu, Jiangning Zhang
https://arxiv.org/abs/2510.11615

LLM-Oriented Token-Adaptive Knowledge Distillation
Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student models. These methods typically treat all tokens indiscriminately and apply a single, fixed temperature, resulting in suboptimal knowledge transfer. To address these limitations, we propose LLM-Oriented Token-Adaptive Knowledge Distillation (AdaKD), a novel framewo…

"World’s first Indigenous-led ocean reserve is one step closer to reality"
#Oceans #Environment

World’s first Indigenous-led ocean reserve is one step closer to reality | The Optimist Daily
A visionary project blending Indigenous knowledge and science could create the first marine reserve led by Pacific Island nations.

Certifying and learning quantum Ising Hamiltonians
Andreas Bluhm, Matthias C. Caro, Francisco Escudero Guti\'errez, Aadil Oufkir, Cambyse Rouz\'e
https://arxiv.org/abs/2509.10239

Certifying and learning quantum Ising Hamiltonians
In this work, we study the problems of certifying and learning quantum Ising Hamiltonians. Our main contributions are as follows: Certification of Ising Hamiltonians. We show that certifying an Ising Hamiltonian in normalized Frobenius norm via access to its time-evolution operator requires only $\widetilde O(1/\varepsilon)$ time evolution. This matches the Heisenberg-scaling lower bound of $Ω(1/\varepsilon)$ up to logarithmic factors. To our knowledge, this is the first nearly-optimal algor…

Sunspot Observations in 1684-1702: John Flamsteed and Philippe de La Hire
Nadezhda Zolotova, Mikhail Vokhmyanin
https://arxiv.org/abs/2510.11375 https://ar…

Sunspot Observations in 1684-1702: John Flamsteed and Philippe de La Hire
In this work, we present an extensive review and detailed analysis of sunspot measurements, drawings, and engravings made by John Flamsteed and, mainly, by Philippe de La Hire during the Maunder minimum. All available information and contemporary knowledge about the sunspot nature are shown. The coordinates, areas, and numbers of sunspots and sunspot groups are reconstructed. Based on these observations, La Hire, Jean-Dominique Cassini, and his son Jacques Cassini regularly published results th…

@… @… too true.
Also, knowledge and intelligence are not the same.
I've had a thorn in my side since summer 2024. I should have responded more robustly at the time, instead: I kept quiet. When the person who stuck it in takes ple…

AI in Computational Thinking Education in Higher Education: A Systematic Literature Review
Ebrahim Rahimi, Clara Maathuis
https://arxiv.org/abs/2510.09677 https://

AI in Computational Thinking Education in Higher Education: A Systematic Literature Review
Computational Thinking (CT) is a key skill set for students in higher education to thrive and adapt to an increasingly technology-driven future and workplace. While research on CT education has gained remarkable momentum in K12 over the past decade, it has remained under-explored in higher education, leaving higher education teachers with an insufficient overview, knowledge, and support regarding CT education. The proliferation and adoption of artificial intelligence (AI) by educational institu…

Reweighting metric measure spaces and Onsager-Machlup
Zachary Selk
https://arxiv.org/abs/2510.10591 https://arxiv.org/pdf/2510.10591

Reweighting metric measure spaces and Onsager-Machlup
Given a metric measure space $M:=(X,d,μ)$ the Onsager-Machlup (OM) functional is a real valued function that has been seen as a generalized notion of a probability density function. The effect of reweighting the measure on OM functionals has been studied, however analogous reweightings of the metric to the best of our knowledge remain open. In this short note, we prove a transformation formula for OM functionals on geodesic metric measure spaces under reweighting of both the metric and the mea…

Domain Knowledge Infused Generative Models for Drug Discovery Synthetic Data
Bing Hu, Jong-Hoon Park, Helen Chen, Young-Rae Cho, Anita Layton
https://arxiv.org/abs/2510.09837 ht…

Domain Knowledge Infused Generative Models for Drug Discovery Synthetic Data
The role of Artificial Intelligence (AI) is growing in every stage of drug development. Nevertheless, a major challenge in drug discovery AI remains: Drug pharmacokinetic (PK) and Drug-Target Interaction (DTI) datasets collected in different studies often exhibit limited overlap, creating data overlap sparsity. Thus, data curation becomes difficult, negatively impacting downstream research investigations in high-throughput screening, polypharmacy, and drug combination. We propose xImagand-DKI, …

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…

A Fast-Converging Decentralized Approach to the Weighted Minimum Vertex Cover Problem
Matteo Mordacchini, Emanuele Carlini, Patrizio Dazzi
https://arxiv.org/abs/2510.11697 https…

A Fast-Converging Decentralized Approach to the Weighted Minimum Vertex Cover Problem
We address the problem of computing a Minimum Weighted Vertex Cover (MWVC) in a decentralized network. MWVC, a classical NP-hard problem, is foundational in applications such as network monitoring and resource placement. We propose a fully decentralized protocol where each node makes decisions using only local knowledge and communicates with its neighbors. The method is adaptive, communication-efficient, and avoids centralized coordination. We evaluate the protocol on real-world and synthetic g…

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang
https://arxiv.org/abs/2510.10585

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
Multi-agent systems powered by large language models exhibit strong capabilities in collaborative problem-solving. However, these systems suffer from substantial knowledge redundancy. Agents duplicate efforts in retrieval and reasoning processes. This inefficiency stems from a deeper issue: current architectures lack mechanisms to ensure agents share minimal sufficient information at each operational stage. Empirical analysis reveals an average knowledge duplication rate of 47.3\% across agent …

Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
Yisen Gao, Jiaxin Bai, Yi Huang, Xingcheng Fu, Qingyun Sun, Yangqiu Song
https://arxiv.org/abs/2510.11462

Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
Deductive and abductive reasoning are two critical paradigms for analyzing knowledge graphs, enabling applications from financial query answering to scientific discovery. Deductive reasoning on knowledge graphs usually involves retrieving entities that satisfy a complex logical query, while abductive reasoning generates plausible logical hypotheses from observations. Despite their clear synergistic potential, where deduction can validate hypotheses and abduction can uncover deeper logical patte…

Source: livestream shopping app Whatnot nears ~$1B in revenue for 2025; Whatnot says it has passed $6B in gross sales this year, more than doubling 2024's sales (Ann Gehan/The Information)
https://www.theinformation.com/briefings/live…

Livestream Shopping App Whatnot Nears $1 Billion in 2025 Revenue
Livestream shopping app Whatnot is targeting close to $1 billion in revenue for 2025, according to a person with knowledge of the company’s finances. The six-year-old company has quietly grown into one of e-commerce’s hottest companies, raising more than $500 million in new funding this year and boosting its valuation to $11.5 billion. Whatnot originally started as a place for collectors of Funko

DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
Hyeseon Ahn, Shinwoo Park, Yo-Sub Han
https://arxiv.org/abs/2510.10987 https://

DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a sophisticated attack that allows a malicious model to generate text containing the authentic-looking watermark of a trusted, victim model. This enables the seamless misattribution of harmful content, such as disinformation, to reputable sources. The key to our attack…

Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
Xin Zhao, Naoki Yoshinaga, Yuma Tsuta, Akiko Aizawa
https://arxiv.org/abs/2510.12115

Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across languages into large language models (LLMs). Although many methods have been proposed to improve domain adaptation, the mechanisms of multilingual knowledge acquisition, how domain knowledge is learned within a language and transferred across languages, remain underexplored. This gap leads to suboptimal performance, particularly in low-resource settings. This work examines the learning dynamics of LLMs du…

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
Shuangquan Lyu, Ming Wang, Huajun Zhang, Jiasen Zheng, Junjiang Lin, Xiaoxuan Sun
https://arxiv.org/abs/2510.10109

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
This paper designs and implements an explainable recommendation model that integrates knowledge graphs with structure-aware attention mechanisms. The model is built on graph neural networks and incorporates a multi-hop neighbor aggregation strategy. By integrating the structural information of knowledge graphs and dynamically assigning importance to different neighbors through an attention mechanism, the model enhances its ability to capture implicit preference relationships. In the proposed me…

Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States
Nicholas Carlotti, Mirko Nava, Alessandro Giusti
https://arxiv.org/abs/2509.10405

Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States
We introduce a model for monocular RGB relative pose estimation of a ground robot that trains from scratch without pose labels nor prior knowledge about the robot's shape or appearance. At training time, we assume: (i) a robot fitted with multiple LEDs, whose states are independent and known at each frame; (ii) knowledge of the approximate viewing direction of each LED; and (iii) availability of a calibration image with a known target distance, to address the ambiguity of monocular depth estima…

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Kartik Narayan, Yang Xu, Tian Cao, Kavya Nerella, Vishal M. Patel, Navid Shiee, Peter Grasch, Chao Jia, Yinfei Yang, Zhe Gan
https://arxiv.org/abs/2510.12801

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and must remain responsive to the dynamic and ever-changing real-world information in order to address information-seeking and knowledge-intensive user queries. Existing approaches, such as retrieval augmented generation (RAG) methods, search agents, and search equipped MLLMs, often suffer from rigid pipelines, excessive search calls, and poorly constructed search queries, which resu…

A Gradient Guided Diffusion Framework for Chance Constrained Programming
Boyang Zhang, Zhiguo Wang, Ya-Feng Liu
https://arxiv.org/abs/2510.12238 https://ar…

A Gradient Guided Diffusion Framework for Chance Constrained Programming
Chance constrained programming (CCP) is a powerful framework for addressing optimization problems under uncertainty. In this paper, we introduce a novel Gradient-Guided Diffusion-based Optimization framework, termed GGDOpt, which tackles CCP through three key innovations. First, GGDOpt accommodates a broad class of CCP problems without requiring the knowledge of the exact distribution of uncertainty-relying solely on a set of samples. Second, to address the nonconvexity of the chance constraint…

Tensor Logic: The Language of AI
Pedro Domingos
https://arxiv.org/abs/2510.12269 https://arxiv.org/pdf/2510.12269…

Tensor Logic: The Language of AI
Progress in AI is hindered by the lack of a programming language with all the requisite features. Libraries like PyTorch and TensorFlow provide automatic differentiation and efficient GPU implementation, but are additions to Python, which was never intended for AI. Their lack of support for automated reasoning and knowledge acquisition has led to a long and costly series of hacky attempts to tack them on. On the other hand, AI languages like LISP an Prolog lack scalability and support for learn…

"How Libraries Can Shape the Next Era of Open Education" @ Katina Magazine: https://katinamagazine.org/content/article/open-knowledge/2025/how-libraries-can-shape-the-next-era-of-open-education
"

Project-Level C-to-Rust Translation via Synergistic Integration of Knowledge Graphs and Large Language Models
Zhiqiang Yuan, Wenjun Mao, Zhuo Chen, Xiyue Shang, Chong Wang, Yiling Lou, Xin Peng
https://arxiv.org/abs/2510.10956

Project-Level C-to-Rust Translation via Synergistic Integration of Knowledge Graphs and Large Language Models
Translating C code into safe Rust is an effective way to ensure its memory safety. Compared to rule-based translation which produces Rust code that remains largely unsafe, LLM-based methods can generate more idiomatic and safer Rust code because LLMs have been trained on vast amount of human-written idiomatic code. Although promising, existing LLM-based methods still struggle with project-level C-to-Rust translation. They typically partition a C project into smaller units (\eg{} functions) base…

Between Knowledge and Care: Evaluating Generative AI-Based IUI in Type 2 Diabetes Management Through Patient and Physician Perspectives
Yibo Meng, Ruiqi Chen, Zhiming Liu, Xiaolan Ding, Yan Guan
https://arxiv.org/abs/2510.10048

Between Knowledge and Care: Evaluating Generative AI-Based IUI in Type 2 Diabetes Management Through Patient and Physician Perspectives
Generative AI systems are increasingly adopted by patients seeking everyday health guidance, yet their reliability and clinical appropriateness remain uncertain. Taking Type 2 Diabetes Mellitus (T2DM) as a representative chronic condition, this paper presents a two-part mixed-methods study that examines how patients and physicians in China evaluate the quality and usability of AI-generated health information. Study~1 analyzes 784 authentic patient questions to identify seven core categories of …

Knowledge-Guided Machine Learning Models to Upscale Evapotranspiration in the U.S. Midwest
Aleksei Rozanov, Samikshya Subedi, Vasudha Sharma, Bryan C. Runck
https://arxiv.org/abs/2510.11505

Knowledge-Guided Machine Learning Models to Upscale Evapotranspiration in the U.S. Midwest
Evapotranspiration (ET) plays a critical role in the land-atmosphere interactions, yet its accurate quantification across various spatiotemporal scales remains a challenge. In situ measurement approaches, like eddy covariance (EC) or weather station-based ET estimation, allow for measuring ET at a single location. Agricultural uses of ET require estimates for each field over broad areas, making it infeasible to deploy sensing systems at each location. This study integrates tree-based and knowle…

Meta-Analysis with JASP, Part II: Bayesian Approaches
Franti\v{s}ek Barto\v{s}, Eric-Jan Wagenmakers
https://arxiv.org/abs/2509.09850 https://arxiv.org/pdf…

Meta-Analysis with JASP, Part II: Bayesian Approaches
Bayesian inference is on the rise, partly because it allows researchers to quantify parameter uncertainty, evaluate evidence for competing hypotheses, incorporate model ambiguity, and seamlessly update knowledge as information accumulates. All of these advantages apply to the meta-analytic settings; however, advanced Bayesian meta-analytic methodology is often restricted to researchers with programming experience. In order to make these tools available to a wider audience, we implemented state-…

Querying Climate Knowledge: Semantic Retrieval for Scientific Discovery
Mustapha Adamu, Qi Zhang, Huitong Pan, Longin Jan Latecki, Eduard C. Dragut
https://arxiv.org/abs/2509.10087

Querying Climate Knowledge: Semantic Retrieval for Scientific Discovery
The growing complexity and volume of climate science literature make it increasingly difficult for researchers to find relevant information across models, datasets, regions, and variables. This paper introduces a domain-specific Knowledge Graph (KG) built from climate publications and broader scientific texts, aimed at improving how climate knowledge is accessed and used. Unlike keyword based search, our KG supports structured, semantic queries that help researchers discover precise connections…

Entropy and Learning of Lipschitz Functions under Log-Concave Measures
Pierre Bizeul, Boaz Klartag
https://arxiv.org/abs/2509.10355 https://arxiv.org/pdf/2…

Entropy and Learning of Lipschitz Functions under Log-Concave Measures
We study regression of $1$-Lipschitz functions under a log-concave measure $μ$ on $\mathbb{R}^d$. We focus on the high-dimensional regime where the sample size $n$ is subexponential in $d$, in which distribution-free estimators are ineffective. We analyze two polynomial-based procedures: the projection estimator, which relies on knowledge of an orthogonal polynomial basis of $μ$, and the least-squares estimator over low-degree polynomials, which requires no knowledge of $μ$ whatsoever. Their…

A Scalable, Privacy-Preserving Decentralized Identity and Verifiable Data Sharing Framework based on Zero-Knowledge Proofs
Hui Yuan
https://arxiv.org/abs/2510.09715 https://

A Scalable, Privacy-Preserving Decentralized Identity and Verifiable Data Sharing Framework based on Zero-Knowledge Proofs
With the proliferation of decentralized applications (DApps), the conflict between the transparency of blockchain technology and user data privacy has become increasingly prominent. While Decentralized Identity (DID) and Verifiable Credentials (VCs) provide a standardized framework for user data sovereignty, achieving trusted identity verification and data sharing without compromising privacy remains a significant challenge. This paper proposes a novel, comprehensive framework that integrates D…

AI-Powered Assistant for Long-Term Access to RHIC Knowledge
Mohammad Atif, Vincent Garonne, Eric Lancon, Jerome Lauret, Alexandr Prozorov, Michal Vranovsky
https://arxiv.org/abs/2509.09688

AI-Powered Assistant for Long-Term Access to RHIC Knowledge
As the Relativistic Heavy Ion Collider (RHIC) at Brookhaven National Laboratory concludes 25 years of operation, preserving not only its vast data holdings ($\sim$1 ExaByte) but also the embedded scientific knowledge becomes a critical priority. The RHIC Data and Analysis Preservation Plan (DAPP) introduces an AI-powered assistant system that provides natural language access to documentation, workflows, and software, with the aim of supporting reproducibility, education, and future discovery. B…

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Kevin Li, Manuel Brack, Sudeep Katakol, Hareesh Ravi, Ajinkya Kale
https://arxiv.org/abs/2510.12789 https…

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains diffusion models' ability to perform cross-modal reasoning and knowledge transfer. Prior attempts to bridge this gap often use the last layer information from VLM, employ multiple visual encoders, or train large unified models jointly for text and image generation, which demands substantial computational resources and l…

Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering
Hanna Abi Akl
https://arxiv.org/abs/2509.10249

Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering
Recent advances in Language Models (LMs) have failed to mask their shortcomings particularly in the domain of reasoning. This limitation impacts several tasks, most notably those involving ontology engineering. As part of a PhD research, we investigate the consequences of incorporating formal methods on the performance of Small Language Models (SLMs) on reasoning tasks. Specifically, we aim to orient our work toward using SLMs to bootstrap ontology construction and set up a series of preliminar…

Chronologically Consistent Generative AI
Songrun He, Linying Lv, Asaf Manela, Jimmy Wu
https://arxiv.org/abs/2510.11677 https://arxiv.org/pdf/2510.11677

Chronologically Consistent Generative AI
We introduce a family of chronologically consistent, instruction-following large language models to eliminate lookahead bias. Each model is trained only on data available before a clearly defined knowledge-cutoff date, ensuring strict temporal separation from any post-cutoff data. The resulting framework offers (i) a simple, conversational chat interface, (ii) fully open, fixed model weights that guarantee replicability, and (iii) a conservative lower bound on forecast accuracy, isolating the s…

Information Asymmetry in Queues with Strategic Customers
Shunan Zheng, John Hasenbein
https://arxiv.org/abs/2510.09899 https://arxiv.org/pdf/2510.09899

Information Asymmetry in Queues with Strategic Customers
This paper studies information asymmetry in an unobservable single-server queueing system. While system managers have knowledge of the true arrival rate, customers may lack this information and instead form arbitrary beliefs. We propose a three-tier hierarchy of information asymmetry with increasing levels of information disclosure:customers keep private beliefs, customers are aware of the beliefs of others, and customers know the true arrival rate. Within this framework, the effects of the bel…

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Xiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Wenjie Zhang
https://arxiv.org/abs/2510.12434

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-based RAG methods suffer from three major limitations: static retrieval planning, non-adaptive retrieval execution, and superficial use of KH structure and semantics, which constrain their ability to perform effective multi-hop question answering. To overcome these limitations, w…

Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control
Jiale Fan, Andrei Cramariuc, Tifanny Portela, Marco Hutter
https://arxiv.org/abs/2510.12363 https://

Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control
The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot motion control, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to a single robot embodiment. This work aims to define a paradigm for pretraining neural network models that enc…

How Students Use Generative AI for Software Testing: An Observational Study
Baris Ardic, Quentin Le Dilavrec, Andy Zaidman
https://arxiv.org/abs/2510.10551 https://

How Students Use Generative AI for Software Testing: An Observational Study
The integration of generative AI tools like ChatGPT into software engineering workflows opens up new opportunities to boost productivity in tasks such as unit test engineering. However, these AI-assisted workflows can also significantly alter the developer's role, raising concerns about control, output quality, and learning, particularly for novice developers. This study investigates how novice software developers with foundational knowledge in software testing interact with generative AI for e…

Deep Research Brings Deeper Harm
Shuo Chen, Zonggen Li, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu
https://arxiv.org/abs/2510.11851

Deep Research Brings Deeper Harm
Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detailed reports. However, the misuse of LLMs with such powerful capabilities can lead to even greater risks. This is especially concerning in high-stakes and knowledge-intensive domains such as biosecurity, where DR can generate a professional report containing detailed forbidden knowledge. Unfortunately, we have found su…

A Research Vision for Web Search on Emerging Topics
Alisa Rieger, Stefan Dietze, Ran Yu
https://arxiv.org/abs/2509.10212 https://arxiv.org/pdf/2509.10212…

A Research Vision for Web Search on Emerging Topics
We regularly encounter information on novel, emerging topics for which the body of knowledge is still evolving, which can be linked, for instance, to current events. A primary way to learn more about such topics is through web search. However, information on emerging topics is sparse and evolves dynamically as knowledge grows, making it uncertain and variable in quality and trustworthiness and prone to deliberate or accidental manipulation, misinformation, and bias. In this paper, we outline a …

SR-Scientist: Scientific Equation Discovery With Agentic AI
Shijie Xia, Yuhan Sun, Pengfei Liu
https://arxiv.org/abs/2510.11661 https://arxiv.org/pdf/2510.…

SR-Scientist: Scientific Equation Discovery With Agentic AI
Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation proposer within search algorithms like genetic programming. In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as co…

From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
Chengrui Xiang, Tengfei Ma, Xiangzheng Fu, Yiping Liu, Bosheng Song, Xiangxiang Zeng
https://arxiv.org/abs/2510.12181

From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
Drug repurposing plays a critical role in accelerating treatment discovery, especially for complex and rare diseases. Biomedical knowledge graphs (KGs), which encode rich clinical associations, have been widely adopted to support this task. However, existing methods largely overlook common-sense biomedical concept knowledge in real-world labs, such as mechanistic priors indicating that certain drugs are fundamentally incompatible with specific treatments. To address this gap, we propose LLaDR, …

The value of storage in electricity distribution: The role of storage
Dirk Lauinger, Deepjyoti Deka, Sungho Shin
https://arxiv.org/abs/2510.12435 https://a…

The value of storage in electricity distribution: The role of storage
Electricity distribution companies deploy battery storage to defer grid upgrades by reducing peak demand. In deregulated jurisdictions, such storage often sits idle because regulatory constraints bar participation in electricity markets. Here, we develop an optimization framework that, to our knowledge, provides the first formal model of market participation constraints within storage investment and operation planning. Applying the framework to a Massachusetts case study, we find that market pa…

What Slows Down FMware Development? An Empirical Study of Developer Challenges and Resolution Times
Zitao Wang, Zhimin Zhao, Michael W. Godfrey
https://arxiv.org/abs/2510.11138 …

What Slows Down FMware Development? An Empirical Study of Developer Challenges and Resolution Times
Foundation Models (FMs), such as OpenAI's GPT, are fundamentally transforming the practice of software engineering by enabling the development of \emph{FMware} -- applications and infrastructures built around these models. FMware systems now support tasks such as code generation, natural-language interaction, knowledge integration, and multi-modal content creation, underscoring their disruptive impact on current software engineering workflows. However, the design, implementation, and evolution …

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…

Detecting Text Manipulation in Images using Vision Language Models
Vidit Vidit, Pavel Korshunov, Amir Mohammadi, Christophe Ecabert, Ketan Kotwal, S\'ebastien Marcel
https://arxiv.org/abs/2509.10278

Detecting Text Manipulation in Images using Vision Language Models
Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing in these studies. We bridge this knowledge gap by analyzing closed- and open-source VLMs on different text manipulation datasets. Our results suggest that open-source models are getting closer, but still behind closed-source ones like GPT- 4o. Additionally, we benchmark image manipulation detection-specific VLMs for te…

ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
Linyi Yang, Yixuan Weng
https://arxiv.org/abs/2510.12194 https://

ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
Current deep-research agents run in a ''fire-and-forget'' mode: once started, they give users no way to fix errors or add expert knowledge during execution. We present ResearStudio, the first open-source framework that places real-time human control at its core. The system follows a Collaborative Workshop design. A hierarchical Planner-Executor writes every step to a live ''plan-as-document,'' a fast communication layer streams each action, file change, and tool call to a web interface. At any …

Is In-Context Learning Learning?
Adrian de Wynter
https://arxiv.org/abs/2509.10414 https://arxiv.org/pdf/2509.10414…

Is In-Context Learning Learning?
In-context learning (ICL) allows some autoregressive models to solve tasks via next-token prediction and without needing further training. This has led to claims about these model's ability to solve (learn) unseen tasks with only a few shots (exemplars) in the prompt. However, deduction does not always imply learning, as ICL does not explicitly encode a given observation. Instead, the models rely on their prior knowledge and the exemplars given, if any. We argue that, mathematically, ICL does c…

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Nojan Sheybani, Alessandro Pegoraro, Jonathan Knauer, Phillip Rieger, Elissa Mollakuqe, Farinaz Koushanfar, Ahmad-Reza Sadeghi
https://arxiv.org/abs/2509.09787

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Split Learning (SL) is a distributed learning approach that enables resource-constrained clients to collaboratively train deep neural networks (DNNs) by offloading most layers to a central server while keeping in- and output layers on the client-side. This setup enables SL to leverage server computation capacities without sharing data, making it highly effective in resource-constrained environments dealing with sensitive data. However, the distributed nature enables malicious clients to manipul…

DyKnow-RAG: Dynamic Knowledge Utilization Reinforcement Framework for Noisy Retrieval-Augmented Generation in E-commerce Search Relevance
Tingqiao Xu, Shaowei Yao, Chenhe Dong, Yiming Jin, Zerui Huang, Dan Ou, Haihong Tang
https://arxiv.org/abs/2510.11122

DyKnow-RAG: Dynamic Knowledge Utilization Reinforcement Framework for Noisy Retrieval-Augmented Generation in E-commerce Search Relevance
Accurately modeling query-item relevance drives e-commerce ranking, yet long-tail, knowledge-heavy, and fast-evolving queries exceed parametric LLM coverage. External context (reviews, attribute encyclopedias, UGC) can help but is noisy, and single-pass latency and cost forbid any clean-then-summarize step. The model must, per query, judge relevance and decide whether to use, partially use, or ignore the context. DyKnow-RAG is a dynamic noisy-RAG framework built on Group Relative Policy Optimiz…

Calibrated Dynamic Modeling for Force and Payload Estimation in Hydraulic Machinery
Lennart Werner, Pol Eyschen, Sean Costello, Pierluigi Micarelli, Marco Hutter
https://arxiv.org/abs/2510.11574

Calibrated Dynamic Modeling for Force and Payload Estimation in Hydraulic Machinery
Accurate real-time estimation of end effector interaction forces in hydraulic excavators is a key enabler for advanced automation in heavy machinery. Accurate knowledge of these forces allows improved, precise grading and digging maneuvers. To address these challenges, we introduce a high-accuracy, retrofittable 2D force- and payload estimation algorithm that does not impose additional requirements on the operator regarding trajectory, acceleration or the use of the slew joint. The approach is …

RAG-Anything: All-in-One RAG Framework
Zirui Guo, Xubin Ren, Lingrui Xu, Jiahao Zhang, Chao Huang
https://arxiv.org/abs/2510.12323 https://arxiv.org/pdf/25…

RAG-Anything: All-in-One RAG Framework
Retrieval-Augmented Generation (RAG) has emerged as a fundamental paradigm for expanding Large Language Models beyond their static training limitations. However, a critical misalignment exists between current RAG capabilities and real-world information environments. Modern knowledge repositories are inherently multimodal, containing rich combinations of textual content, visual elements, structured tables, and mathematical expressions. Yet existing RAG frameworks are limited to textual content, …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Yuchen Yan, Zhihua Liu, Hao Wang, Weiming Li, Xiaoshuai Hao
https://arxiv.org/abs/2510.11541 …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval…

EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Kunyu Peng, Di Wen, Kailun Yang, Jia Fu, Yufan Chen, Ruiping Liu, Jiamin Wu, Junwei Zheng, M. Saquib Sarfraz, Luc Van Gool, Danda Pani Paudel, Rainer Stiefelhagen
https://arxiv.org/abs/2510.12687

EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Open-Set Domain Generalization (OSDG) aims to enable deep learning models to recognize unseen categories in new domains, which is crucial for real-world applications. Label noise hinders open-set domain generalization by corrupting source-domain knowledge, making it harder to recognize known classes and reject unseen ones. While existing methods address OSDG under Noisy Labels (OSDG-NL) using hyperbolic prototype-guided meta-learning, they struggle to bridge domain gaps, especially with limited…

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Ting Li, Yang Yang, Yipeng Yu, Liang Yao, Guoqing Chao, Ruifeng Xu
https://arxiv.org/abs/2510.11584

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to enhance attack performance. However, it is unable to generate human-readable explanations, and exhibits poor generalizability. In the past few years, large language models (LLMs) have demonstrated powerful capabilities in text comprehension, generation, and reas…

How well can LLMs provide planning feedback in grounded environments?
Yuxuan Li, Victor Zhong
https://arxiv.org/abs/2509.09790 https://arxiv.org/pdf/2509.0…

How well can LLMs provide planning feedback in grounded environments?
Learning to plan in grounded environments typically requires carefully designed reward functions or high-quality annotated demonstrations. Recent works show that pretrained foundation models, such as large language models (LLMs) and vision language models (VLMs), capture background knowledge helpful for planning, which reduces the amount of reward design and demonstrations needed for policy learning. We evaluate how well LLMs and VLMs provide feedback across symbolic, language, and continuous c…

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
Shubham Chatterjee, Jeff Dalton
https://arxiv.org/abs/2510.11589 https://

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representa…

ExDoS: Expert-Guided Dual-Focus Cross-Modal Distillation for Smart Contract Vulnerability Detection
Yifan Jia, Ye Tian, Yanbin Wang, Jianguo Sun, Haitao Xu
https://arxiv.org/abs/2509.10252

ExDoS: Expert-Guided Dual-Focus Cross-Modal Distillation for Smart Contract Vulnerability Detection
The success of smart contracts has made them a target for attacks, but their closed-source nature often forces vulnerability detection to work on bytecode, which is inherently more challenging than source-code-based analysis. While recent studies try to align source and bytecode embeddings during training to transfer knowledge, current methods rely on graph-level alignment that obscures fine-grained structural and semantic correlations between the two modalities. Moreover, the absence of precis…

Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy, Jordan T. Ash
https://arxiv.org/abs/2510.11686

Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration wi…

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…

KnowRL: Teaching Language Models to Know What They Know
Sahil Kale, Devendra Singh Dhami
https://arxiv.org/abs/2510.11407 https://arxiv.org/pdf/2510.11407

KnowRL: Teaching Language Models to Know What They Know
Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more than one in five cases, making any response born of such internal uncertainty impossible to fully trust. Inspired by self-improvement reinforcement learning techniques that require minimal data, we present a simple but powerful framework KnowRL that strengthens a model's intern…

Comparing Knowledge Source Integration Methods for Optimizing Healthcare Knowledge Fusion in Rescue Operation
Mubaris Nadeem, Madjid Fathi
https://arxiv.org/abs/2510.09223 https…

Comparing Knowledge Source Integration Methods for Optimizing Healthcare Knowledge Fusion in Rescue Operation
In the field of medicine and healthcare, the utilization of medical expertise, based on medical knowledge combined with patients' health information is a life-critical challenge for patients and health professionals. The within-laying complexity and variety form the need for a united approach to gather, analyze, and utilize existing knowledge of medical treatments, and medical operations to provide the ability to present knowledge for the means of accurate patient-driven decision-making. One wa…

GeoGPT.RAG Technical Report
Fei Huang, Fan Wu, Zeqing Zhang, Qihao Wang, Long Zhang, Grant Michael Boquet, Hongyang Chen
https://arxiv.org/abs/2509.09686 https://

GeoGPT.RAG Technical Report
GeoGPT is an open large language model system built to advance research in the geosciences. To enhance its domain-specific capabilities, we integrated Retrieval Augmented Generation(RAG), which augments model outputs with relevant information retrieved from an external knowledge source. GeoGPT uses RAG to draw from the GeoGPT Library, a specialized corpus curated for geoscientific content, enabling it to generate accurate, context-specific answers. Users can also create personalized knowledge b…

VISaGE: Understanding Visual Generics and Exceptions
Stella Frank, Emily Allaway
https://arxiv.org/abs/2510.12548 https://arxiv.org/pdf/2510.12548

VISaGE: Understanding Visual Generics and Exceptions
While Vision Language Models (VLMs) learn conceptual representations, in the form of generalized knowledge, during training, they are typically used to analyze individual instances. When evaluation instances are atypical, this paradigm results in tension between two priors in the model. The first is a pragmatic prior that the textual and visual input are both relevant, arising from VLM finetuning on congruent inputs; the second is a semantic prior that the conceptual representation is generally…

MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs
Yuechun Yu, Han Ying, Haoan Jin, Wenjian Jiang, Dong Xian, Binghao Wang, Zhou Yang, Mengyue Wu
https://arxiv.org/abs/2510.12224

MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs
The reliable evaluation of large language models (LLMs) in medical applications remains an open challenge, particularly in capturing the complexity of multi-turn doctor-patient interactions that unfold in real clinical environments. Existing evaluation methods typically rely on post hoc review of full conversation transcripts, thereby neglecting the dynamic, context-sensitive nature of medical dialogues and the evolving informational needs of patients. In this work, we present MedKGEval, a nove…

Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
Matthew Adrian, Yunsie Chung, Kevin Boyd, Saee Paliwal, Srimukh Prasad Veccham, Alan C. Cheng
https://arxiv.org/abs/2510.12719

Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
Chemical pretrained models, sometimes referred to as foundation models, are receiving considerable interest for drug discovery applications. The general chemical knowledge extracted from self-supervised training has the potential to improve predictions for critical drug discovery endpoints, including on-target potency and ADMET properties. Multi-task learning has previously been successfully leveraged to improve predictive models. Here, we show that enabling multitasking in finetuning of chemic…

CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms
Peiyuan Gong, Feiran Zhu, Yaqi Yin, Chenglei Dai, Chao Zhang, Kai Zheng, Wentian Bao, Jiaxin Mao, Yi Zhang
https://arxiv.org/abs/2510.10095

CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms
Short-video platforms have rapidly become a new generation of information retrieval systems, where users formulate queries to access desired videos. However, user queries, especially long-tail ones, often suffer from spelling errors, incomplete phrasing, and ambiguous intent, resulting in mismatches between user expectations and retrieved results. While large language models (LLMs) have shown success in long-tail query rewriting within e-commerce, they struggle on short-video platforms, where p…

Semantic-Condition Tuning: Fusing Graph Context with Large Language Models for Knowledge Graph Completion
Ruitong Liu, Yan Wen, Te Sun, Yunjia Wu, Pingyang Huang, Zihang Yu, Siyuan Li
https://arxiv.org/abs/2510.08966

Semantic-Condition Tuning: Fusing Graph Context with Large Language Models for Knowledge Graph Completion
Fusing Knowledge Graphs with Large Language Models is crucial for knowledge-intensive tasks like knowledge graph completion. The prevailing paradigm, prefix-tuning, simply concatenates knowledge embeddings with text inputs. However, this shallow fusion overlooks the rich relational semantics within KGs and imposes a significant implicit reasoning burden on the LLM to correlate the prefix with the text. To address these, we propose Semantic-condition Tuning (SCT), a new knowledge injection parad…

Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
Linfeng Gao, Baolong Bi, Zheng Yuan, Le Wang, Zerui Chen, Zhimin Wei, Shenghua Liu, Qinggang Zhang, Jinsong Su
https://arxiv.org/abs/2510.12460

Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance the factuality of Large Language Models (LLMs). However, existing RAG systems often suffer from an unfaithfulness issue, where the model's response contradicts evidence from the retrieved context. Existing approaches to improving contextual faithfulness largely rely on external interventions, such as prompt engineering, decoding constraints, or reward-based fine-tuning. These works treat the LLM as a black box an…

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
Rui Lu, Zhenyu Hou, Zihan Wang, Hanchen Zhang, Xiao Liu, Yujiang Li, Shi Feng, Jie Tang, Yuxiao Dong
https://arxiv.org/abs/2509.10446

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon reasoning capacity with browsing tools and the lack of sufficiently difficult supervised data. To address these challenges, we present DeepDive to advance deep search agents. First, we propose a strategy to automatically synthesize complex, difficult, and hard-…

Compartmentalised Agentic Reasoning for Clinical NLI
Ma\"el Jullien, Lei Xu, Marco Valentino, Andr\'e Freitas
https://arxiv.org/abs/2509.10222 https://

Compartmentalised Agentic Reasoning for Clinical NLI
A common assumption holds that scaling data and parameters yields increasingly structured, generalisable internal representations. We interrogate this assumption in clinical natural language inference (NLI) by adopting a benchmark decomposed into four reasoning families, Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction, and introducing CARENLI, a Compartmentalised Agentic Reasoning for Clinical NLI that separates knowledge access from principled in…

Wave-Based Semantic Memory with Resonance-Based Retrieval: A Phase-Aware Alternative to Vector Embedding Stores
Aleksandr Listopad
https://arxiv.org/abs/2509.09691 https://

Wave-Based Semantic Memory with Resonance-Based Retrieval: A Phase-Aware Alternative to Vector Embedding Stores
Conventional vector-based memory systems rely on cosine or inner product similarity within real-valued embedding spaces. While computationally efficient, such approaches are inherently phase-insensitive and limited in their ability to capture resonance phenomena crucial for meaning representation. We propose Wave-Based Semantic Memory, a novel framework that models knowledge as wave patterns $ψ(x) = A(x) e^{iϕ(x)}$ and retrieves it through resonance-based interference. This approach preserves…

MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
Bo Cheng, Xu Wang, Jinda Liu, Yi Chang, Yuan Wu
https://arxiv.org/abs/2510.11598 https://

MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles to efficiently leverage inter-task knowledge in complex multi-task learning scenarios, often requiring substantial task-specific data to achieve optimal performance. To address this limitation, we introduce MeTA-LoRA, a two-stage optimization framework that …

DB3 Team's Solution For Meta KDD Cup' 25
Yikuan Xia, Jiazun Chen, Yirui Zhan, Suifeng Zhao, Weipeng Jiang, Chaorui Zhang, Wei Han, Bo Bai, Jun Gao
https://arxiv.org/abs/2509.09681

DB3 Team's Solution For Meta KDD Cup' 25
This paper presents the db3 team's winning solution for the Meta CRAG-MM Challenge 2025 at KDD Cup'25. Addressing the challenge's unique multi-modal, multi-turn question answering benchmark (CRAG-MM), we developed a comprehensive framework that integrates tailored retrieval pipelines for different tasks with a unified LLM-tuning approach for hallucination control. Our solution features (1) domain-specific retrieval pipelines handling image-indexed knowledge graphs, web sources, and multi-turn c…

Teaching Language Models to Faithfully Express their Uncertainty
Bryan Eikema, Evgenia Ilia, Jos\'e G. C. de Souza, Chrysoula Zerva, Wilker Aziz
https://arxiv.org/abs/2510.12587

Teaching Language Models to Faithfully Express their Uncertainty
Large language models (LLMs) often miscommunicate their uncertainty: repeated queries can produce divergent answers, yet generated responses are typically unhedged or hedged in ways that do not reflect this variability. This conveys unfaithful information about the uncertain state of the LLMs' knowledge, creating a faithfulness gap that affects even strong LLMs. We introduce Faithful Uncertainty Tuning (FUT): a fine-tuning approach that teaches instruction-tuned LLMs to express uncertainty fait…

EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
Zirui Liao
https://arxiv.org/abs/2510.08958 https://arxiv.org/pdf/2510.08958

EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
Cognitive neuroscience research indicates that humans leverage cues to activate entity-centered memory traces (engrams) for complex, multi-hop recollection. Inspired by this mechanism, we introduce EcphoryRAG, an entity-centric knowledge graph RAG framework. During indexing, EcphoryRAG extracts and stores only core entities with corresponding metadata, a lightweight approach that reduces token consumption by up to 94\% compared to other structured RAG systems. For retrieval, the system first ex…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/3]:
- Polish-English medical knowledge transfer: A new benchmark and results
{\L}ukasz Grzybowski, Jakub Pokrywka, Micha{\l} Ciesi\'o{\l}ka, Jeremi I. Kaczmarek, Marek Kubis

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…

Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
Marco Del Tredici, Jacob McCarran, Benjamin Breen, Javier Aspuru Mijares, Weichen Winston Yin, Jacob M. Taylor, Frank Koppens, Dirk Englund
https://arxiv.org/abs/2510.12787

Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
We present Ax-Prover, a multi-agent system for automated theorem proving in Lean that can solve problems across diverse scientific domains and operate either autonomously or collaboratively with human experts. To achieve this, Ax-Prover approaches scientific problem solving through formal proof generation, a process that demands both creative reasoning and strict syntactic rigor. Ax-Prover meets this challenge by equipping Large Language Models (LLMs), which provide knowledge and reasoning, wit…

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…

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Hanyang Chen, Mark Zhao, Rui Yang, Qinwei Ma, Ke Yang, Jiarui Yao, Kangrui Wang, Hao Bai, Zhenhailong Wang, Rui Pan, Mengchao Zhang, Jose Barreiros, Aykut Onol, ChengXiang Zhai, Heng Ji, Manling Li, Huan Zhang, Tong Zhang
https://arxiv…

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning …

BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)
Tomas Ruiz, Siyao Peng, Barbara Plank, Carsten Schwemmer
https://arxiv.org/abs/2510.12516

BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)
Test-time scaling is a family of techniques to improve LLM outputs at inference time by performing extra computation. To the best of our knowledge, test-time scaling has been limited to domains with verifiably correct answers, like mathematics and coding. We transfer test-time scaling to the LeWiDi-2025 tasks to evaluate annotation disagreements. We experiment with three test-time scaling methods: two benchmark algorithms (Model Averaging and Majority Voting), and a Best-of-N sampling method. T…

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen
https://arxiv.org/abs/2510.12476

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no prior work has examined personalized machine-generated text (MGT) detection. In this paper, we introduce \dataset, the first benchmark for evaluating detector robustness in personalized settings, built from literary and blog texts paired with their LLM-generated…