arXiv subjects

Xuan Zhou

Publications and source records attributed to Xuan Zhou.

At least 19 recordsLinked to original sources

arXiv2026

Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts

Ethical evaluation of Large Language Models (LLMs) often characterizes model values as static and monolithic. In contrast, we argue that LLM value expression is better understood as a structured yet dynamic phenomenon. To investigate this, we introduce Conflict-driven Value Probing, a controlled framework that places LLMs in value conflicts and implements four types of interventions that perturb these conflicts to probe LLM value expression. Applying this framework to ten LLMs, we identify three recurring patterns. (1) Expression duality: models shift from broad idealistic orientations in abstract assessment toward more pragmatic priorities in concrete conflicts. (2) Functional steerability: models readily reconfigure their expressed value profiles toward task-defined value objectives. (3) Bounded plasticity: such reconfiguration is not without constraints, i.e. pressure induces a security- and goal-oriented priority shift while negative framing distinguishes protected values from those more amenable to redirection. Together, these findings characterize both the structure and dynamics of LLM value expression: context flexibly reconfigures expressed priorities, yet within behavioral boundaries. This behavioral account provides a foundation for understanding controllability, alignment, and safety in LLMs. Code and data are available at https://github.com/ZeroGen-Lab/CFProbe.

cs.CL↗

arXiv2026

Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data

Personalized agents are increasingly applied to assist users across a wide range of tasks. Effective personalized assistance requires not only retrieving explicit facts from past interactions stored in agent memory, but also inferring abstract personal characteristics. However, existing memory benchmarks primarily evaluate whether an agent can retrieve information explicitly stated in conversational histories, failing to provide an effective assessment of deeper user understanding. In this work, we propose Setoka, a benchmark for evaluating memory-augmented personalized agents with hierarchical user understanding from heterogeneous data. Grounded in theories from cognitive and personality psychology, Setoka defines four levels of user understanding, i.e., semantic memory, episodic memory, behavior pattern, and personality trait. Moreover, to enable realistic yet privacy-preserving evaluation, we design a psychometrics-based pipeline that synthesizes diverse, coherent heterogeneous user data and queries at scale. Finally, we leverage Setoka to evaluate 3 language models combined with 5 memory systems for 10 synthetic users. Our comprehensive evaluation reveals that while existing systems perform well on semantic memory retrieval, their performance declines on episodic memory. Moreover, when dealing with behavior pattern and personality trait understanding tasks that require integrating heterogeneous and fragmented information dispersed over time, performance declines even further. These findings demonstrate that user understanding cannot be handled by simple fact retrieval, motivating the design of memory mechanisms for cross-source integration and abstraction over long-term user behavior.

cs.AI↗

arXiv2026

Quasinormal modes of scalar and Maxwell field perturbations coupled to the Einstein tensor in generalized Nariai spacetimes

We investigate the quasinormal modes of scalar and Maxwell field perturbations coupled to the Einstein tensor in generalized Nariai spacetimes. Our results show that, for both types of perturbations, the coupling introduces different critical values, which separate the frequency spectrum into distinct branches. Near these critical values, the square-root term that determines $\omega_R^2$ may change sign, giving rise to a parameter interval in which the modes are purely imaginary. Away from this regime, the coupling affects the oscillatory parts of the two fields in opposite ways: $\omega_R^2$ generally increases with the coupling constant $\eta$ for the scalar field, whereas it decreases with $\eta$ for the Maxwell field. The magnetic charge tends to enhance the oscillatory response, while increasing the spacetime dimension narrows the purely imaginary regime. This comparison shows analytically that the same curvature coupling can affect scalar and Maxwell perturbations in qualitatively different ways.

gr-qc↗

arXiv2026

On the mathematics table problem

In this paper we study the mathematical table problem from a geometric-topological point of view. We prove a zero-existence theorem on a cylinder, which gives a new proof of Fenn's square-table theorem under Fenn's boundary conditions, and establish a variant under different boundary conditions. We also prove that every square table admits a horizontal placement on saddle surfaces. Finally, we show that almost every level set of a smooth Fenn graph contains a rectangle similar to any prescribed rectangle and an orientation-preserving similar copy of every prescribed cyclic quadrilateral.

math.GT↗

arXiv2026

Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One

In this paper, we study the universal approximation property of residual neural networks. For input and output dimensions $d_x$ and $d_y$, and LeakyReLU, ReLU, ReLU-like activation functions, the upper and lower bounds of the minimum block width are established. To achieve $L^p$ approximation $(1\leq p <+\infty)$ on any compact set, we show that the exact minimum block width is $\max\{d_x,d_y\}$ when each residual branch has inner width 1. Furthermore, we show that residual neural networks with block width $\min\{d_x+d_y, \max\{2d_x+1,d_y\}\}$ can achieve uniform approximation on any compact set under the constraint that each residual branch has inner width 1. Besides, for any activation function family, we prove that there exist functions that cannot be approximated by residual neural networks with block width less than $\max\{d_x, d_y\}$, both in the $L^p$ sense and the uniform sense, regardless of inner width. Consequently, for LeakyReLU, ReLU, ReLU-like activation functions and $d_y\geq 2d_x+1$, the exact minimum block width for uniform approximation is $d_y$ when each residual branch has inner width 1.

cs.LG↗

arXiv2026

Surface Functionalization Enables Two-Dimensional Altermagnetism and Giant Tunnel Magnetoresistance

Two-dimensional (2D) altermagnets (AMs) are highly desirable for ultrafast, stray-field-free spintronics because they combine compensated magnetic order and momentum-dependent spin splitting with the scalability, tunability, and interface compatibility of atomically thin materials. However, practical 2D AMs remain scarce. Rather than relying solely on the search for intrinsic 2D AMs, an appealing route is to transform known 2D antiferromagnets (AFMs) into AMs through symmetry engineering. Here, we propose surface functionalization as a symmetry-guided, nonvolatile chemical switch for realizing this AFM-to-AM transformation. By breaking inversion and out-of-plane mirror symmetries while preserving the rotation symmetry connecting opposite-spin sublattices, single-sided functionalization lifts spin degeneracy and induces altermagnetic spin splitting. Using monolayer FeSe as a representative platform, first-principles calculations show that hydrogenation, oxidation, and fluorination convert spin-degenerate antiferromagnetic FeSe into a d-wave AM with pronounced momentum-dependent spin splitting. At the device level, our transport simulations reveal that the functionalized FeSe monolayer magnetic tunnel junctions exhibit giant tunnel magnetoresistance (TMR) up to $1.87\times10^3\%$, originating from momentum-selective spin filtering between parallel and antiparallel N\'eel-vector configurations. The strong dependence of TMR on functionalization geometry further demonstrates that surface chemistry provides an effective control knob for altermagnetic transport. Our work establishes a symmetry-to-chemistry-to-device strategy for engineering 2D AMs and developing high-performance altermagnetic spintronic devices.

cond-mat.mtrl-sci↗

arXiv2026

GASim: A Graph-Accelerated Hybrid Framework for Social Simulation

Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM). However, this incurs high latency due to expensive memory retrieval and sequential ABM execution. To address this challenge, we propose GASim, a graph-accelerated hybrid multi-agent framework for large-scale social simulations. For core agents driven by LLM, GASim introduces Graph-Optimized Memory (GOM) to replace intensive LLM-based retrieval pipelines with lightweight propagation over a sparse memory graph. For the majority of ordinary agents, GASim employs Graph Message Passing (GMP), substituting sequential ABM execution with parallel updates by fine-grained feature aggregation and Graph Attention Network. We further introduce Entropy-Driven Grouping (EDG) that coordinates this hybrid partitioning, leveraging information entropy to dynamically identify emergent core agents situated in information-diverse neighborhoods. Extensive experiments show that GASim not only delivers a substantial 9.94-fold end-to-end speedup over the traditional hybrid framework but also consumes less than 20% of baseline tokens, significantly reducing costs while preserving strong alignment with real-world public opinion trends. Our code is available at https://github.com/Jasmine0201/GASim.

cs.AI↗

arXiv2026

Relocation of compact sets in $\mathbb{R}^n$ by diffeomorphisms and linear separability of datasets in $\mathbb{R}^n$

Relocation of compact sets in an $n$-dimensional manifold by self-diffeomorphism is of its own interest as well as significant potential applications to data classification in data science. This paper presents a theory for relocating a finite number of compact sets in $\mathbb{R}^n$ to be relocated to arbitrary target domains in $\mathbb{R}^n$ by diffeomorphisms of $\mathbb{R}^n$. Furthermore, we prove that for any such collection, there exists a differentiable embedding into $\mathbb{R}^{n+1}$ such that their images become linearly separable. As applications of the established theory, we show that a finite number of compact datasets in $\mathbb{R}^n$ can be made linearly separable by width-$n$ deep neural networks (DNNs) with Leaky-ReLU, ELU, or SELU activation functions, under a mild condition. In addition, we show that any finite number of mutually disjoint compact datasets in $\mathbb{R}^n$ can be made linearly separable in $\mathbb{R}^{n+1}$ by a width-$(n+1)$ DNN.

cs.LG↗

arXiv2026

CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity

We introduce CARTBENCH, a museum-grounded benchmark for evaluating vision-language models (VLMs) on Chinese artworks beyond short-form recognition and QA. CARTBENCH comprises four subtasks: CURATORQA for evidence-grounded recognition and reasoning, CATALOGCAPTION for structured four-section expert-style appreciation, REINTERPRET for defensible reinterpretation with expert ratings, and CONNOISSEURPAIRS for diagnostic authenticity discrimination under visually similar confounds. CARTBENCH is built by aligning image-bearing Palace Museum objects from Wikidata with authoritative catalog pages, spanning five art categories across multiple dynasties. Across nine representative VLMs, we find that high overall CURATORQA accuracy can mask sharp drops on hard evidence linking and style-to-period inference; long-form appreciation remains far from expert references; and authenticity-oriented diagnostic discrimination stays near chance, underscoring the difficulty of connoisseur-level reasoning for current models.

cs.CL↗

arXiv2026

Curve resampling based high-quality high-order unstructured quadrilateral mesh generation

High-order quadrilateral meshes offer superior accuracy and computational efficiency in numerical simulations. However, existing methods struggle to simultaneously preserve boundary/interface features, ensure high quality, and achieve efficient generation, particularly for complex geometries where degenerate and inverted elements frequently occur. To address this issue, this paper proposes a high-quality high-order unstructured quadrilateral mesh generation method based on geometric error-bounded curve reconstruction, which employs an indirect approach to enforce interface consistency. By optimization-based curve reconstruction strategies, our method improves mesh quality while maintaining the validity of high-order elements. Compared to direct high-order mesh optimization techniques, our approach reduces the optimization problem to curve reconstruction problem, significantly lowering computational complexity and enhancing efficiency. Experimental results demonstrate that the proposed method efficiently generates high-quality high-order quadrilateral meshes while preserving boundary/interface geometric features, offering improved adaptability and numerical stability in complex geometries.

cs.GR↗

arXiv2026

Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction

The pursuit of human-like conversational agents has long been guided by the Turing test. For modern speech-to-speech (S2S) systems, a critical yet unanswered question is whether they can converse like humans. To tackle this, we conduct the first Turing test for S2S systems, collecting 2,968 human judgments on dialogues between 9 state-of-the-art S2S systems and 28 human participants. Our results deliver a clear finding: no existing evaluated S2S system passes the test, revealing a significant gap in human-likeness. To diagnose this failure, we develop a fine-grained taxonomy of 18 human-likeness dimensions and crowd-annotate our collected dialogues accordingly. Our analysis shows that the bottleneck is not semantic understanding but stems from paralinguistic features, emotional expressivity, and conversational persona. Furthermore, we find that off-the-shelf AI models perform unreliably as Turing test judges. In response, we propose an interpretable model that leverages the fine-grained human-likeness ratings and delivers accurate and transparent human-vs-machine discrimination, offering a powerful tool for automatic human-likeness evaluation. Our work establishes the first human-likeness evaluation for S2S systems and moves beyond binary outcomes to enable detailed diagnostic insights, paving the way for human-like improvements in conversational AI systems.

cs.AI↗

arXiv2026

TiInsight: A SQL-based Automated Exploratory Data Analysis System through Large Language Models

The SQL-based exploratory data analysis has garnered significant attention within the data analysis community. The emergence of large language models (LLMs) has facilitated the paradigm shift from manual to automated data exploration. However, existing methods generally lack the ability for cross-domain analysis, and the exploration of LLMs capabilities remains insufficient. This paper presents TiInsight, an SQL-based automated cross-domain exploratory data analysis system. First, TiInsight offers a user-friendly GUI enabling users to explore data using natural language queries. Second, TiInsight offers a robust cross-domain exploratory data analysis pipeline: hierarchical data context (i.e., HDC) generation, question clarification and decomposition, text-to-SQL (i.e., TiSQL), and data visualization (i.e., TiChart). Third, we have implemented and deployed TiInsight in the production environment of PingCAP and demonstrated its capabilities using representative datasets. The demo video is available at https://youtu.be/JzYFyYd-emI.

cs.DB↗

arXiv2025

Quasi-interpolation with random sampling centers

We propose and study a general quasi-interpolation framework for stochastic function approximation, which stems and draws motivation from convolution-type solutions for certain practical weighted variational problems. We obtain our quasi-interpolants using Monte Carlo discretization of the pertinent integrals and establish a family of $L^p$-McDiarmid-type concentration inequalities for $1\leq p\leq \infty$, which resulted in verifiable expected error estimates for the stochastic quasi-interpolants. The $L^1$-version of these concentration inequalities is dynamically-independent of dimensions, which offers a partial stochastic mitigation of the so called ``curse of dimensionality". The $L^\infty$-version of these concentration inequalities strengthens the existing expected $L^\infty$-error estimates in the literature. Numerical simulation results are provided at the end of the paper to validate the underlying theoretical analysis.

math.NA↗

arXiv2025

EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce

Foundation agents have rapidly advanced in their ability to reason and interact with real environments, making the evaluation of their core capabilities increasingly important. While many benchmarks have been developed to assess agent performance, most concentrate on academic settings or artificially designed scenarios while overlooking the challenges that arise in real applications. To address this issue, we focus on a highly practical real-world setting, the e-commerce domain, which involves a large volume of diverse user interactions, dynamic market conditions, and tasks directly tied to real decision-making processes. To this end, we introduce EcomBench, a holistic E-commerce Benchmark designed to evaluate agent performance in realistic e-commerce environments. EcomBench is built from genuine user demands embedded in leading global e-commerce ecosystems and is carefully curated and annotated through human experts to ensure clarity, accuracy, and domain relevance. It covers multiple task categories within e-commerce scenarios and defines three difficulty levels that evaluate agents on key capabilities such as deep information retrieval, multi-step reasoning, and cross-source knowledge integration. By grounding evaluation in real e-commerce contexts, EcomBench provides a rigorous and dynamic testbed for measuring the practical capabilities of agents in modern e-commerce.

cs.AI↗

arXiv2025

Minimum Width of Deep Narrow Networks for Universal Approximation

Determining the minimum width of fully connected neural networks has become a fundamental problem in recent theoretical studies of deep neural networks. In this paper, we study the lower bounds and upper bounds of the minimum width required for fully connected neural networks in order to have universal approximation capability, which is important in network design and training. We show that $w_{min}\leq\max(2d_x+1, d_y)$ also holds true for networks with ELU, SELU activation functions, and the upper bound of this inequality is attained when $d_y=2d_x$, where $d_x$, $d_y$ denote the input and output dimensions, respectively. Besides, we show that $d_x+1\leq w_{min}\leq d_x+d_y$ for networks with LeakyReLU, ELU, CELU, SELU, Softplus activation functions, by proving that ReLU activation function can be approximated by these activation functions. In addition, in the case that the activation function is injective or can be uniformly approximated by a sequence of injective functions (e.g., ReLU), we present a new proof of the inequality $w_{min}\ge d_y+\mathbf{1}_{d_x<d_y\leq2d_x}$ by constructing a more intuitive example via a new geometric approach based on Poincar\'e-Miranda Theorem.

cs.LG↗

arXiv2025

Universal Scaling Functions of the Gr{\"u}neisen Ratio near Quantum Critical Points

The Gr\"uneisen ratio, defined as $\Gamma_g \equiv (1/T) (\partial T/\partial g)_S$, serves as a highly sensitive probe for detecting quantum critical points (QCPs) driven by an external feild $g$ and for characterizing the magnetocaloric effect (MCE). Near a QCP, the Gr\"uneisen ratio displays a universal divergence which is governed by a universality-class-dependent scaling function stemming from the scale invariance. In this work, we systematically investigate the universal scaling functions of Gr\"uneisen ratio in both one-dimensional (1D) and two-dimensional (2D) quantum spin systems, including the transverse-field Ising model, the spin-1/2 Heisenberg model, the quantum $q$-state Potts model ($q=3,4$) and the $J_1$-$J_2$ columnar dimer model. Our approach employs the thermal tensor-network method for infinite-size 1D systems and the stochastic series expansion quantum Monte Carlo (SSE QMC) simulations for 2D systems, enabling precise calculations of the Gr\"uneisen ratio near QCPs. Through data collapse analysis, we extract the corresponding scaling functions, which establish quantitative frameworks to interpret magnetocaloric experiments and guide the development of ultralow-temperature refrigeration.

cond-mat.str-el↗

arXiv2025

Sedeve-Kit, a Specification-Driven Development Framework for Building Distributed Systems

Developing distributed systems presents significant challenges, primarily due to the complexity introduced by non-deterministic concurrency and faults. To address these, we propose a specification-driven development framework. Our method encompasses three key stages. The first stage defines system specifications and invariants using TLA${^+}$. It allows us to perform model checking on the algorithm's correctness and generate test cases for subsequent development phases. In the second stage, based on the established specifications, we write code to ensure consistency and accuracy in the implementation. Finally, after completing the coding process, we rigorously test the system using the test cases generated in the initial stage. This process ensures system quality by maintaining a strong connection between the abstract design and the concrete implementation through continuous verification.

cs.SE↗

arXiv2025

WideSearch: Benchmarking Agentic Broad Info-Seeking

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such "wide-context" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent reliability on these large-scale collection tasks. The benchmark features 200 manually curated questions (100 in English, 100 in Chinese) from over 15 diverse domains, grounded in real user queries. Each task requires agents to collect large-scale atomic information, which could be verified one by one objectively, and arrange it into a well-organized output. A rigorous five-stage quality control pipeline ensures the difficulty, completeness, and verifiability of the dataset. We benchmark over 10 state-of-the-art agentic search systems, including single-agent, multi-agent frameworks, and end-to-end commercial systems. Most systems achieve overall success rates near 0\%, with the best performer reaching just 5\%. However, given sufficient time, cross-validation by multiple human testers can achieve a near 100\% success rate. These results demonstrate that present search agents have critical deficiencies in large-scale information seeking, underscoring urgent areas for future research and development in agentic search. Our dataset, evaluation pipeline, and benchmark results have been publicly released at https://widesearch-seed.github.io/

cs.CL↗