Tootfinder

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Quantum-Assisted Correlation Clustering
Antonio Macaluso, Supreeth Mysore Venkatesh, Diego Arenas, Matthias Klusch, Andreas Dengel

BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
Shiqiao Zhou, Holger Sch\"oner, Huanbo Lyu, Edouard Fouch\'e, Shuo Wang
https://arxiv.org/abs/2509.00622

BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
Time series forecasting is a long-standing and highly challenging research topic. Recently, driven by the rise of large language models (LLMs), research has increasingly shifted from purely time series methods toward harnessing textual modalities to enhance forecasting performance. However, the vast discrepancy between text and temporal data often leads current multimodal architectures to over-emphasise one modality while neglecting the other, resulting in information loss that harms forecastin…

Optimal signals assignment for eBay View Item page
Matan Mandelbrod, Biwei Jiang, Giald Wagner, Tal Franji, Guy Feigenblat
https://arxiv.org/abs/2510.01198 https://

Optimal signals assignment for eBay View Item page
Signals are short textual or visual snippets displayed on the eBay View-Item (VI) page, providing additional, contextual information for users about the viewed item. The aim in displaying the signals is to facilitate intelligent purchase and to incentivise engagement. In this paper, we present two approaches for developing statistical models that optimally populate the VI page with signals. Both approaches were A/B tested, and yielded significant increase in business metrics.

Replaced article(s) found for math.CT. https://arxiv.org/list/math.CT/new
[1/1]:
- Multicategories from Symmetric Monoidal Categories
A. D. Elmendorf
https://…

Replaced article(s) found for physics.ed-ph. https://arxiv.org/list/physics.ed-ph/new
[1/1]:
- Can Large Language Models Correctly Interpret Equations with Errors?
Lachlan McGinness, Peter Baumgartner

Tell Congress: NO Funding for Primate Breeding! #AnimalRights

URGENT: Tell Congress NO to Funding Primate Breeding!
Right now, Congress is working on the 2025 federal budget, and the Senate Appropriations Committee has allocated a staggering $30 million to expand primate breeding and research at National Primate Research Centers. This funding will support invasive, unethical experiments on primates—causing unimaginable suffering while advancing unreliable science that fails over 90% of the time in human clinical trials. 🔬 Despite these facts, the NIH asked for $10 million, but the Senate has tripled th…

Speculative Design of Equitable Robotics: Queer Fictions and Futures
Minja Axelsson
https://arxiv.org/abs/2509.01643 https://arxiv.org/pdf/2509.01643

Speculative Design of Equitable Robotics: Queer Fictions and Futures
This paper examines the speculative topic of equitable robots through an exploratory essay format. It focuses specifically on robots by and for LGBTQ+ populations. It aims to provoke thought and conversations in the field about what aspirational queer robotics futures may look like, both in the arts and sciences. First, it briefly reviews the state-of-the-art of queer robotics in fiction and science, drawing together threads from each. Then, it discusses queering robots through three speculativ…

Replaced article(s) found for math.CA. https://arxiv.org/list/math.CA/new
[1/1]:
- $q$-Hypergeometric Orthogonal Polynomials with $q=-1$
Luis Verde-Star
https:/…

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- Fast solvers for Tokamak fluid models with PETSC
Mark F. Adams, Jin Chen, Benjamin Sturdevant

Replaced article(s) found for math.FA. https://arxiv.org/list/math.FA/new
[1/1]:
- The algebraic structure of hyperinterpolation class on the sphere
Congpei An, Jiashu Ran

Replaced article(s) found for q-fin.CP. https://arxiv.org/list/q-fin.CP/new
[1/1]:
- Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio O...
Juhyeong Kim, Sungyoon Choi, Youngbin Lee, Yejin Kim, Yongmin Choi, Yongjae Lee

Replaced article(s) found for physics.chem-ph. https://arxiv.org/list/physics.chem-ph/new
[1/1]:
- The Enduring Relevance of Semiempirical Quantum Mechanics
Jonathan E. Moussa

Crosslisted article(s) found for physics.ins-det. https://arxiv.org/list/physics.ins-det/new
[1/1]:
- WISPFI Experiment: Prototype Development
Josep Maria Batllori, Dieter Horns, Marios Maroudas

Replaced article(s) found for cond-mat.mes-hall. https://arxiv.org/list/cond-mat.mes-hall/new
[1/1]:
- Theory of Valley Splitting in Si/SiGe Spin-Qubits: Interplay of Strain, Resonances and Random All...
Abel Thayil, Lasse Ermoneit, Markus Kantner

SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
Shicheng Liu, Kai Sun, Lisheng Fu, Xilun Chen, Xinyuan Zhang, Zhaojiang Lin, Rulin Shao, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
https://arxiv.org/abs/2510.01832

SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging. Existing methods either lack generalization or are resource-intensive due to per-page LLM inference. In this paper, we introduce SCRIBES (SCRIpt-Based Semi-Structured Content Extraction at Web-Scale), a novel reinforcement learning framework that leverages layo…

Site : "Check out these designers"
Me : *Clicks Link*
Me : *Lands on Instagram page*
Instagram : *Displays limited page under create an account modal*
Me : *Closes tab*
#instagram

I recommend reading the diffs. Making git docs systematically less user-hostile is a significant service to our profession. Thanks Julia!
https://social.jvns.ca/@b0rk/115135734775061433

Can we cite Wikipedia? What if Wikipedia was more reliable than its detractors ?
Mohamed El Louadi
https://arxiv.org/abs/2509.02462 https://arxiv.org/pdf/2…

Can we cite Wikipedia? What if Wikipedia was more reliable than its detractors ?
Wikipedia, a widely successful encyclopedia recognized in academic circles and used by both students and professors alike, has led educators to question whether it can be cited as an information source, given its widespread use for this very purpose. The dilemma quickly emerged: if Wikipedia has become the go-to information source for so many, why can't it be cited? If consulting and using Wikipedia as a source of information is permitted, why does it become controversial the moment one attempt…

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/2]:
- ROI-GS: Interest-based Local Quality 3D Gaussian Splatting
Quoc-Anh Bui, Gilles Rougeron, G\'eraldine Morin, Simone Gasparini

AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent
Jingru Fan, Yufan Dang, Jingyao Wu, Huatao Li, Runde Yang, Xiyuan Yang, Yuheng Wang, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Dahai Li, Chen Qian
https://arxiv.org/abs/2509.02444

AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent
With the raid evolution of large language models and multimodal foundation models, the mobile-agent landscape has proliferated without converging on the fundamental challenges. This paper identifies four core problems that must be solved for mobile agents to deliver practical, scalable impact: (1) generalization across tasks, modalities, apps, and devices; (2) accuracy, specifically precise on-screen interaction and click targeting; (3) long-horizon capability for sustained, multi-step goals; a…

A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle
Ziteng Gao, Jiaqi Qu, Chaoyu Chen
https://arxiv.org/abs/2509.01611 https:/…

A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle
Lane change decision-making for autonomous vehicles is a complex but high-reward behavior. In this paper, we propose a hybrid input based deep reinforcement learning (DRL) algorithm, which realizes abstract lane change decisions and lane change actions for autonomous vehicles within traffic flow. Firstly, a surrounding vehicles trajectory prediction method is proposed to reduce the risk of future behavior of surrounding vehicles to ego vehicle, and the prediction results are input into the rein…

Crosslisted article(s) found for math.CA. https://arxiv.org/list/math.CA/new
[1/1]:
- On sharp Strichartz estimate for hyperbolic Schr\"{o}dinger equation on $\mathbb{T}^3$
Baoping Liu, Xu Zheng

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation
Dong Liu, Yanxuan Yu, Jiayi Zhang, Yifan Li, Ben Lengerich, Ying Nian Wu

Replaced article(s) found for math.FA. https://arxiv.org/list/math.FA/new
[1/1]:
- A characterization of completely alternating functions
Monojit Bhattacharjee, Rajkamal Nailwal

Replaced article(s) found for physics.ed-ph. https://arxiv.org/list/physics.ed-ph/new
[1/1]:
- Learning quantum properties with informationally redundant external representations: An eye-track...
Eva Rexigel, Linda Qerimi, Jonas Bley, Sarah Malone, Stefan K\"uchemann, J…

Gas Electroluminescence in a Dual Phase Xenon-Doped Argon Detector
James W. Kingston, Jianyang Qi, Jingke Xu, Ethan P. Bernard, Adam D. Tidball, Alec W. Peck, Nathaniel S. Bowden, Mani Tripathi, Kaixuan Ni, Shawn Westerdale
https://arxiv.org/abs/2510.02261

Gas Electroluminescence in a Dual Phase Xenon-Doped Argon Detector
Noble element detectors using argon or xenon as the detection medium are widely used in the searches for rare neutrino and dark matter interactions. Xenon doping in liquid argon can preserve attractive properties of an argon target while enhancing the detectable signals with properties of xenon. In this work, we deployed a dual-phase liquid argon detector with up to 4% xenon doping in the liquid and studied its gas electroluminescence properties as a function of xenon concentration. At $\sim$2%…

Replaced article(s) found for physics.chem-ph. https://arxiv.org/list/physics.chem-ph/new
[1/1]:
- Machine learning for accuracy in density functional approximations
Johannes Voss

Journalists' Perceptions of Artificial Intelligence and Disinformation Risks
Urko Pe\~na-Alonso, Sim\'on Pe\~na-Fern\'andez, Koldobika Meso-Ayerdi
https://arxiv.org/abs/2509.01824

Journalists' Perceptions of Artificial Intelligence and Disinformation Risks
This study examines journalists' perceptions of the impact of artificial intelligence (AI) on disinformation, a growing concern in journalism due to the rapid expansion of generative AI and its influence on news production and media organizations. Using a quantitative approach, a structured survey was administered to 504 journalists in the Basque Country, identified through official media directories and with the support of the Basque Association of Journalists. This survey, conducted online an…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/5]:
- UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models
Yuhao Sun, Zhuoer Xu, Shiwen Cui, Kun Yang, Lingyun Yu, Yongdong Zhang, Hongtao Xie

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/2]:
- Development and Evaluation of an AI-Driven Telemedicine System for Prenatal Healthcare
Juan Barrientos, Michaelle P\'erez, Douglas Gonz\'alez, Favio Reyna, Julio Fajardo, Andrea Lara

Aleatoric Uncertainty from AI-based 6D Object Pose Predictors for Object-relative State Estimation
Thomas Jantos, Stephan Weiss, Jan Steinbrener
https://arxiv.org/abs/2509.01583

Aleatoric Uncertainty from AI-based 6D Object Pose Predictors for Object-relative State Estimation
Deep Learning (DL) has become essential in various robotics applications due to excelling at processing raw sensory data to extract task specific information from semantic objects. For example, vision-based object-relative navigation relies on a DL-based 6D object pose predictor to provide the relative pose between the object and the robot as measurements to the robot's state estimator. Accurately knowing the uncertainty inherent in such Deep Neural Network (DNN) based measurements is essential…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[12/15]:
- Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation
Vaishnav Vaidheeswaran, Dilith Jayakody, Samruddhi Mulay, Anand Lo, Md Mahbub Alam, Gabriel Spadon

The Stein-Weiss inequality in variable exponent Morrey spaces
David Cruz-Uribe, Arash Ghorbanalizadeh, Durvudkhan Suragan
https://arxiv.org/abs/2510.02235 https://

The Stein-Weiss inequality in variable exponent Morrey spaces
In this paper we prove the Stein-Weiss inequality in variable exponent Morrey spaces over a bounded domain. Our work extends earlier results in the variable exponent Lebesgue and Morrey settings, and utilizes new proof techniques applicable to Morrey spaces. We build on the foundational paper by Almeida, Hasanov, and Samko, which introduced Morrey spaces of variable exponents. As an application of our main result, we prove Poincaré-type inequalities using the approach of a recent paper by the …

The Application of VMM3A Readout for Multi-Grid Neutron Detectors
A. Backis, F. Piscitelli, D. Pfeiffer, J. R. M. Annand, M. Aouane, K. G. Fissum, K. Livingston, G. Mauri, D. Raspino
https://arxiv.org/abs/2510.01981

The Application of VMM3A Readout for Multi-Grid Neutron Detectors
The T-REX neutron spectrometer at the European Spallation Source will use Multi-Grid Technology, which is a voxelised proportional counter relying on\mathrm{^{10}B_{4}C} coatings to detect the scattered neutrons. Measurements of the position dependence of pulse-height and relative detection efficiency of a Multi-Grid prototype of the T-REX spectrometer are presented for two different schemes of signal-processing electronics based on the VMM3A ASIC and CREMAT technology. These measurements, inte…

Crosslisted article(s) found for physics.chem-ph. https://arxiv.org/list/physics.chem-ph/new
[1/1]:
- A Path towards Thresholdless Colloidal Quantum Dot Lasers by Solving Decades of Mythology on Opti...
Davide Zenatti, Patanjali Kambhampati

Crosslisted article(s) found for math.FA. https://arxiv.org/list/math.FA/new
[1/1]:
- Continuous Donoho-Elad Spark Uncertainty Principle
K. Mahesh Krishna
https…

[2025-10-03 Fri (UTC), no new articles found for physics.ed-ph Physics Education]
toXiv_bot_toot

Agentic Workflow for Education: Concepts and Applications
Yuan-Hao Jiang, Yijie Lu, Ling Dai, Jiatong Wang, Ruijia Li, Bo Jiang
https://arxiv.org/abs/2509.01517 https://

Agentic Workflow for Education: Concepts and Applications
With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a four-component model comprising self-reflection, tool invocation, task planning, and multi-agent collaboration. We distinguish AWE from traditional LLM-based linear interactions and propose a theoretical framework grounded in the von Neumann Multi-Agent System (MA…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/5]:
- Multi-bit Audio Watermarking
Luca A. Lanzend\"orfer, Kyle Fearne, Florian Gr\"otschla, Roger Wattenhofer

FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field
Fan Zhu, Yifan Zhao, Ziyu Chen, Biao Yu, Hui Zhu
https://arxiv.org/abs/2509.01547 https://

FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field
Visual SLAM has regained attention due to its ability to provide perceptual capabilities and simulation test data for Embodied AI. However, traditional SLAM methods struggle to meet the demands of high-quality scene reconstruction, and Gaussian SLAM systems, despite their rapid rendering and high-quality mapping capabilities, lack effective pose optimization methods and face challenges in geometric reconstruction. To address these issues, we introduce FGO-SLAM, a Gaussian SLAM system that emplo…

Bilinear and Fractional Leibniz Rules Beyond Euclidean Spaces: Weighted Besov and Triebel--Lizorkin Estimates
The Anh Bui
https://arxiv.org/abs/2510.01942 https://

Bilinear and Fractional Leibniz Rules Beyond Euclidean Spaces: Weighted Besov and Triebel--Lizorkin Estimates
We establish fractional Leibniz rules in weighted settings for nonnegative self-adjoint operators on spaces of homogeneous type. Using a unified method that avoids Fourier transforms, we prove bilinear estimates for spectral multiplier on weighted Hardy, Besov and Triebel-Lizorkin spaces. Our approach is flexible and applies beyond the Euclidean setting-covering, for instance, nilpotent Lie groups, Grushin operators, and Hermite expansions-thus extending classical Kato-Ponce inequalities. The f…

Dark characterization of Ti/Al LEKIDs for the search of axions in the W-band
Victor Rollano, Alejandro Pascual Laguna, David Rodriguez, Martino Calvo, Maria Teresa Magaz, Daniel Granados, Alessandro Monfardini, Alicia Gomez
https://arxiv.org/abs/2510.01913

Dark characterization of Ti/Al LEKIDs for the search of axions in the W-band
We report the electrical (dark) characterization of lumped-element kinetic inductance detectors (LEKIDs) fabricated from a Titanium/Aluminum bilayer and designed for broadband absorption in the W-band (75-110 GHz). These detectors are prototypes for future QCD axion search experiments within the Canfranc Axion Detection Experiment (CADEx), which demand sub 1e-19 W/Hz^0.5 sensitivities under low optical backgrounds. We combine a Mattis-Bardeen analysis to the temperature dependence of the detect…

Theoretical Exploration of the Diene-Transmissive Hetero-Diels-Alder Strategy Toward Boron-Functionalized Octahydroquinolines
Amine Rafik, Abdeljabbar Jaddi, Khalid Abbiche, Mohammed Salah, Miguel Carvajal, Khadija Marakchi
https://arxiv.org/abs/2510.02293

Theoretical Exploration of the Diene-Transmissive Hetero-Diels-Alder Strategy Toward Boron-Functionalized Octahydroquinolines
A diene-transmissive hetero-Diels-Alder strategy, grounded in previous experimental works and employing boronated dienophiles, is proposed for the synthesis of boron-bearing octahydroquinolines. To assess its feasibility, three representative reactions were investigated, and their thermodynamics were evaluated in toluene and acetonitrile at various temperatures using the WB97X-D level of theory. The peri-, regio-, stereo-, and $π$-facial selectivities were predicted. The reactions mechanisms w…

Replaced article(s) found for math.FA. https://arxiv.org/list/math.FA/new
[1/1]:
- On nonexpansiveness of metric projection operators on Wasserstein spaces
Anshul Adve, Alp\'ar M\'esz\'aros

Crosslisted article(s) found for physics.ed-ph. https://arxiv.org/list/physics.ed-ph/new
[1/1]:
- A principled way to think about AI in education: guidance for action based on goals, models of hu...
Noah D. Finkelstein

Ireland in 2057: Projections using a Geographically Diverse Dynamic Microsimulation
Se\'an Caulfield Curley, Karl Mason, Patrick Mannion
https://arxiv.org/abs/2509.01446 htt…

Ireland in 2057: Projections using a Geographically Diverse Dynamic Microsimulation
This paper presents a dynamic microsimulation model developed for Ireland, designed to simulate key demographic processes and individual life-course transitions from 2022 to 2057. The model captures four primary events: births, deaths, internal migration, and international migration, enabling a comprehensive examination of population dynamics over time. Each individual in the simulation is defined by five core attributes: age, sex, marital status, highest level of education attained, and econom…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/5]:
- Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
Shayegani, Hines, Dong, Abu-Ghazaleh, Lutz, Whitehead, Balachandran, Nushi, Vineet

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu, Chao Sun, Rongzhou Zhang, Guanyu Zhou, Lijie Wen, Xuming Hu
https://arxiv.org/abs/2509.00723

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
Recently, Omni-modal large language models (OLLMs) have sparked a new wave of research, achieving impressive results in tasks such as audio-video understanding and real-time environment perception. However, hallucination issues still persist. Similar to the bimodal setting, the priors from the text modality tend to dominate, leading OLLMs to rely more heavily on textual cues while neglecting visual and audio information. In addition, fully multimodal scenarios introduce new challenges. Most exi…

Analyzing Reluctance to Ask for Help When Cooperating With Robots: Insights to Integrate Artificial Agents in HRC
Ane San Martin, Michael Hagenow, Julie Shah, Johan Kildal, Elena Lazkano
https://arxiv.org/abs/2509.01450

Analyzing Reluctance to Ask for Help When Cooperating With Robots: Insights to Integrate Artificial Agents in HRC
As robot technology advances, collaboration between humans and robots will become more prevalent in industrial tasks. When humans run into issues in such scenarios, a likely future involves relying on artificial agents or robots for aid. This study identifies key aspects for the design of future user-assisting agents. We analyze quantitative and qualitative data from a user study examining the impact of on-demand assistance received from a remote human in a human-robot collaboration (HRC) assem…

The centered maximal operator removes the non-concave Cantor part from the gradient
Panu Lahti, Julian Weigt
https://arxiv.org/abs/2510.01936 https://arxiv…

The centered maximal operator removes the non-concave Cantor part from the gradient
We study regularity of the centered Hardy--Littlewood maximal function $M f$ of a function $f$ of bounded variation in $\mathbb R^d$, $d\in \mathbb N$. In particular, we show that at $|D^c f|$-a.e. point $x$ where $f$ has a non-concave blow-up, it holds that $M f(x)>f^*(x)$. We further deduce from this that if the variation measure of $f$ has no jump part and its Cantor part has non-concave blow-ups, then BV regularity of $M f$ can be upgraded to Sobolev regularity.

BabyMOSS stitched sensors: results of characterisation tests for ALICE ITS3 upgrade
Alessandro Sturniolo (on behalf of the ALICE Collaboration)
https://arxiv.org/abs/2510.01834 …

BabyMOSS stitched sensors: results of characterisation tests for ALICE ITS3 upgrade
During the Long Shutdown 3 (LS3, scheduled 2026-2030), the innermost 3 layers (Inner Barrel, or IB) of the present ALICE ITS2 will be replaced with large-area, flexible, stitched CMOS 65 nm sensors, arranged in 2 half-barrels of 3 half-layers each, in the framework of the ITS3 upgrade project. For the first time in a High Energy Physics experiment, such large-scale sensors will be bent into truly half-cylindrical shaped half-layers, requiring little mechanical support. This will also help lower…

Microscopic Structure of Aqueous Alkylamine mixtures: a Computer Simulation Study
Martina Po\v{z}ar, Lena Friedrich, Bernarda Lovrin\v{c}evi\'c, Michael Paulus, Christian Sternemann, Aur\'elien Perera
https://arxiv.org/abs/2510.02146

Microscopic Structure of Aqueous Alkylamine mixtures: a Computer Simulation Study
Aqueous alkylamine mixtures are studied by computer simulations in order to understand the microscopic origin of the water rich side prominent x-ray scattering pre-peaks reported in a recent study. These pre-peaks are puzzling in view of the apparently contradicting facts that neat amines show pre-peaks much weaker than neat alkanols, while water-rich aqueous alcohols do not. These observations can be intuitively rationalized by noting that the amine head group have two hydrogen atoms when the …

Power series statistical convergence and an abstract Korovkin-type approximation theorem
Dilek S\"oylemez, Mehmet \"Unver
https://arxiv.org/abs/2509.02557 https://

Power series statistical convergence and an abstract Korovkin-type approximation theorem
This paper establishes an abstract Korovkin-type approximation theorem in general spaces, extending the framework of approximation theory to accommodate broader contexts. A critical result supporting this theorem is the proof that any $P$-statistically convergent sequence contains a classically convergent subsequence over a density $1$ set, which plays a foundational role in the analysis. As a conclusion, we investigate the convergence of the $r$-th order generalization of linear operators, whi…

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
Shiji Zhao, Ranjie Duan, Jiexi Liu, Xiaojun Jia, Fengxiang Wang, Cheng Wei, Ruoxi Cheng, Yong Xie, Chang Liu, Qing Guo, Jialing Tao, Hui Xue, Xingxing Wei
https://arxiv.org/abs/2509.01444…

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit strong reasoning skills, enabling them to infer user intent more accurately and respond appropriately. However, both LLMs and LRMs face the potential safety risks under jailbreak attacks, which raise concerns about their safety capabilities. Current safety evalua…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- HiSpec: Hierarchical Speculative Decoding for LLMs
Avinash Kumar, Sujay Sanghavi, Poulami Das

On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations
Albert Sadowski, Jaros{\l}aw A. Chudziak
https://arxiv.org/abs/2509.00710 https:…

On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations
Legal reasoning requires both precise interpretation of statutory language and consistent application of complex rules, presenting significant challenges for AI systems. This paper introduces a modular multi-agent framework that decomposes legal reasoning into distinct knowledge acquisition and application stages. In the first stage, specialized agents extract legal concepts and formalize rules to create verifiable intermediate representations of statutes. The second stage applies this knowledg…

TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation
Peiran Liu, Qiang Zhang, Daojie Peng, Lingfeng Zhang, Yihao Qin, Hang Zhou, Jun Ma, Renjing Xu, Yiding Ji
https://arxiv.org/abs/2509.01364

TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation
Object Navigation (ObjectNav) has made great progress with large language models (LLMs), but still faces challenges in memory management, especially in long-horizon tasks and dynamic scenes. To address this, we propose TopoNav, a new framework that leverages topological structures as spatial memory. By building and updating a topological graph that captures scene connections, adjacency, and semantic meaning, TopoNav helps agents accumulate spatial knowledge over time, retrieve key information, …

An existence theorem for sliding minimal sets
Guy David, Camille Labourie
https://arxiv.org/abs/2510.01905 https://arxiv.org/pdf/2510.01905

An existence theorem for sliding minimal sets
We prove an existence theorem for the sliding boundary variant of the Plateau problem for $2$-dimensional sets in $\mathbb{R}^n$. The simplest case of sufficient condition is when $n=3$ and the boundary $Γ$ is a finite disjoint union of smooth closed curves contained in the boundary of a convex body, but the main point of our sufficient condition is to prevent the limits in measure of a minimizing sequence to have singularities of type $\mathbb{Y}$ along $Γ$.

Study of the response of a large volume TPC prototype for the CYGNO experiment at LNGS
Rita Antonietti
https://arxiv.org/abs/2510.01646 https://arxiv.org/p…

Study of the response of a large volume TPC prototype for the CYGNO experiment at LNGS
Astrophysical and cosmological evidence strongly supports the existence of Dark Matter (DM), yet no candidate particle is predicted by the Standard Model (SM) of particle physics. Among the most studied and hypotheses are Weakly Interacting Massive Particle (WIMPs), which could account for the observed relic DM density through weak interactions in the early Universe. Direct detection experiments aim to observe low-energy nuclear recoils induced by DM interactions, requiring detectors with very …

Imaging and controlling electron motion and chemical structural dynamics of biological system in real time and space
Ligong Zhao, Mohamed Sennary, Dina Hussein, Anaisa Coelho, Tingting Yang, Mohamed Y. El-Naggar, Mohammed Th. Hassan
https://arxiv.org/abs/2510.02105

Imaging and controlling electron motion and chemical structural dynamics of biological system in real time and space
Ultrafast electron microscopy (UEM) has found widespread applications in physics, chemistry, and materials science, enabling real-space imaging of dynamics on ultrafast timescales. Recent advances have pushed the temporal resolution of UEM into the attosecond regime, enabling the attomicroscopy technique to directly visualize electron motion. In this work, we extend the capabilities of this powerful imaging tool to investigate ultrafast electron dynamics in a biological system by imaging and co…

Compactness of compositions of strictly singular operators on direct sums of Baernstein, Schreier and $\ell_p$-spaces
Niels Jakob Laustsen, Henrik Wirzenius
https://arxiv.org/abs/2509.02405

Compactness of compositions of strictly singular operators on direct sums of Baernstein, Schreier and $\ell_p$-spaces
Let $X$ be the direct sum of finitely many Banach spaces chosen from the following three families: (i) the Baernstein spaces $B_p$ for $1

Assessing prompting frameworks for enhancing literature reviews among university students using ChatGPT
Aminul Islam, Mukta Bansal, Lena Felix Stephanie, Poernomo Gunawan, Pui Tze Sian, Sabrina Luk, Eunice Tan, Hortense Le Ferrand
https://arxiv.org/abs/2509.01128

Assessing prompting frameworks for enhancing literature reviews among university students using ChatGPT
Writing literature reviews is a common component of university curricula, yet it often poses challenges for students. Since generative artificial intelligence (GenAI) tools have been made publicly accessible, students have been employing them for their academic writing tasks. However, there is limited evidence of structured training on how to effectively use these GenAI tools to support students in writing literature reviews. In this study, we explore how university students use one of the most…

NetGent: Agent-Based Automation of Network Application Workflows
Jaber Daneshamooz, Eugene Vuong, Laasya Koduru, Sanjay Chandrasekaran, Arpit Gupta
https://arxiv.org/abs/2509.00625

NetGent: Agent-Based Automation of Network Application Workflows
We present NetGent, an AI-agent framework for automating complex application workflows to generate realistic network traffic datasets. Developing generalizable ML models for networking requires data collection from network environments with traffic that results from a diverse set of real-world web applications. However, using existing browser automation tools that are diverse, repeatable, realistic, and efficient remains fragile and costly. NetGent addresses this challenge by allowing users to …

Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning
Seonsoo Kim, Jun-Gill Kang, Taehong Kim, Seongil Hong
https://arxiv.org/abs/2509.01297 h…

Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning
In meta-learning and its downstream tasks, many methods rely on implicit adaptation to task variations, where multiple factors are mixed together in a single entangled representation. This makes it difficult to interpret which factors drive performance and can hinder generalization. In this work, we introduce a disentangled multi-context meta-learning framework that explicitly assigns each task factor to a distinct context vector. By decoupling these variations, our approach improves robustness…

A Note on the Paper "Localization of Zeros of Polar Polynomials on the Unit Disk"
Renato Alvarez-Nodarse, Kenier Castillo
https://arxiv.org/abs/2510.01703 https://

A Note on the Paper "Localization of Zeros of Polar Polynomials on the Unit Disk"
In this note we show that the only result of [Rocky Mountain J. Math. 54 (2024), no. 4, 995--1004] is nothing more than a misformulated version of an exercise from classical texts, presented with a flawed proof. To place the matter on firmer ground, we provide instead a direct solution of a more general problem.

Noise Modeling and Calibration of a Two-Stage Cryogenic Charge Amplifier for the SPLENDOR Experiment
Jadyn Anczarski, Owen Andrews, Taylor Aralis, Caleb Fink, Noah Kurinsky, Arran Phipps, Aditi Pradeep, Betty A. Young
https://arxiv.org/abs/2510.01463

Noise Modeling and Calibration of a Two-Stage Cryogenic Charge Amplifier for the SPLENDOR Experiment
The SPLENDOR Collaboration studies novel narrow-gap semiconductors and engineered a substrate agnostic detector platform to achieve $\mathcal{O}$(meV) energy sensitivity designed for low mass dark matter searches. This was achieved using low-capacitance and low-noise commercial CryoHEMTs in a split-stage topology integrated throughout a dilution refrigerator. Designed with a source-follower HEMT at the base temperature stage and a voltage amplifier at 4\,K, this amplifier has input-limited volt…

Theoretical investigation of real-fluid effects on the oxidation of hydrogen and syngas in high-pressure flow reactors
Mingrui Wang, Tianzhou Jiang, Ting Zhang, Hongjie Zhang, Hongqing Wu, Rongpei Jiang, Yang Li, Song Cheng
https://arxiv.org/abs/2510.01625

Theoretical investigation of real-fluid effects on the oxidation of hydrogen and syngas in high-pressure flow reactors
Investigating the high-pressure pyrolysis and oxidation of hydrogen and syngas is essential for developing accurate combustion models under real engine conditions. Accordingly, flow reactors have been increasingly used in these fundamental combustion research at high-pressure conditions to achieve chemical kinetic modeling. However, these previous chemical kinetic modeling for pyrolysis and oxidation has almost been completely conducted based on ideal gas assumption, which might fail at high-pr…

Approximation of rearrangements by polarizations
Gabriele Bianchi, Richard J. Gardner, Paolo Gronchi, Markus Kiderlen
https://arxiv.org/abs/2509.02162 https://

Approximation of rearrangements by polarizations
The symmetric decreasing rearrangement of functions on $\mathbb{R}^n$ features in several seminal inequalities, such as the Pólya-Szegő inequality. The latter was shown by the authors to hold for all smoothing rearrangements, a class that includes the more general $(k,n)$-Steiner rearrangement, as well as others introduced by Brock and by Solynin. The theory of rearrangements and their associated set maps is developed, with an emphasis on approximation, particularly by polarizations. The Pól…

Replaced article(s) found for cs.CY. https://arxiv.org/list/cs.CY/new
[1/1]:
- The Urban Impact of AI: Modeling Feedback Loops in Next-Venue Recommendation
Giovanni Mauro, Marco Minici, Luca Pappalardo

Toward a Holistic Multi-Criteria Trajectory Evaluation Framework for Autonomous Driving in Mixed Traffic Environment
Nouhed Naidja (L2S, VeDeCom), St\'ephane Font (L2S), Marc Revilloud (L2S), Guillaume Sandou (L2S)
https://arxiv.org/abs/2509.01291

Toward a Holistic Multi-Criteria Trajectory Evaluation Framework for Autonomous Driving in Mixed Traffic Environment
This paper presents a unified framework for the evaluation and optimization of autonomous vehicle trajectories, integrating formal safety, comfort, and efficiency criteria. An innovative geometric indicator, based on the analysis of safety zones using adaptive ellipses, is used to accurately quantify collision risks. Our method applies the Shoelace formula to compute the intersection area in the case of misaligned and time-varying configurations. Comfort is modeled using indicators centered on …

Social World Models
Xuhui Zhou, Jiarui Liu, Akhila Yerukola, Hyunwoo Kim, Maarten Sap
https://arxiv.org/abs/2509.00559 https://arxiv.org/pdf/2509.00559

Social World Models
Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems struggle to automatically structure and reason about these implicit social contexts. In this paper, we introduce a novel structured social world representation formalism (S3AP), designed to help AI systems reason more effectively about social dynamics. Following a POMDP-driven design, S3AP represents social interactions …

[2025-10-03 Fri (UTC), 5 new articles found for math.CA Classical Analysis and ODEs]
toXiv_bot_toot

[2025-10-03 Fri (UTC), 6 new articles found for physics.ins-det Instrumentation and Detectors]
toXiv_bot_toot

[2025-10-03 Fri (UTC), 4 new articles found for physics.chem-ph Chemical Physics]
toXiv_bot_toot

Molecules and Calder\'on-Zygmund operators with noncommuting kernels on $\mathrm{H}_1^c$
Antonio Ismael Cano-M\'armol
https://arxiv.org/abs/2509.01798 https://

Molecules and Calderón-Zygmund operators with noncommuting kernels on $\mathrm{H}_1^c$
We study the description of semicommutative Hardy spaces in terms of molecules. We use this characterization to obtain $\mathrm{H}_1^c - \mathrm{H}_1^c$ estimates for Calderón-Zygmund operators with kernels with values in a semifinite von Neumann algebra $\mathcal{M}$.

Towards Data-Driven Metrics for Social Robot Navigation Benchmarking
Pilar Bachiller-Burgos, Ulysses Bernardet, Luis V. Calderita, Pranup Chhetri, Anthony Francis, Noriaki Hirose, No\'e P\'erez, Dhruv Shah, Phani T. Singamaneni, Xuesu Xiao, Luis J. Manso
https://arxiv.org/abs/2509.01251

Towards Data-Driven Metrics for Social Robot Navigation Benchmarking
This paper presents a joint effort towards the development of a data-driven Social Robot Navigation metric to facilitate benchmarking and policy optimization. We provide our motivations for our approach and describe our proposal for storing rated social navigation trajectory datasets. Following these guidelines, we compiled a dataset with 4427 trajectories -- 182 real and 4245 simulated -- and presented it to human raters, yielding a total of 4402 rated trajectories after data quality assurance…

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci, Zhe Han, Yunpeng Zhang
https://arxiv.org/abs/2509.00543

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
This paper presents the development of an AI-powered workflow that uses Large Language Models (LLMs) to assist in drafting schematic architectural floor plans from natural language prompts. The proposed system interprets textual input to automatically generate layout options including walls, doors, windows, and furniture arrangements. It combines prompt engineering, a furniture placement refinement algorithm, and Python scripting to produce spatially coherent draft plans compatible with design …

Replaced article(s) found for math.CA. https://arxiv.org/list/math.CA/new
[1/1]:
- A degree one Carleson operator along the paraboloid
Lars Becker
https://

Hausdorff Operators on de Branges Spaces and Paley-Wiener spaces
A. R. Mirotin
https://arxiv.org/abs/2509.01757 https://arxiv.org/pdf/2509.01757

Hausdorff Operators on de Branges Spaces and Paley-Wiener spaces
For a class of de Branges spaces containing polynomials, sufficient and necessary conditions are given for the boundedness and compactness of the Hausdorff operators under consideration. For the Paly-Wiener spaces we reduce the study of our Hausdorff operators to classical integral ones. The operators that appeared are Carleman and therefore closeble in $L^2(\mathbb{R})$. We obtain also conditions for boundedness, compactness and nuclearity of our operators in the Paley-Wiener space as well as …

Replaced article(s) found for physics.chem-ph. https://arxiv.org/list/physics.chem-ph/new
[1/1]:
- Large Differences Between Stochastic and Deterministic Kinetics in a Simple Autocatalytic Reactio...
Tomasz Bednarek, Jakub J\k{e}drak

OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping
Jianyu Dou, Yinan Deng, Jiahui Wang, Xingsi Tang, Yi Yang, Yufeng Yue
https://arxiv.org/abs/2509.01228

OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping
Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we propose OpenMulti, an open-vocabulary instance-level multi-agent distributed implicit mapping framework. Specifically, we introduce a Cross-Agent Instance Alignment module, which constructs an Instance…

LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
Li Weigang, Pedro Carvalho Brom, Lucas Ramson Siefert
https://arxiv.org/abs/2509.00510 https://…

LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
We propose a novel SuperBrain framework for collective intelligence, grounded in the co-evolution of large language models (LLMs) and human users. Unlike static prompt engineering or isolated agent simulations, our approach emphasizes a dynamic pathway from Subclass Brain to Superclass Brain: (1) A Subclass Brain arises from persistent, personalized interaction between a user and an LLM, forming a cognitive dyad with adaptive learning memory. (2) Through GA-assisted forward-backward evolution, …

Classification of Vision-Based Tactile Sensors: A Review
Haoran Li, Yijiong Lin, Chenghua Lu, Max Yang, Efi Psomopoulou, Nathan F Lepora
https://arxiv.org/abs/2509.02478 https:/…

Classification of Vision-Based Tactile Sensors: A Review
Vision-based tactile sensors (VBTS) have gained widespread application in robotic hands, grippers and prosthetics due to their high spatial resolution, low manufacturing costs, and ease of customization. While VBTSs have common design features, such as a camera module, they can differ in a rich diversity of sensing principles, material compositions, multimodal approaches, and data interpretation methods. Here, we propose a novel classification of VBTS that categorizes the technology into two pr…

Artificial Intelligence-Based Analysis of Ice Cream Melting Behavior Under Various Ingredients
Zhang Lai Bin, Zhen Bin It
https://arxiv.org/abs/2509.00507 https://

Artificial Intelligence-Based Analysis of Ice Cream Melting Behavior Under Various Ingredients
The stability of ice cream during melting is a critical factor for consumer's acceptance and product quality. With the commonly added stabilizer to improve texture, structure and slower melting as the factors to analyze. This report explores the effects of locust bean gum, guar gum, maltodextrin, and carrageenan on the melting behavior of homemade ice cream. The main objective was to assess how these additives influence melting resistance and to identify a more cost-effective recipe formulation…

Multi-Agent Data Visualization and Narrative Generation
Anton Wolter, Georgios Vidalakis, Michael Yu, Ankit Grover, Vaishali Dhanoa
https://arxiv.org/abs/2509.00481 https://

Multi-Agent Data Visualization and Narrative Generation
Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization field, multi-agent systems can be useful for employing agents throughout the entire data-to-communication pipeline. We present a lightweight multi-agent system that automates the data analysis workflow, from data exploration to generating coherent visual narratives for insight communication. Our approach combines a hybrid…

NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks
Yen-Che Chien, Kuang-Da Wang, Wei-Yao Wang, Wen-Chih Peng
https://arxiv.org/abs/2509.00446

NEWSAGENT: Benchmarking Multimodal Agents as Journalists with Real-World Newswriting Tasks
Recent advances in autonomous digital agents from industry (e.g., Manus AI and Gemini's research mode) highlight potential for structured tasks by autonomous decision-making and task decomposition; however, it remains unclear to what extent the agent-based systems can improve multimodal web data productivity. We study this in the realm of journalism, which requires iterative planning, interpretation, and contextual reasoning from multimodal raw contents to form a well structured news. We introd…

SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces
Brian Wang, Mani Srivastava
https://arxiv.org/abs/2509.00287 https://arxiv.org…

SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces
Modern urban spaces are equipped with an increasingly diverse set of sensors, all producing an abundance of multimodal data. Such multimodal data can be used to identify and reason about important incidents occurring in urban landscapes, such as major emergencies, cultural and social events, as well as natural disasters. However, such data may be fragmented over several sources and difficult to integrate due to the reliance on human-driven reasoning for identifying relationships between the mul…

SHERPA: A Model-Driven Framework for Large Language Model Execution
Boqi Chen, Kua Chen, Jos\'e Antonio Hern\'andez L\'opez, Gunter Mussbacher, D\'aniel Varr\'o, Amir Feizpour
https://arxiv.org/abs/2509.00272

SHERPA: A Model-Driven Framework for Large Language Model Execution
Recently, large language models (LLMs) have achieved widespread application across various fields. Despite their impressive capabilities, LLMs suffer from a lack of structured reasoning ability, particularly for complex tasks requiring domain-specific best practices, which are often unavailable in the training data. Although multi-step prompting methods incorporating human best practices, such as chain-of-thought and tree-of-thought, have gained popularity, they lack a general mechanism to cont…

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
Rimom Costa
https://arxiv.org/abs/2509.00251 https://arxiv.org/pdf/2509.00251

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
Large language models (LLMs) are fluent but largely static after pre-training; new or shifting knowledge is typically added with retrieval-augmented generation (RAG) or fine-tuning. RAG raises latency and engineering overhead and often fails to integrate facts; prompt engineering is brittle and can conflict with prior knowledge; fine-tuning is costly and risks catastrophic forgetting. We propose Instruction-Level Weight Shaping (ILWS): curated system instructions act as external, auditable pseu…

Universal Deep Research: Bring Your Own Model and Strategy
Peter Belcak, Pavlo Molchanov
https://arxiv.org/abs/2509.00244 https://arxiv.org/pdf/2509.00244

Universal Deep Research: Bring Your Own Model and Strategy
Deep research tools are among the most impactful and most commonly encountered agentic systems today. We observe, however, that each deep research agent introduced so far is hard-coded to carry out a particular research strategy using a fixed choice of tools. We introduce Universal Deep Research (UDR), a generalist agentic system that wraps around any language model and enables the user to create, edit, and refine their own entirely custom deep research strategies without any need for additiona…

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
Jinzhou Tang, Jusheng Zhang, Qinhan Lv, Sidi Liu, Jing Yang, Chengpei Tang, Keze Wang
https://arxiv.org/abs/2509.00189

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). However, existing paradigms face a critical trade-off. On one hand, reusable fixed workflows require manual reconfiguration upon environmental changes; on the other hand, flexible reactive loops fail to distill reasoning progress into transferable structures. We introduce Hierarchical Variable Agent (HiVA), a novel framew…

Virtual Group Knowledge and Group Belief in Topological Evidence Models (Extended Version)
Alexandru Baltag, Malvin Gattinger, Djanira Gomes
https://arxiv.org/abs/2509.00184 htt…

Virtual Group Knowledge and Group Belief in Topological Evidence Models (Extended Version)
We study notions of (virtual) group knowledge and group belief within multi-agent evidence models, obtained by extending the topological semantics of evidence-based belief and fallible knowledge from individuals to groups. We completely axiomatize and show the decidability of the logic of ("hard" and "soft") group evidence, and do the same for an especially interesting fragment of it: the logic of group knowledge and group belief. We also extend these languages with dynamic evidence-sharing ope…

Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online Budget
Davin Choo, Yohai Trabelsi, Fentabil Getnet, Samson Warkaye Lamma, Wondesen Nigatu, Kasahun Sime, Lisa Matay, Milind Tambe, St\'ephane Verguet
https://arxiv.org/abs/2509.00135…

Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online Budget
As part of nationwide efforts aligned with the United Nations' Sustainable Development Goal 3 on Universal Health Coverage, Ethiopia's Ministry of Health is strengthening health posts to expand access to essential healthcare services. However, only a fraction of this health system strengthening effort can be implemented each year due to limited budgets and other competing priorities, thus the need for an optimization framework to guide prioritization across the regions of Ethiopia. In this pape…

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
Ang Li, Zhihang Yuan, Yang Zhang, Shouda Liu, Yisen Wang
https://arxiv.org/abs/2509.00125

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
Reinforcement Learning with Verifiable Feedback (RLVF) has become a key technique for enhancing the reasoning abilities of Large Language Models (LLMs). However, its reliance on sparse, outcome based rewards, which only indicate if a final answer is correct or not, fails to provide granular guidance on the reasoning process itself. This limitation hinders efficient learning, as the model cannot distinguish between high quality and inefficient solutions, nor can it learn effectively from differe…

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
Manish Shukla
https://arxiv.org/abs/2509.00115 https://arxiv.org/pdf/2509.00115

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
Agentic artificial intelligence (AI) -- multi-agent systems that combine large language models with external tools and autonomous planning -- are rapidly transitioning from research laboratories into high-stakes domains. Our earlier "Basic" paper introduced a five-axis framework and proposed preliminary metrics such as goal drift and harm reduction but did not provide an algorithmic instantiation or empirical evidence. This "Advanced" sequel fills that gap. First, we revisit recent benchmarks a…

MODE: Mixture of Document Experts for RAG
Rahul Anand
https://arxiv.org/abs/2509.00100 https://arxiv.org/pdf/2509.00100

MODE: Mixture of Document Experts for RAG
Retrieval-Augmented Generation (RAG) often relies on large vector databases and cross-encoders tuned for large-scale corpora, which can be excessive for small, domain-specific collections. We present MODE (Mixture of Document Experts), a lightweight alternative that replaces fine-grained nearest-neighbor search with cluster-and-route retrieval. Documents are embedded, grouped into semantically coherent clusters, and represented by cached centroids. At query time, we route to the top centroid(s)…

Ensemble Debates with Local Large Language Models for AI Alignment
Ephraiem Sarabamoun
https://arxiv.org/abs/2509.00091 https://arxiv.org/pdf/2509.00091

Ensemble Debates with Local Large Language Models for AI Alignment
As large language models (LLMs) take on greater roles in high-stakes decisions, alignment with human values is essential. Reliance on proprietary APIs limits reproducibility and broad participation. We study whether local open-source ensemble debates can improve alignmentoriented reasoning. Across 150 debates spanning 15 scenarios and five ensemble configurations, ensembles outperform single-model baselines on a 7-point rubric (overall: 3.48 vs. 3.13), with the largest gains in reasoning depth …

Wrong Face, Wrong Move: The Social Dynamics of Emotion Misperception in Agent-Based Models
David Freire-Obreg\'on
https://arxiv.org/abs/2509.00080 https://

Wrong Face, Wrong Move: The Social Dynamics of Emotion Misperception in Agent-Based Models
The ability of humans to detect and respond to others' emotions is fundamental to understanding social behavior. Here, agents are instantiated with emotion classifiers of varying accuracy to study the impact of perceptual accuracy on emergent emotional and spatial behavior. Agents are visually represented with face photos from the KDEF database and endowed with one of three classifiers trained on the JAFFE (poor), CK+ (medium), or KDEF (high) datasets. Agents communicate locally on a 2D toroida…

Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation
Andrew G. A. Correa, Ana C. H de Matos
https://arxiv.org/abs/2509.00079 https://

Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation
Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted refinement pass. We extract logprobs, compute Shannon entropy on top-$k$ alternatives, and apply a simple OR-logic trigger over perplexity, maximum token entropy, and low-confidence-token count. Unlike approaches that use entropy only for measurement or decoding, we …

Language and Experience: A Computational Model of Social Learning in Complex Tasks
C\'edric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman, Jacob Andreas, Joshua Tenenbaum
https://arxiv.org/abs/2509.00074

Language and Experience: A Computational Model of Social Learning in Complex Tasks
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a proba…