arXiv subjects

Xiaofei Xie

Publications and source records attributed to Xiaofei Xie.

At least 55 records · Page 3Linked to original sources

arXiv2025

Leveraging LLM Agents for Automated Video Game Testing

Testing MMORPGs (Massively Multiplayer Online Role-Playing Games) is a critical yet labor-intensive task in game development due to their complexity and frequent updating nature. Traditional automated game testing approaches struggle to achieve high state coverage and efficiency in these rich, open-ended environments, while existing LLM-based game-playing approaches are limited to shallow reasoning ability in understanding complex game state-action spaces and long-complex tasks. To address these challenges, we propose TITAN, an effective LLM-driven agent framework for intelligent MMORPG testing. TITAN incorporates four key components to: (1) perceive and abstract high-dimensional game states, (2) proactively optimize and prioritize available actions, (3) enable long-horizon reasoning with action trace memory and reflective self-correction, and (4) employ LLM-based oracles to detect potential functional and logic bugs with diagnostic reports. We implement the prototype of TITAN and evaluate it on two large-scale commercial MMORPGs spanning both PC and mobile platforms. In our experiments, TITAN achieves significantly higher task completion rates (95%) and bug detection performance compared to existing automated game testing approaches. An ablation study further demonstrates that each core component of TITAN contributes substantially to its overall performance. Notably, TITAN detects four previously unknown bugs that prior testing approaches fail to identify. We provide an in-depth discussion of these results, which offer guidance for new avenues of advancing intelligent, general-purpose testing systems. Moreover, TITAN has been deployed in eight real-world game QA pipelines, underscoring its practical impact as an LLM-driven game testing framework.

cs.SE↗

arXiv2025

Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they struggle to interpret what programs actually do during runtime, and (2) the inconsistent and fragmented representation of semantic information, such as execution traces, across existing methods, which hinders their ability to generalize and reason effectively. These challenges underscore the necessity for more systematic approaches to enhance the reasoning capabilities of Code LLMs. To address these issues, we introduce a generic framework to support integrating semantic information~(e.g., execution trace) to code task-relevant prompts, and conduct a comprehensive study to explore the role of semantic information in enhancing the reasoning ability of Code LLMs accordingly. Specifically, we focus on investigating the usefulness of trace-based semantic information in boosting supervised fine-tuning~(SFT) and post-phase inference of Code LLMs. The experimental results surprisingly disagree with previous works and demonstrate that semantic information has limited usefulness for SFT and test time scaling of Code LLM.

cs.SE↗

arXiv2025

Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations

Code generation models are widely used in software development, yet their sensitivity to prompt phrasing remains under-examined. Identical requirements expressed with different emotions or communication styles can yield divergent outputs, while most benchmarks emphasize only peak performance. We present PromptSE (Prompt Sensitivity Evaluation), a framework that creates semantically equivalent prompt variants with emotion and personality templates, and that evaluates stability using probability aware continuous scoring or using binary pass rates when logits are unavailable. The results are aggregated into a proposed area under curve metric (AUC-E) for cross model comparison. Across 14 models from three families (Llama, Qwen, and DeepSeek), our study shows that performance and stability behave as largely decoupled optimization objectives, and it reveals architectural and scale related patterns that challenge common assumptions about model robustness. The framework supports rapid screening for closed-source models as well as detailed stability analysis in research settings. PromptSE enables practitioners to quantify performance stability trade offs for deployment and model selection, positioning prompt stability as a complementary evaluation dimension alongside performance and fairness, and contributing to more trustworthy AI-assisted software development tools.

cs.SE↗

arXiv2025

FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned faster than normal knowledge, and ii) trigger patterns have a greater effect on image classification than normal class patterns. Our approach generates the images with newly learned knowledge by identifying the differences between the old and new global models, and filters trigger images by evaluating the effect of these generated images. By using these trigger images, our approach eliminates poisoned models to ensure the updated global model is benign. Comprehensive experiments demonstrate that our approach can defend against almost all the existing types of backdoor attacks and outperform all the seven state-of-the-art defense methods with both IID and non-IID scenarios. Especially, our approach can successfully defend against the backdoor attack even when 80\% of the clients are malicious.

cs.LG↗

arXiv2025

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning

Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for identifying the most important data to label. Despite this success, one question remains unanswered: is AL safe? In this work, we introduce ALA, a practical and the first framework to utilize the acquisition function as the poisoning attack surface to reveal the weakness of active learning. Specifically, ALA optimizes imperceptibly poisoned inputs to exhibit high uncertainty scores, increasing their probability of being selected by acquisition functions. To evaluate ALA, we conduct extensive experiments across three datasets, three acquisition functions, and two types of clean-label backdoor triggers. Results show that our attack can achieve high success rates (up to 94%) even under low poisoning budgets (0.5%-1.0%) while preserving model utility and remaining undetectable to human annotators. Our findings remind active learning users: acquisition functions can be easily exploited, and active learning should be deployed with caution in trusted data scenarios.

cs.CR↗

arXiv2025

Understanding the Supply Chain and Risks of Large Language Model Applications

The rise of Large Language Models (LLMs) has led to the widespread deployment of LLM-based systems across diverse domains. As these systems proliferate, understanding the risks associated with their complex supply chains is increasingly important. LLM-based systems are not standalone as they rely on interconnected supply chains involving pretrained models, third-party libraries, datasets, and infrastructure. Yet, most risk assessments narrowly focus on model or data level, overlooking broader supply chain vulnerabilities. While recent studies have begun to address LLM supply chain risks, there remains a lack of benchmarks for systematic research. To address this gap, we introduce the first comprehensive dataset for analyzing and benchmarking LLM supply chain security. We collect 3,859 real-world LLM applications and perform interdependency analysis, identifying 109,211 models, 2,474 datasets, and 9,862 libraries. We extract model fine-tuning paths, dataset reuse, and library reliance, mapping the ecosystem's structure. To evaluate security, we gather 1,555 risk-related issues-50 for applications, 325 for models, 18 for datasets, and 1,229 for libraries from public vulnerability databases. Using this dataset, we empirically analyze component dependencies and risks. Our findings reveal deeply nested dependencies in LLM applications and significant vulnerabilities across the supply chain, underscoring the need for comprehensive security analysis. We conclude with practical recommendations to guide researchers and developers toward safer, more trustworthy LLM-enabled systems.

cs.SE↗

arXiv2025

GUI Test Migration via Abstraction and Concretization

GUI test migration aims to produce test cases with events and assertions to test specific functionalities of a target app. Existing migration approaches typically focus on the widget-mapping paradigm that maps widgets from source apps to target apps. However, since different apps may implement the same functionality in different ways, direct mapping may result in incomplete or buggy test cases, thus significantly impacting the effectiveness of testing target functionality and the practical applicability of migration approaches. In this paper, we propose a new migration paradigm (i.e., the abstraction-concretization paradigm) that first abstracts the test logic for the target functionality and then utilizes this logic to generate the concrete GUI test case. Furthermore, we introduce MACdroid, the first approach that migrates GUI test cases based on this paradigm. Specifically, we propose an abstraction technique that utilizes source test cases from source apps targeting the same functionality to extract a general test logic for that functionality. Then, we propose a concretization technique that utilizes the general test logic to guide an LLM in generating the corresponding GUI test case (including events and assertions) for the target app. We evaluate MACdroid on two widely-used datasets (including 31 apps, 34 functionalities, and 123 test cases). On the FrUITeR dataset, the test cases generated by MACdroid successfully test 64% of the target functionalities, improving the baselines by 191%. On the Lin dataset, MACdroid successfully tests 75% of the target functionalities, outperforming the baselines by 42%. These results underscore the effectiveness of MACdroid in GUI test migration.

cs.SE↗

arXiv2025

Gradients as an Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two major problems: i) extremely high communication overhead due to massive item embeddings involved in recommendation systems, and ii) intolerably low training efficiency caused by the entanglement of both heterogeneous network environments and client devices. Although existing methods attempt to employ various compression techniques to reduce communication overhead, due to the parameter errors introduced by model compression, they inevitably suffer from model performance degradation. To simultaneously address the above problems, this paper presents a communication-efficient FedRec framework named FedRAS, which adopts an action-sharing strategy to cluster the gradients of item embedding into a specific number of model updating actions for communication rather than directly compressing the item embeddings. In this way, the cloud server can use the limited actions from clients to update all the items. Since gradient values are significantly smaller than item embeddings, constraining the directions of gradients (i.e., the action space) introduces smaller errors compared to compressing the entire item embedding matrix into a reduced space. To accommodate heterogeneous devices and network environments, FedRAS incorporates an adaptive clustering mechanism that dynamically adjusts the number of actions. Comprehensive experiments on well-known datasets demonstrate that FedRAS can reduce the size of communication payloads by up to 96.88%, while not sacrificing recommendation performance within various heterogeneous scenarios. We have open-sourced FedRAS at https://github.com/mastlab-T3S/FedRAS.

cs.LG↗

arXiv2025

ADReFT: Adaptive Decision Repair for Safe Autonomous Driving via Reinforcement Fine-Tuning

Autonomous Driving Systems (ADSs) continue to face safety-critical risks due to the inherent limitations in their design and performance capabilities. Online repair plays a crucial role in mitigating such limitations, ensuring the runtime safety and reliability of ADSs. Existing online repair solutions enforce ADS compliance by transforming unacceptable trajectories into acceptable ones based on predefined specifications, such as rule-based constraints or training datasets. However, these approaches often lack generalizability, adaptability and tend to be overly conservative, resulting in ineffective repairs that not only fail to mitigate safety risks sufficiently but also degrade the overall driving experience. To address this issue, we propose Adaptive Decision Repair (ADReFT), a novel and effective repair method that identifies safety-critical states through offline learning from failed tests and generates appropriate mitigation actions to improve ADS safety. Specifically, ADReFT incorporates a transformer-based model with two joint heads, State Monitor and Decision Adapter, designed to capture complex driving environment interactions to evaluate state safety severity and generate adaptive repair actions. Given the absence of oracles for state safety identification, we first pretrain ADReFT using supervised learning with coarse annotations, i.e., labeling states preceding violations as positive samples and others as negative samples. It establishes ADReFT's foundational capability to mitigate safety-critical violations, though it may result in somewhat conservative mitigation strategies. Therefore, we subsequently finetune ADReFT using reinforcement learning to improve its initial capability and generate more precise and contextually appropriate repair decisions. Our evaluation results illustrate that ADReFT achieves better repair performance.

cs.LG↗

arXiv2025

STCLocker: Deadlock Avoidance Testing for Autonomous Driving Systems

Autonomous Driving System (ADS) testing is essential to ensure the safety and reliability of autonomous vehicles (AVs) before deployment. However, existing techniques primarily focus on evaluating ADS functionalities in single-AV settings. As ADSs are increasingly deployed in multi-AV traffic, it becomes crucial to assess their cooperative performance, particularly regarding deadlocks, a fundamental coordination failure in which multiple AVs enter a circular waiting state indefinitely, resulting in motion planning failures. Despite its importance, the cooperative capability of ADSs to prevent deadlocks remains insufficiently underexplored. To address this gap, we propose the first dedicated Spatio-Temporal Conflict-Guided Deadlock Avoidance Testing technique, STCLocker, for generating DeadLock Scenarios (DLSs), where a group of AVs controlled by the ADS under test are in a circular wait state. STCLocker consists of three key components: Deadlock Oracle, Conflict Feedback, and Conflict-aware Scenario Generation. Deadlock Oracle provides a reliable black-box mechanism for detecting deadlock cycles among multiple AVs within a given scenario. Conflict Feedback and Conflict-aware Scenario Generation collaborate to actively guide AVs into simultaneous competition over spatial conflict resources (i.e., shared passing regions) and temporal competitive behaviors (i.e., reaching the conflict region at the same time), thereby increasing the effectiveness of generating conflict-prone deadlocks. We evaluate STCLocker on two types of ADSs: Roach, an end-to-end ADS, and OpenCDA, a module-based ADS supporting cooperative communication. Experimental results show that, on average, STCLocker generates more DLS than the best-performing baseline.

cs.SE↗

arXiv2025

VulStamp: Vulnerability Assessment using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess low exploitability or would incur negligible impact in practical operational environments. Consequently, vulnerability severity assessment has emerged as a critical component in optimizing software development efficiency. Existing vulnerability assessment methods typically rely on manually crafted descriptions associated with source code artifacts. However, due to variability in description quality and subjectivity in intention interpretation, the performance of these methods is seriously limited. To address this issue, this paper introduces VulStamp, a novel intention-guided framework, to facilitate description-free vulnerability assessment. Specifically, VulStamp adopts static analysis together with Large Language Model (LLM) to extract the intention information of vulnerable code. Based on the intention information, VulStamp uses a prompt-tuned model for vulnerability assessment. Furthermore, to mitigate the problem of imbalanced data associated with vulnerability types, VulStamp integrates a Reinforcement Learning (RL)-based prompt-tuning method to train the assessment model.

cs.SE↗

arXiv2025

Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing

Large language model-(LLM) based automated program repair (APR) techniques have shown promising results in resolving real-world GitHub issue tasks. Existing APR systems are primarily evaluated in unimodal settings (e.g., SWE-bench). However, these autonomous systems struggle to resolve multimodal problem scenarios (e.g., SWE-bench M) due to limitations in interpreting and leveraging visual information. In multimodal scenarios, LLMs need to rely on visual information in the graphical user interface (GUI) to understand bugs and generate fixes. To bridge this gap, we propose GUIRepair, a cross-modal reasoning approach for resolving multimodal issue scenarios by understanding and capturing visual information. Specifically, GUIRepair integrates two key components, Image2Code and Code2Image, to enhance fault comprehension and patch validation. Image2Code extracts relevant project documents based on the issue report, then applies this domain knowledge to generate the reproduced code responsible for the visual symptoms, effectively translating GUI images into executable context for better fault comprehension. Code2Image replays the visual issue scenario using the reproduced code and captures GUI renderings of the patched program to assess whether the fix visually resolves the issue, providing feedback for patch validation. We evaluate GUIRepair on SWE-bench M, and the approach demonstrates significant effectiveness. When utilizing GPT-4o as the base model, GUIRepair solves 157 instances, outperforming the best open-source baseline by 26 instances. Furthermore, when using o4-mini as the base model, GUIRepair can achieve even better results and solve 175 instances, outperforming the top commercial system by 22 instances. This emphasizes the success of our new perspective on incorporating cross-modal reasoning by understanding and capturing visual information to resolve multimodal issues.

cs.SE↗

arXiv2025

The Foundation Cracks: A Comprehensive Study on Bugs and Testing Practices in LLM Libraries

Large Language Model (LLM) libraries have emerged as the foundational infrastructure powering today's AI revolution, serving as the backbone for LLM deployment, inference optimization, fine-tuning, and production serving across diverse applications. Despite their critical role in the LLM ecosystem, these libraries face frequent quality issues and bugs that threaten the reliability of AI systems built upon them. To address this knowledge gap, we present the first comprehensive empirical investigation into bug characteristics and testing practices in modern LLM libraries. We examine 313 bug-fixing commits extracted across two widely-adopted LLM libraries: HuggingFace Transformers and vLLM.Through rigorous manual analysis, we establish comprehensive taxonomies categorizing bug symptoms into 5 types and root causes into 14 distinct categories.Our primary discovery shows that API misuse has emerged as the predominant root cause (32.17%-48.19%), representing a notable transition from algorithm-focused defects in conventional deep learning frameworks toward interface-oriented problems. Additionally, we examine 7,748 test functions to identify 7 distinct test oracle categories employed in current testing approaches, with predefined expected outputs (such as specific tensors and text strings) being the most common strategy. Our assessment of existing testing effectiveness demonstrates that the majority of bugs escape detection due to inadequate test cases (41.73%), lack of test drivers (32.37%), and weak test oracles (25.90%). Drawing from these findings, we offer some recommendations for enhancing LLM library quality assurance.

cs.SE↗

arXiv2025

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-linguistic reasoning abilities. This dual limitation makes it challenging to comprehensively assess LLMs' performance in the multilingual setting. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-linguistic comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves multiple powerful LLMs for translation, followed by expert review to ensure accurate expression, consistent terminology, and cultural relevance. Building on this, we systematically evaluate 36 state-of-the-art LLMs, including reasoning-enhanced and multilingual-optimized LLMs. The results reveal significant disparities in the multilingual capabilities of LLMs: While they perform well in high-resource languages, their performance declines markedly in low-resource languages, with gaps of up to 24.3%. Through MMLU-ProX, we aim to advance the development of more inclusive AI systems and promote equitable access to technology across global contexts.

cs.CL↗

arXiv2025

A Systematic Literature Review on Neural Code Translation

Code translation aims to convert code from one programming language to another automatically. It is motivated by the need for multi-language software development and legacy system migration. In recent years, neural code translation has gained significant attention, driven by rapid advancements in deep learning and large language models. Researchers have proposed various techniques to improve neural code translation quality. However, to the best of our knowledge, no comprehensive systematic literature review has been conducted to summarize the key techniques and challenges in this field. To fill this research gap, we collected 57 primary studies covering the period 2020~2025 on neural code translation. These studies are analyzed from seven key perspectives: task characteristics, data preprocessing, code modeling, model construction, post-processing, evaluation subjects, and evaluation metrics. Our analysis reveals current research trends, identifies unresolved challenges, and shows potential directions for future work. These findings can provide valuable insights for both researchers and practitioners in the field of neural code translation.

cs.SE↗

arXiv2025

Benchmarking and Revisiting Code Generation Assessment: A Mutation-Based Approach

Code Large Language Models (CLLMs) have exhibited outstanding performance in program synthesis, attracting the focus of the research community. The evaluation of CLLM's program synthesis capability has generally relied on manually curated benchmarks. However, there is a substantial gap between real-world scenarios and benchmark settings. Existing benchmarks typically provide only a single input prompt for the evaluation of each synthesis problem. However, in practice, a problem can be described in various ways, including with typos, where developers may struggle to understand certain descriptions and seek clarification to find more suitable wording. Such various descriptions may lead to variations in the performance of CLLMs on the same question, resulting in a biased evaluation when using existing benchmarks. In this paper, we aim to explore these pitfalls with the goal of revisiting and enhancing future benchmark designs. To simulate real-world variations in problem descriptions, we propose 10 mutation strategies and introduce three new metrics to evaluate their impact on code generation. We then assess five popular CLLMs using 12,834 generated prompt variants, and found a significant performance discrepancy between the results from existing benchmarks and those from mutated benchmarks containing perturbations and variations. This finding underscores the need for more robust evaluation methods and benchmarks.

cs.SE↗

arXiv2025

TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis

Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW) content, such as pornography, violence, political content, and discrimination. To mitigate the risk of generating NSFW content, refusal mechanisms, i.e., safety checkers, have been developed to check potential NSFW content. Adversarial prompting techniques have been developed to evaluate the robustness of the refusal mechanisms. The key challenge remains to subtly modify the prompt in a way that preserves its sensitive nature while bypassing the refusal mechanisms. In this paper, we introduce TokenProber, a method designed for sensitivity-aware differential testing, aimed at evaluating the robustness of the refusal mechanisms in T2I models by generating adversarial prompts. Our approach is based on the key observation that adversarial prompts often succeed by exploiting discrepancies in how T2I models and safety checkers interpret sensitive content. Thus, we conduct a fine-grained analysis of the impact of specific words within prompts, distinguishing between dirty words that are essential for NSFW content generation and discrepant words that highlight the different sensitivity assessments between T2I models and safety checkers. Through the sensitivity-aware mutation, TokenProber generates adversarial prompts, striking a balance between maintaining NSFW content generation and evading detection. Our evaluation of TokenProber against 5 safety checkers on 3 popular T2I models, using 324 NSFW prompts, demonstrates its superior effectiveness in bypassing safety filters compared to existing methods (e.g., 54%+ increase on average), highlighting TokenProber's ability to uncover robustness issues in the existing refusal mechanisms.

cs.CR↗

arXiv2025

PatchFuzz: Patch Fuzzing for JavaScript Engines

Patch fuzzing is a technique aimed at identifying vulnerabilities that arise from newly patched code. While researchers have made efforts to apply patch fuzzing to testing JavaScript engines with considerable success, these efforts have been limited to using ordinary test cases or publicly available vulnerability PoCs (Proof of Concepts) as seeds, and the sustainability of these approaches is hindered by the challenges associated with automating the PoC collection. To address these limitations, we propose an end-to-end sustainable approach for JavaScript engine patch fuzzing, named PatchFuzz. It automates the collection of PoCs of a broader range of historical vulnerabilities and leverages both the PoCs and their corresponding patches to uncover new vulnerabilities more effectively. PatchFuzz starts by recognizing git commits which intend to fix security bugs. Subsequently, it extracts and processes PoCs from these commits to form the seeds for fuzzing, while utilizing code revisions to focus limited fuzzing resources on the more vulnerable code areas through selective instrumentation. The mutation strategy of PatchFuzz is also optimized to maximize the potential of the PoCs. Experimental results demonstrate the effectiveness of PatchFuzz. Notably, 54 bugs across six popular JavaScript engines have been exposed and a total of $62,500 bounties has been received.

cs.CR↗