Search arXiv⌕ Search

arXiv subjects

Xiang Li

Publications and source records attributed to Xiang Li.

At least 325 records · Page 18Linked to original sources
arXiv2026

HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid

Automated software environment setup is a prerequisite for testing, debugging, and reproducing failures, yet remains challenging in practice due to complex dependencies, heterogeneous build systems, and incomplete documentation. Recent work leverages large language models to automate this process, but typically evaluates success using weak signals such as dependency installation or partial test execution, which do not ensure that a project can actually run. In this paper, we argue that environment setup success should be evaluated through executable evidence rather than a single binary signal. We introduce the Environment Maturity Hierarchy, which defines three success levels based on progressively stronger execution requirements, culminating in successful execution of a project's main entry point. Guided by this hierarchy, we propose HerAgent, an automated environment setup approach that incrementally constructs executable environments through execution-based validation and repair. We evaluate HerAgent on four public benchmarks, where it outperforms all related work, achieving up to 79.6\% improvement due to its holistic understanding of project structure and dependencies. On complex C/C++ projects, HerAgent surpasses prior approaches by 66.7\%. In addition, HerAgent uniquely resolves 11-30 environment instances across the benchmarks that no prior method can configure.

cs.SE↗
arXiv2026

Berry-Esseen Bounds and Moderate Deviations for Catoni-Type Robust Estimation

A powerful robust mean estimator introduced by Catoni (2012) allows for mean estimation of heavy-tailed data while achieving the performance characteristics of classical mean estimator for sub-Gaussian data. While Catoni's framework has been widely extended across statistics, stochastic algorithms, and machine learning, fundamental asymptotic questions regarding the Central Limit Theorem and rare event deviations remain largely unaddressed. In this paper, we investigate Catoni-type robust estimators in two contexts: (i) mean estimation for heavy-tailed data, and (ii) linear regression with heavy-tailed innovations. For the first model, we establish the Berry--Esseen bound and moderate deviation principles, addressing both known and unknown variance settings. For the second model, we demonstrate that the associated estimator is consistent and satisfies a multi-dimensional Berry-Esseen bound.

math.ST↗
arXiv2026

Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model

Recent progress in VLMs has demonstrated impressive capabilities across a variety of tasks in the natural image domain. Motivated by these advancements, the remote sensing community has begun to adopt VLMs for remote sensing vision-language tasks, including scene understanding, image captioning, and visual question answering. However, existing remote sensing VLMs typically rely on closed-set scene understanding and focus on generic scene descriptions, yet lack the ability to incorporate external knowledge. This limitation hinders their capacity for semantic reasoning over complex or context-dependent queries that involve domain-specific or world knowledge. To address these challenges, we first introduced a multimodal Remote Sensing World Knowledge (RSWK) dataset, which comprises high-resolution satellite imagery and detailed textual descriptions for 14,141 well-known landmarks from 175 countries, integrating both remote sensing domain knowledge and broader world knowledge. Building upon this dataset, we proposed a novel Remote Sensing Retrieval-Augmented Generation (RS-RAG) framework, which consists of two key components. The Multi-Modal Knowledge Vector Database Construction module encodes remote sensing imagery and associated textual knowledge into a unified vector space. The Knowledge Retrieval and Response Generation module retrieves and re-ranks relevant knowledge based on image and/or text queries, and incorporates the retrieved content into a knowledge-augmented prompt to guide the VLM in producing contextually grounded responses. We validated the effectiveness of our approach on three representative vision-language tasks, including image captioning, image classification, and visual question answering, where RS-RAG significantly outperformed state-of-the-art baselines.

cs.CV↗
arXiv2026

XMap: Fast Internet-wide IPv4 and IPv6 Network Scanner

XMap is an open-source network scanner designed for performing fast Internet-wide IPv4 and IPv6 network research scanning. XMap was initially developed as the research artifact of a paper published at 2021 IEEE/IFIP International Conference on Dependable Systems and Networks (DSN '21) and then made available on GitHub. XMap is the first tool to support fast Internet-wide IPv6 network scanning in 2020. During the last five years, XMap has made substantial impact in academia, industry, and government. It has been referenced in 52 research papers (15 published at top-tier security venues and 11 in leading networking societies), received over 450 GitHub stars, featured in multiple news outlets, and deployed or recommended by international companies up to date. Additionally, XMap has contributed to the implementation of RFC documents and the discovery of various vulnerabilities. This paper provides fundamental details about XMap, its architecture, and its impact.

cs.CR↗
arXiv2026

Direct Visualization of Room-temperature Stair-stepped Quantum Spin Hall States in Bi4Br4

Topological insulators host exotic quantum phenomena such as the quantum spin Hall (QSH) effect, which enables dissipationless one-dimensional edge conduction. Realizing such states at room temperature and on a macroscopic scale is essential for energy-efficient electronics and quantum technologies, yet remains a fundamental challenge due to material limitations. Here, using microwave impedance microscopy, we directly visualize robust QSH states persisting up to 300 K in α-Bi4Br4 nanowires. This stability and scalability are enabled by a stair stepped stacking configuration, a multilayer geometry in which QSH edge states from individual layers remain spatially decoupled. This configuration circumvents the stringent alignment and layer number constraints of previous proposals, allowing robust stair-stepped QSH (SS-QSH) conduction in structures several micrometers long and hundreds of nanometers high. Magnetic field and temperature dependent measurements confirm their intrinsic topological nature. Crucially, the SS-QSH and bulk signals scale with nanowire height, verifying the stair stepped origin. Our results are also successfully reproduced by finite-element analysis simulations. This work establishes α Bi4Br4 as a practical platform for high temperature topological electronics and demonstrates a generalizable stacking strategy for designing scalable QSH systems.

cond-mat.mes-hall↗
arXiv2026

JMigBench: A Benchmark for Evaluating LLMs on Source Code Migration (Java 8 to Java 11)

We build a benchmark to evaluate large language models (LLMs) for source code migration tasks, specifically upgrading functions from Java 8 to Java 11. We first collected a dataset of function pairs from open-source repositories, but limitations in data quality led us to construct a refined dataset covering eight categories of deprecated APIs. Using this dataset, the Mistral Codestral model was evaluated with CodeBLEU and keyword-based metrics to measure lexical and semantic similarity as well as migration correctness. Results show that the evaluated model (Mistral Codestral) can handle trivial one-to-one API substitutions with moderate success, achieving identical migrations in 11.11% of the cases, but it struggles with more complex migrations such as CORBA or JAX-WS. These findings suggest Mistral Codestral can partially reduce developer effort by automating repetitive migration tasks but cannot yet replace humans within the scope of the JMigBench benchmark. The benchmark and analysis provide a foundation for future work on expanding datasets, refining prompting strategies, and improving migration performance across different LLMs.

cs.SE↗
arXiv2026

Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents

Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on automated code migration which including refactoring, API adaptation, and dependency updates has advanced rapidly, the exploration of the automated environment interaction that must accompany it remains relatively scarce. In practice, code and its environment are intricately intertwined. Relying solely on static analysis of the environment leads to an inadequate understanding of the target setting, prolongs feedback cycles, and consequently causes significant rework and project delays, thereby reducing overall efficiency. We contend that successful software evolution demands a holistic perspective that integrates both code and environment migration. To understand the current landscape and challenges, we first provide an overview of the status of automated environment construction. We then propose a novel framework paradigm that tightly integrates automated environment setup with the code migration workflow. Finally, we explore the challenges and future directions for automated environment interaction within the code migration domain. Our findings emphasize that without automated environment interaction, the automation of code migration is only half complete.

cs.SE↗
arXiv2026

LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation

The deployment of Large Language Models (LLMs) in high-stakes clinical settings demands rigorous and reliable evaluation. However, existing medical benchmarks remain static, suffering from two critical limitations: (1) data contamination, where test sets inadvertently leak into training corpora, leading to inflated performance estimates; and (2) temporal misalignment, failing to capture the rapid evolution of medical knowledge. Furthermore, current evaluation metrics for open-ended clinical reasoning often rely on either shallow lexical overlap (e.g., ROUGE) or subjective LLM-as-a-Judge scoring, both inadequate for verifying clinical correctness. To bridge these gaps, we introduce LiveMedBench, a continuously updated, contamination-free, and rubric-based benchmark that weekly harvests real-world clinical cases from online medical communities, ensuring strict temporal separation from model training data. We propose a Multi-Agent Clinical Curation Framework that filters raw data noise and validates clinical integrity against evidence-based medical principles. For evaluation, we develop an Automated Rubric-based Evaluation Framework that decomposes physician responses into granular, case-specific criteria, achieving substantially stronger alignment with expert physicians than LLM-as-a-Judge. To date, LiveMedBench comprises 2,756 real-world cases spanning 38 medical specialties and multiple languages, paired with 16,702 unique evaluation criteria. Extensive evaluation of 38 LLMs reveals that even the best-performing model achieves only 39.2%, and 84% of models exhibit performance degradation on post-cutoff cases, confirming pervasive data contamination risks. Error analysis further identifies contextual application-not factual knowledge-as the dominant bottleneck, with 35-48% of failures stemming from the inability to tailor medical knowledge to patient-specific constraints.

cs.AI↗
arXiv2026

Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving

Large Language Models (LLMs) have shown remarkable capabilities in automating software engineering tasks, spurring the emergence of coding agents that scaffold LLMs with external tools to resolve repository-level problems. However, existing agents still struggle to navigate large-scale codebases, as the Needle-in-a-Haystack problem persists even with million-token context windows, where relevant evidence is often overwhelmed by large volumes of irrelevant code and documentation. Prior codebase navigation approaches, including embedding-based retrieval, file-system exploration, and graph-based retrieval, address parts of this challenge but fail to capture the temporal continuity of agent reasoning, rendering agents stateless and causing repeated repository traversals that hinder scalable planning and reasoning. To address these limitations, we present Prometheus, a memory-centric coding agent framework for long-horizon codebase navigation. Prometheus represents the repository as a unified knowledge graph to encode semantic dependencies and employs a context engine augmented with working memory that retains and reuses previously explored contexts to ensure continuity across reasoning steps. Built upon this engine, Prometheus integrates memory-enhanced navigation into a multi-agent system for automated issue resolution, encompassing issue classification, bug reproduction, patch generation, and verification. Comprehensive experiments are conducted on two widely used issue resolution benchmarks, i.e., SWE-bench Verified and SWE-PolyBench Verified. Powered by GPT-5, Prometheus achieves state-of-the-art performance with 74.4% and 33.8% resolution rates on the two benchmarks, ranking Top-6 and Top-1 among open-source agent systems, respectively. Our data and code are available at https://github.com/EuniAI/Prometheus.

cs.SE↗
arXiv2026

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

With the rapid advancement and adoption of Audio Large Language Models (ALLMs), voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial misuse still remain unexplored. While prior work has examined aspects of trustworthiness in ALLMs, such as harmful content generation and hallucination, systematic security evaluations of voice agents are still lacking. To address this gap, we propose Aegis, a red-teaming framework for the governance, integrity, and security of voice agents. Aegis models the realistic deployment pipeline of voice agents and designs structured adversarial scenarios of critical risks, including privacy leakage, privilege escalation, resource abuse, etc. We evaluate the framework through case studies in banking call centers, IT Support, and logistics. Our evaluation shows that while access controls mitigate data-level risks, voice agents remain vulnerable to behavioral attacks that cannot be addressed through access restrictions alone, even under strict access controls. We observe systematic differences across model families, with open-weight models exhibiting higher susceptibility, underscoring the need for layered defenses that combine access control, policy enforcement, and behavioral monitoring to secure next-generation voice agents.

cs.CR↗
arXiv2026

Grand Challenges around Designing Computers' Control Over Our Bodies

Advances in emerging technologies, such as on-body mechanical actuators and electrical muscle stimulation, have allowed computers to take control over our bodies. This presents opportunities as well as challenges, raising fundamental questions about agency and the role of our bodies when interacting with technology. To advance this research field as a whole, we brought together expert perspectives in a week-long seminar to articulate the grand challenges that should be tackled when it comes to the design of computers' control over our bodies. These grand challenges span technical, design, user, and ethical aspects. By articulating these grand challenges, we aim to begin initiating a research agenda that positions bodily control not only as a technical feature but as a central, experiential, and ethical concern for future human-computer interaction endeavors.

cs.HC↗
arXiv2026

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection

Large language models (LLMs) raise concerns about content authenticity and integrity because they can generate human-like text at scale. Text watermarks, which embed detectable statistical signals into generated text, offer a provable way to verify content origin. Many detection methods rely on pivotal statistics that are i.i.d. under human-written text, making goodness-of-fit (GoF) tests a natural tool for watermark detection. However, GoF tests remain largely underexplored in this setting. In this paper, we systematically evaluate eight GoF tests across three popular watermarking schemes, using three open-source LLMs, two datasets, various generation temperatures, and multiple post-editing methods. We find that general GoF tests can improve both the detection power and robustness of watermark detectors. Notably, we observe that text repetition, common in low-temperature settings, gives GoF tests a unique advantage not exploited by existing methods. Our results highlight that classic GoF tests are a simple yet powerful and underused tool for watermark detection in LLMs.

cs.LG↗
arXiv2026

Hidden simplicity in AdS spinning Mellin amplitudes via scaffolding

We uncover surprising hidden simplicity in Mellin amplitudes for tree-level AdS holographic correlators for spinning operators, such as AdS "gluons" and "gravitons" (spin 1 and 2). We define Mellin amplitudes with $n$ spinning operators via the so-called "scaffolding" of $2n$-scalar ones with specific projection operators for each spin state, which are rational functions of Mellin variables of $2n$ scalars generalizing flat-space scaffolding amplitudes. We classify possible three-point structures with spin 1 and 2 which take the same form as massive three-point amplitudes in flat space, and match with special solutions such as those extracted from 6-scalar ones in $\mathrm{AdS}_5\times S^3$ or $\mathrm{AdS}_5\times S^5$. Focusing on $\mathrm{AdS}_5$ gluons, we directly bootstrap spinning amplitudes in scaffolding form up to $n=6$ gluons (which amounts to $2n=12$ scalars) using factorizations, multi-linearity and flat-space limit. The results take a remarkably simple form in analogy with flat-space amplitudes, which can be constructed from familiar 3- and 4-vertices as well as propagators of massive spin-1 particles. Surprisingly, we find that vertices with any descendant levels are proportional to the primary ones with nice combinatorial coefficients, which makes manifest the correct flat-space limit in the simplest possible way.

hep-th↗
arXiv2026

Chiral gapped states are universally non-topological

We propose an operator generalization of the Li-Haldane conjecture regarding the entanglement Hamiltonian of a disk in a 2+1D chiral gapped groundstate. The logic applies to regions with sharp corners, from which we derive several universal properties regarding corner entanglement. These universal properties follow from a set of locally-checkable conditions on the wavefunction. We also define a quantity $(\mathfrak{c}_{\text{tot}})_{\text{min}}$ that reflects the robustness of corner entanglement contributions, and show that it provides an obstruction to a gapped boundary. One reward from our analysis is that we can construct a local gapped Hamiltonian within the same chiral gapped phase from a given wavefunction; we conjecture that it is closer to the low-energy renormalization group fixed point than the original parent Hamiltonian. Our analysis of corner entanglement reveals the emergence of a universal conformal geometry encoded in the entanglement structure of bulk regions of chiral gapped states that is not visible in topological field theory. Our formalism also gives an explanation of the modular commutator formula for the chiral central charge.

cond-mat.str-el↗
arXiv2026

Probing the structure of cyclic hydrocarbon molecules with X-ray-induced Coulomb explosion imaging

Coulomb explosion imaging (CEI) is a powerful experimental technique that maps a molecule's geometric structure onto the momenta of ionic molecular fragments produced by rapid multiple ionization. Here, we apply CEI induced by pulses from an X-ray free-electron laser in order to image and distinguish complex hydrocarbon isomers with the chemical formula C7H8: toluene, cycloheptatriene, and 1,6-heptadiyne. The measured fragment-ion momentum distributions show discernible differences between the three isomers and provide signatures of specific carbon and hydrogen sites in the molecule. In contrast to previous work, we demonstrate that distinct 'marker atoms' are not strictly required for constructing a meaningful molecular frame of reference for the interpretation of the momentum-space data. Our work paves the way for tracking the ultrafast motion of nuclei during isomerization reactions in pure hydrocarbons.

physics.chem-ph↗
arXiv2026

How Do We Evaluate Experiences in Immersive Environments?

How do we evaluate experiences in immersive environments? Despite decades of research in immersive technologies such as virtual reality, the field remains fragmented. Studies rely on overlapping constructs, heterogeneous instruments, and little agreement on what counts as immersive experience. To better understand this landscape, we conducted a bottom-up scoping review of 375 papers published in ACM CHI, UIST, VRST, SUI, IEEE VR, ISMAR, and TVCG. Our analysis reveals that evaluation practices are often domain- and purpose-specific, shaped more by local choices than by shared standards. Yet this diversity also points to new directions. Instead of multiplying instruments, researchers benefit from integrating and refining them into smarter measures. Rather than focusing only on system outputs, evaluations must center the user's lived experience. Computational modeling offers opportunities to bridge signals across methods, but lasting progress requires open and sustainable evaluation practices that support comparability and reuse. Ultimately, our contribution is to map current practices and outline a forward-looking agenda for immersive experience research.

cs.HC↗
arXiv2026

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Diffusion models, though originally designed for generative tasks, have demonstrated impressive self-supervised representation learning capabilities. A particularly intriguing phenomenon in these models is the emergence of unimodal representation dynamics, where the quality of learned features peaks at an intermediate noise level. In this work, we conduct a comprehensive theoretical and empirical investigation of this phenomenon. Leveraging the inherent low-dimensionality structure of image data, we theoretically demonstrate that the unimodal dynamic emerges when the diffusion model successfully captures the underlying data distribution. The unimodality arises from an interplay between denoising strength and class confidence across noise scales. Empirically, we further show that, in classification tasks, the presence of unimodal dynamics reliably reflects the generalization of the diffusion model: it emerges when the model generates novel images and gradually transitions to a monotonically decreasing curve as the model begins to memorize the training data.

cs.LG↗
arXiv2026

CAARMA: Class Augmentation with Adversarial Mixup Regularization

Speaker verification is a typical zero-shot learning task, where inference of unseen classes is performed by comparing embeddings of test instances to known examples. The models performing inference must hence naturally generate embeddings that cluster same-class instances compactly, while maintaining separation across classes. In order to learn to do so, they are typically trained on a large number of classes (speakers), often using specialized losses. However real-world speaker datasets often lack the class diversity needed to effectively learn this in a generalizable manner. We introduce CAARMA, a class augmentation framework that addresses this problem by generating synthetic classes through data mixing in the embedding space, expanding the number of training classes. To ensure the authenticity of the synthetic classes we adopt a novel adversarial refinement mechanism that minimizes categorical distinctions between synthetic and real classes. We evaluate CAARMA on multiple speaker verification tasks, as well as other representative zero-shot comparison-based speech analysis tasks and obtain consistent improvements: our framework demonstrates a significant improvement of 8\% over all baseline models. The code is available at: https://github.com/massabaali7/CAARMA/

cs.SD↗