arXiv subjects

Yiran Zhang

Publications and source records attributed to Yiran Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

IntelliRadar: A Comprehensive Platform to Pinpoint Malicious Package Information from Cyber Intelligence

Malicious packages in public registries pose serious threats to software supply chain security. While current software component analysis (SCA) tools rely on databases like OSV and Snyk to detect these threats, these databases suffer from delayed updates and incomplete coverage. However, they miss intelligence from unstructured sources like social media and developer forums, where new threats are often first reported. This delay extends the lifecycle of malicious packages and increases risks for downstream users. To address this, we developed a novel and comprehensive approach to construct a platform IntelliRadar to collect disclosed malicious package names from unstructured web content. Specifically, by exhaustively searching and snowballing the public sources of malicious package names, and incorporating large language models (LLMs) with domain-specialized Least to Most prompts, IntelliRadar ensures comprehensive collection of historical and current disclosed malicious package names from diverse unstructured sources. As a result, we constructed a comprehensive malicious package database containing 34,313 malicious NPM and PyPI package names. Our evaluation shows that IntelliRadar achieves high performance (97.91% precision) on malicious package intelligence extraction. Compared to existing databases, IntelliRadar identifies 7,542 more malicious package names than OSV and 12,684 more than Snyk. Furthermore, 76.6% of NPM components and 70.3% of PyPI components in IntelliRadar were collected earlier than in Snyk's database. IntelliRadar is also more cost-efficient, with a cost of $0.003 per piece of malicious package intelligence and only $7 per month for continuous monitoring. Furthermore, we identified and received confirmation for 1,981 malicious packages in downstream package manager mirror registries through the IntelliRadar.

cs.SE↗

arXiv2025

Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA

Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning processes within these interactions presents a significant challenge due to complex contextual dependencies and a lack of specialized visualization tools, leading to a high cognitive load for researchers. To address this gap, we present VISTA, an web-based Visual Interactive System for Textual Analytics in multi-turn reasoning tasks. VISTA allows users to visualize the influence of context on model decisions and interactively modify conversation histories to conduct "what-if" analyses across different models. Furthermore, the platform can automatically parse a session and generate a reasoning dependency tree, offering a transparent view of the model's step-by-step logical path. By providing a unified and interactive framework, VISTA significantly reduces the complexity of analyzing reasoning chains, thereby facilitating a deeper understanding of the capabilities and limitations of current LLMs. The platform is open-source and supports easy integration of custom benchmarks and local models.

cs.CL↗

arXiv2025

Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation

Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods perform inadequately in large-scale application-level software code generation, failing to ensure reasonable orga- nizational structures of project code and making it difficult to maintain the code generation process. To address this, this paper envisions a Knowledge-Guided Application-Level Code Generation framework named KGACG, which aims to trans- form software requirements specification and architectural design document into executable code through a collaborative closed- loop of the Code Organization & Planning Agent (COPA), Coding Agent (CA), and Testing Agent (TA), combined with a feedback mechanism. We demonstrate the collaborative process of the agents in KGACG in a Java Tank Battle game case study while facing challenges. KGACG is dedicated to advancing the automation of application-level software development.

cs.SE↗

arXiv2025

Adaptivity Gaps for Stochastic Probing with Subadditive Functions

In this paper, we study the stochastic probing problem under a general monotone norm objective. Given a ground set $U = [n]$, each element $i \in U$ has an independent nonnegative random variable $X_i$ with known distribution. Probing an element reveals its value, and the sequence of probed elements must satisfy a prefix-closed feasibility constraint $\mathcal{F}$. A monotone norm $f: \mathbb{R}_{\geq 0}^n \to \mathbb{R}_{\geq 0}$ determines the reward $f(X_P)$, where $P$ is the set of probed elements and $X_P$ is the vector with $X_i$ for $i \in P$ and 0 otherwise. The goal is to design a probing strategy maximizing the expected reward $\mathbb{E}[f(X_P)]$. We focus on the adaptivity gap: the ratio between the expected rewards of optimal adaptive and optimal non-adaptive strategies. We resolve an open question posed in [GNS17, KMS24], showing that for general monotone norms, the adaptivity gap is $O(\log^2 n)$. A refined analysis yields an improved bound of $O(\log r \log n / \log\log n)$, where $r$ is the maximum size of a feasible probing sequence. As a by-product, we derive an asymptotically tight adaptivity gap $Θ( \log n/\log\log n)$ for Bernoulli probing with binary-XOS objectives, matching the known lower bound. Additionally, we show an $O(\log^3 n)$ upper bound for Bernoulli probing with general subadditive objectives. For monotone symmetric norms, we prove the adaptivity gap is $O(1)$, improving the previous $O(\log n)$ bound from [PRS23].

cs.DS↗

arXiv2025

UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories

Software maintainability critically depends on high-quality requirements descriptions and explicit traceability between requirements and code. Although automated code summarization (ACS) and requirements traceability (RT) techniques have been widely studied, existing ACS methods mainly generate implementation-level (i.e., developer-oriented) requirements (IRs) for fine-grained units (e.g., methods), while RT techniques often overlook the impact of project evolution. As a result, user-level (i.e., end user-oriented) requirements (URs) and live trace links remain underexplored, despite their importance for supporting user understanding and for validating whether AI-generated software aligns with user intent. To address this gap, we propose UserTrace, a multi-agent system that automatically generates URs and recovers live trace links (from URs to IRs to code) from software repositories. UserTrace coordinates four specialized agents (i.e., Code Reviewer, Searcher, Writer, and Verifier) through a three-phase process: structuring repository dependencies, deriving IRs for code units, and synthesizing URs with domain-specific context. Our comparative evaluation shows that UserTrace produces URs with higher completeness, correctness, and helpfulness than an established baseline, and achieves superior precision in trace link recovery compared to five state-of-the-art RT approaches. A user study further demonstrates that UserTrace helps end users validate whether the AI-generated repositories align with their intent.

cs.SE↗

arXiv2025

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are naturally inverse dual tasks, we propose \textbf{SUDER} (\textbf{S}elf-improving \textbf{U}nified LMMs with \textbf{D}ual s\textbf{E}lf-\textbf{R}ewards), a framework reinforcing the understanding and generation capabilities of LMMs with a self-supervised dual reward mechanism. SUDER leverages the inherent duality between understanding and generation tasks to provide self-supervised optimization signals for each other. Specifically, we sample multiple outputs for a given input in one task domain, then reverse the input-output pairs to compute the dual likelihood within the model as self-rewards for optimization. Extensive experimental results on visual understanding and generation benchmarks demonstrate that our method can effectively enhance the performance of the model without any external supervision, especially achieving remarkable improvements in text-to-image tasks.

cs.AI↗

arXiv2025

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision

Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough in this area. However, existing methods that only rely on LLMs remain inadequate in the quality of generated code, offering no guarantees of satisfying practical requirements. They lack a systematic strategy for requirements development and modeling. Recently, LLM-based agents typically possess powerful abilities and play an essential role in facilitating the alignment of LLM outputs with user requirements. In this paper, we envision the first multi-agent framework for reliable code generation based on \textsc{re}quirements \textsc{de}velopment and \textsc{fo}rmalization, named \textsc{ReDeFo}. This framework incorporates three agents, highlighting their augmentation with knowledge and techniques of formal methods, into the requirements-to-code generation pipeline to strengthen quality assurance. The core of \textsc{ReDeFo} is the use of formal specifications to bridge the gap between potentially ambiguous natural language requirements and precise executable code. \textsc{ReDeFo} enables rigorous reasoning about correctness, uncovering hidden bugs, and enforcing critical properties throughout the development process. In general, our framework aims to take a promising step toward realizing the long-standing vision of reliable, auto-generated software.

cs.SE↗

arXiv2025

MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration

Software architecture design is a critical, yet inherently complex and knowledge-intensive phase of software development. It requires deep domain expertise, development experience, architectural knowledge, careful trade-offs among competing quality attributes, and the ability to adapt to evolving requirements. Traditionally, this process is time-consuming and labor-intensive, and relies heavily on architects, often resulting in limited design alternatives, especially under the pressures of agile development. While Large Language Model (LLM)-based agents have shown promising performance across various SE tasks, their application to architecture design remains relatively scarce and requires more exploration, particularly in light of diverse domain knowledge and complex decision-making. To address the challenges, we proposed MAAD (Multi-Agent Architecture Design), an automated framework that employs a knowledge-driven Multi-Agent System (MAS) for architecture design. MAAD orchestrates four specialized agents (i.e., Analyst, Modeler, Designer and Evaluator) to collaboratively interpret requirements specifications and produce architectural blueprints enriched with quality attributes-based evaluation reports. We then evaluated MAAD through a case study and comparative experiments against MetaGPT, a state-of-the-art MAS baseline. Our results show that MAAD's superiority lies in generating comprehensive architectural components and delivering insightful and structured architecture evaluation reports. Feedback from industrial architects across 11 requirements specifications further reinforces MAAD's practical usability. We finally explored the performance of the MAAD framework with three LLMs (GPT-4o, DeepSeek-R1, and Llama 3.3) and found that GPT-4o exhibits better performance in producing architecture design, emphasizing the importance of LLM selection in MAS-driven architecture design.

cs.SE↗

arXiv2025

Convection Anisotropies of Cosmic Rays in Highly Magnetized Plasma

Recently, Zhang & Liu (2024) proposed a turbulent convection model for multiscale anisotropies of cosmic rays (CRs), with an assumption of isotropic diffusion such that the anisotropies are statistically isotropic. However, this assumption may be unrealistic for TeV CRs, whose observations have revealed the significance of the local interstellar background magnetic field. To meet the difficulty, the turbulent convection scenario needs to be extended to cover anisotropic diffusion. In this paper, we focus on the parallel diffusion with isotropic pitch-angle scattering, which may be an approximation to the transport process driven by weak hydromagnetic waves in a magnetic flux tube, where fluctuations of the wave velocities lead to the turbulent convection. The consequence is the breaking of the statistical isotropy, while the overall shape of the angular power spectrum, $ \overline{C_\ell}\propto\ell ^{-γ-1} $ ($ \ell\gg 1 $), remains similar to that in the isotropic diffusion model, where $ \ell $ are degrees of spherical harmonics, and $ γ$ is the turbulence spectral index of the convection field. It is then expected that the power-law index of the TeV CR small-scale angular power spectrum can be explained with the Kolmogorov law $ γ=5/3 $, irrespective of the background magnetic field to some extent.

astro-ph.HE↗

arXiv2025

Origin Tracer: A Method for Detecting LoRA Fine-Tuning Origins in LLMs

As large language models (LLMs) continue to advance, their deployment often involves fine-tuning to enhance performance on specific downstream tasks. However, this customization is sometimes accompanied by misleading claims about the origins, raising significant concerns about transparency and trust within the open-source community. Existing model verification techniques typically assess functional, representational, and weight similarities. However, these approaches often struggle against obfuscation techniques, such as permutations and scaling transformations. To address this limitation, we propose a novel detection method Origin-Tracer that rigorously determines whether a model has been fine-tuned from a specified base model. This method includes the ability to extract the LoRA rank utilized during the fine-tuning process, providing a more robust verification framework. This framework is the first to provide a formalized approach specifically aimed at pinpointing the sources of model fine-tuning. We empirically validated our method on thirty-one diverse open-source models under conditions that simulate real-world obfuscation scenarios. We empirically analyze the effectiveness of our framework and finally, discuss its limitations. The results demonstrate the effectiveness of our approach and indicate its potential to establish new benchmarks for model verification.

cs.AI↗

arXiv2025

Resolving Intervalley Gaps and Many-Body Resonances in Moiré Superconductor

Magic-angle twisted multilayer graphene stands out as a highly tunable class of moiré materials that exhibit strong electronic correlations and robust superconductivity. However, understanding the relations between the low-temperature superconducting phase and the preceding correlated phases established at higher temperatures remains a challenge. Here, we employ scanning tunneling microscopy and spectroscopy to track the formation sequence of correlated phases established by the interplay of dynamic correlations, intervalley coherence, and superconductivity in magic-angle twisted trilayer graphene (MATTG). We discover the existence of two well-resolved gaps pinned at the Fermi level within the superconducting doping range. While the outer gap, previously associated with pseudogap phase, persists at high temperatures and magnetic fields, the newly revealed inner gap is more fragile in line with superconductivity MATTG transport experiments. Andreev reflection spectroscopy taken at the same location confirms a clear trend that closely follows the doping behaviour of the inner gap, and not the outer one. Moreover, spectroscopy taken at nanoscale domain boundaries further corroborates the contrasting behavior of the two gaps, with the inner gap remaining resilient to structural variations, as expected from the finite superconducting coherence length. By comparing our findings with recent topological heavy-fermion models, we identify that the outer gap originates from the splitting of the Abrikosov-Suhl-Kondo resonance due to the breaking of the valley symmetry arising from correlation-driven effects. Our results suggest an intricate but tractable hierarchy of correlated phases in twisted multilayer graphene.

cond-mat.supr-con↗

arXiv2025

New Results on a General Class of Minimum Norm Optimization Problems

We study the general norm optimization for combinatorial problems, initiated by Chakrabarty and Swamy (STOC 2019). We propose a general formulation that captures a large class of combinatorial structures: we are given a set $U$ of $n$ weighted elements and a family of feasible subsets $F$. Each subset $S\in F$ is called a feasible solution/set of the problem. We denote the value vector by $v=\{v_i\}_{i\in [n]}$, where $v_i\geq 0$ is the value of element $i$. For any subset $S\subseteq U$, we use $v[S]$ to denote the $n$-dimensional vector $\{v_e\cdot \mathbf{1}[e\in S]\}_{e\in U}$. Let $f: \mathbb{R}^n\rightarrow\mathbb{R}_+$ be a symmetric monotone norm function. Our goal is to minimize the norm objective $f(v[S])$ over feasible subset $S\in F$. We present a general equivalent reduction of the norm minimization problem to a multi-criteria optimization problem with logarithmic budget constraints, up to a constant approximation factor. Leveraging this reduction, we obtain constant factor approximation algorithms for the norm minimization versions of several covering problems, such as interval cover, multi-dimensional knapsack cover, and logarithmic factor approximation for set cover. We also study the norm minimization versions for perfect matching, $s$-$t$ path and $s$-$t$ cut. We show the natural linear programming relaxations for these problems have a large integrality gap. To complement the negative result, we show that, for perfect matching, there is a bi-criteria result: for any constant $ε,δ>0$, we can find in polynomial time a nearly perfect matching (i.e., a matching that matches at least $1-ε$ proportion of vertices) and its cost is at most $(8+δ)$ times of the optimum for perfect matching. Moreover, we establish the existence of a polynomial-time $O(\log\log n)$-approximation algorithm for the norm minimization variant of the $s$-$t$ path problem.

cs.DS↗

arXiv2025

Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design

Architecture design is a critical step in software development. However, creating a high-quality architecture is often costly due to the significant need for human expertise and manual effort. Recently, agents built upon Large Language Models (LLMs) have achieved remarkable success in various software engineering tasks. Despite this progress, the use of agents to automate the architecture design process remains largely unexplored. To address this gap, we envision a Knowledge-based Multi-Agent Architecture Design (MAAD) framework. MAAD uses agents to simulate human roles in the traditional software architecture design process, thereby automating the design process. To empower these agents, MAAD incorporates knowledge extracted from three key sources: 1) existing system designs, 2) authoritative literature, and 3) architecture experts. By envisioning the MAAD framework, we aim to advance the full automation of application-level system development.

cs.SE↗

arXiv2025

Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization

Commenting code is a crucial activity in software development, as it aids in facilitating future maintenance and updates. To enhance the efficiency of writing comments and reduce developers' workload, researchers has proposed various automated code summarization (ACS) techniques to automatically generate comments/summaries for given code units. However, these ACS techniques primarily focus on generating summaries for code units at the method level. There is a significant lack of research on summarizing higher-level code units, such as file-level and module-level code units, despite the fact that summaries of these higher-level code units are highly useful for quickly gaining a macro-level understanding of software components and architecture. To fill this gap, in this paper, we conduct a systematic study on how to use LLMs for commenting higher-level code units, including file level and module level. These higher-level units are significantly larger than method-level ones, which poses challenges in handling long code inputs within LLM constraints and maintaining efficiency. To address these issues, we explore various summarization strategies for ACS of higher-level code units, which can be divided into three types: full code summarization, reduced code summarization, and hierarchical code summarization. The experimental results suggest that for summarizing file-level code units, using the full code is the most effective approach, with reduced code serving as a cost-efficient alternative. However, for summarizing module-level code units, hierarchical code summarization becomes the most promising strategy. In addition, inspired by the research on method-level ACS, we also investigate using the LLM as an evaluator to evaluate the quality of summaries of higher-level code units. The experimental results demonstrate that the LLM's evaluation results strongly correlate with human evaluations.

cs.SE↗

arXiv2025

RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection

The recent generative AI models' capability of creating realistic and human-like content is significantly transforming the ways in which people communicate, create and work. The machine-generated content is a double-edged sword. On one hand, it can benefit the society when used appropriately. On the other hand, it may mislead people, posing threats to the society, especially when mixed together with natural content created by humans. Hence, there is an urgent need to develop effective methods to detect machine-generated content. However, the lack of aligned multimodal datasets inhibited the development of such methods, particularly in triple-modality settings (e.g., text, image, and voice). In this paper, we introduce RU-AI, a new large-scale multimodal dataset for robust and effective detection of machine-generated content in text, image and voice. Our dataset is constructed on the basis of three large publicly available datasets: Flickr8K, COCO and Places205, by adding their corresponding AI duplicates, resulting in a total of 1,475,370 instances. In addition, we created an additional noise variant of the dataset for testing the robustness of detection models. We conducted extensive experiments with the current SOTA detection methods on our dataset. The results reveal that existing models still struggle to achieve accurate and robust detection on our dataset. We hope that this new data set can promote research in the field of machine-generated content detection, fostering the responsible use of generative AI. The source code and datasets are available at https://github.com/ZhihaoZhang97/RU-AI.

cs.CV↗

arXiv2024

Demonstration Attack against In-Context Learning for Code Intelligence

Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software developers. To further improve the performance of LLMs on specific code intelligence tasks and reduce training costs, researchers reveal a new capability of LLMs: in-context learning (ICL). ICL allows LLMs to learn from a few demonstrations within a specific context, achieving impressive results without parameter updating. However, the rise of ICL introduces new security vulnerabilities in the code intelligence field. In this paper, we explore a novel security scenario based on the ICL paradigm, where attackers act as third-party ICL agencies and provide users with bad ICL content to mislead LLMs outputs in code intelligence tasks. Our study demonstrates the feasibility and risks of such a scenario, revealing how attackers can leverage malicious demonstrations to construct bad ICL content and induce LLMs to produce incorrect outputs, posing significant threats to system security. We propose a novel method to construct bad ICL content called DICE, which is composed of two stages: Demonstration Selection and Bad ICL Construction, constructing targeted bad ICL content based on the user query and transferable across different query inputs. Ultimately, our findings emphasize the critical importance of securing ICL mechanisms to protect code intelligence systems from adversarial manipulation.

cs.CR↗

arXiv2024

Twist-Programmable Superconductivity in Spin-Orbit Coupled Bilayer Graphene

The relative twist angle between layers of near-lattice-matched van der Waals materials is critical for the emergent correlated phenomena associated with moire flat bands. However, the concept of angle rotation control is not exclusive to moiré superlattices in which electrons directly experience a twist-angle-dependent periodic potential. Instead, it can also be employed to induce programmable symmetry-breaking perturbations with the goal of stabilizing desired correlated states. Here, we experimentally demonstrate `moireless' twist-tuning of superconductivity together with other correlated orders in Bernal bilayer graphene proximitized by tungsten diselenide. The alignment between the two materials systematically controls the strength of the induced Ising spin-orbit coupling (SOC), profoundly altering the phase diagram. As Ising SOC is increased, superconductivity onsets at a higher displacement field and features a higher critical temperature, reaching up to 0.5K. Within the main superconducting dome and in the strong Ising SOC limit, we find an unusual phase transition characterized by a nematic redistribution of holes among trigonally warped Fermi pockets and enhanced resilience to in-plane magnetic fields. The behavior of the superconducting phase is well captured by our theoretical model, which emphasizes the role of interband interactions between Fermi pockets arising due to interaction-enhanced symmetry breaking. Moreover, we identify two additional superconducting regions, one of which descends from an inter-valley coherent normal state and exhibits a Pauli-limit violation ratio exceeding 40, among the highest for all known superconductors. Our results provide new insights into ultra-clean graphene-based superconductors and underscore the potential of utilizing moireless-twist engineering across a range of van der Waals heterostructures.

cond-mat.supr-con↗

arXiv2024

TrustNavGPT: Modeling Uncertainty to Improve Trustworthiness of Audio-Guided LLM-Based Robot Navigation

While LLMs are proficient at processing text in human conversations, they often encounter difficulties with the nuances of verbal instructions and, thus, remain prone to hallucinate trust in human command. In this work, we present TrustNavGPT, an LLM based audio guided navigation agent that uses affective cues in spoken communication elements such as tone and inflection that convey meaning beyond words, allowing it to assess the trustworthiness of human commands and make effective, safe decisions. Our approach provides a lightweight yet effective approach that extends existing LLMs to model audio vocal features embedded in the voice command and model uncertainty for safe robotic navigation.

cs.RO↗