arXiv subjects

Qianxiang Wang

Publications and source records attributed to Qianxiang Wang.

At least 19 recordsLinked to original sources

arXiv2026

Context Matters: Improving the Practical Reliability of LLM-Based Unit Test Generation

Automated unit test generation has recently benefited from advances in large language models (LLMs), yet our industrial deployments reveal a persistent gap between promising research results and practical usability. In real-world projects with complex frameworks and cross-file dependencies, LLM-generated tests frequently fail to compile, require costly manual repair, or provide unstable coverage improvements. This paper reports our experience in designing, deploying, and evaluating CATGen, a context-aware workflow for LLM-based unit test generation, informed by repeated industrial failures and refinements. Rather than relying on LLMs to infer incomplete project context, we found that compilation robustness critically depends on making project-level dependencies explicit, stabilizing test class scaffolding, and replacing iterative LLM-based repair with lightweight static analysis. These experience-driven insights shaped CATGen's multi-stage design, which combines structured context retrieval, deterministic test skeleton construction, and program analysis-based post-processing. We evaluate CATGen on real-world complex focal methods from proprietary industrial projects and additionally on the Defects4J benchmark to assess generalizability. Across both settings, CATGen substantially improves compilation success and structural coverage while significantly reducing generation time and token consumption compared to existing LLM-based approaches. Our results demonstrate that reliable LLM-based unit test generation in practice depends less on prompt engineering alone and more on systematic engineering support grounded in real-world development constraints.

cs.SE↗

arXiv2026

XSearch: Explainable Code Search via Concept-to-Code Alignment

Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embedding space and retrieve results based on vector similarity. Despit strong performance on benchmark datasets, they often suffer from poor explainability and generalization. Retrieved code may appear semantically similar yet miss critical functional requirements of the query, while providing no explanation of why the result was retrieved. Moreover, such failures become more severe under distribution shift, where models struggle to generalize to unseen benchmarks. In this work, we propose XSearch, an intrinsically explainable code search framework. Our key insight is that by relying on global embedding similarity, existing retrievers inherently take an inductive view. They learn statistical patterns rather than truly understanding the query's functional requirements. We address this problem by reformulating code search as a deductive concept alignment problem. XSearch (i) identifies functional concepts in the query and (ii) explicitly aligns them with corresponding code statements. This explain-then-predict design produces inherent concept-level explanations and mitigates shortcut learning that harms out-of-distribution generalization. We train an encoder with explicit concept-alignment objectives and perform retrieval through explicit matching between query concepts and code statements. Experiments show that, trained on CodeSearchNet using GraphCodeBERT (125M parameters), XSearch improves performance on out-of-distribution benchmarks from 0.02 to 0.33 (15x) over eight state-of-the-art retrievers, and consistently outperforms both encoder- and decoder-based baselines with up to 7B parameters. A user study demonstrates that concept-alignment explanations enable users to evaluate retrieved results faster and more accurately.

cs.SE↗

arXiv2026

Towards an Understanding of Context Utilization in Code Intelligence

Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that incorporating contextual information beyond the basic original task inputs (i.e., source code) can substantially enhance model performance. Such contextual signals may be obtained directly or indirectly from sources such as API documentation or intermediate representations like abstract syntax trees can significantly improve the effectiveness of code intelligence. Despite growing academic interest, there is a lack of systematic analysis of context in code intelligence. To address this gap, we conduct an extensive literature review of 146 relevant studies published between September 2007 and August 2024. Our investigation yields four main contributions. (1) A quantitative analysis of the research landscape, including publication trends, venues, and the explored domains; (2) A novel taxonomy of context types used in code intelligence; (3) A task-oriented analysis investigating context integration strategies across diverse code intelligence tasks; (4) A critical evaluation of evaluation methodologies for context-aware methods. Based on these findings, we identify fundamental challenges in context utilization in current code intelligence systems and propose a research roadmap that outlines key opportunities for future research.

cs.SE↗

arXiv2026

SWE-Exp: Experience-Driven Software Issue Resolution

Recent advances in large language model (LLM) agents have shown remarkable progress in software issue resolution, leveraging advanced techniques such as multi-agent collaboration and Monte Carlo Tree Search (MCTS). However, current agents act as memoryless explorers - treating each problem separately without retaining or reusing knowledge from previous repair experiences. This leads to redundant exploration of failed trajectories and missed chances to adapt successful issue resolution methods to similar problems. To address this problem, we introduce SWE-Exp, an experience-enhanced approach that distills concise and actionable experience from prior agent trajectories, enabling continuous learning across issues. Our method introduces a multi-faceted experience bank that captures both successful and failed repair attempts. Specifically, it extracts reusable issue resolution knowledge at different levels - from high-level problem comprehension to specific code changes. Experiments show that SWE-Exp achieves a Pass@1 resolution rate of 73.0% on SWE-Bench Verified using the state-of-the-art LLM Claude 4 Sonnet, significantly outperforming prior results under other agent frameworks. Our approach establishes a new paradigm in which automated software engineering agents systematically accumulate and leverage repair expertise, fundamentally shifting from trial-and-error exploration to strategic, experience-driven issue resolution.

cs.SE↗

arXiv2025

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

Issue resolution has made remarkable progress thanks to the advanced reasoning capabilities of large language models (LLMs). Recently, agent-based frameworks such as SWE-agent have further advanced this progress by enabling autonomous, tool-using agents to tackle complex software engineering tasks. While existing agent-based issue resolution approaches are primarily based on agents' independent explorations, they often get stuck in local solutions and fail to identify issue patterns that span across different parts of the codebase. To address this limitation, we propose SWE-Debate, a competitive multi-agent debate framework that encourages diverse reasoning paths and achieves more consolidated issue localization. SWE-Debate first creates multiple fault propagation traces as localization proposals by traversing a code dependency graph. Then, it organizes a three-round debate among specialized agents, each embodying distinct reasoning perspectives along the fault propagation trace. This structured competition enables agents to collaboratively converge on a consolidated fix plan. Finally, this consolidated fix plan is integrated into an MCTS-based code modification agent for patch generation. Experiments on the SWE-bench benchmark show that SWE-Debate achieves new state-of-the-art results in open-source agent frameworks and outperforms baselines by a large margin.

cs.SE↗

arXiv2024

CodeV: Issue Resolving with Visual Data

Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue resolving is a key challenge among these tasks. While recent approaches have made progress on this task, they focus on textual data within issues, neglecting visual data. However, this visual data is crucial for resolving issues as it conveys additional knowledge that text alone cannot. We propose CodeV, the first approach to leveraging visual data to enhance the issue-resolving capabilities of LLMs. CodeV resolves each issue by following a two-phase process: data processing and patch generation. To evaluate CodeV, we construct a benchmark for visual issue resolving, namely Visual SWE-bench. Through extensive experiments, we demonstrate the effectiveness of CodeV, as well as provide valuable insights into leveraging visual data to resolve GitHub issues.

cs.SE↗

arXiv2024

On the Evaluation of Large Language Models in Unit Test Generation

Unit testing is an essential activity in software development for verifying the correctness of software components. However, manually writing unit tests is challenging and time-consuming. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation. Existing research primarily focuses on closed-source LLMs (e.g., ChatGPT and CodeX) with fixed prompting strategies, leaving the capabilities of advanced open-source LLMs with various prompting settings unexplored. Particularly, open-source LLMs offer advantages in data privacy protection and have demonstrated superior performance in some tasks. Moreover, effective prompting is crucial for maximizing LLMs' capabilities. In this paper, we conduct the first empirical study to fill this gap, based on 17 Java projects, five widely-used open-source LLMs with different structures and parameter sizes, and comprehensive evaluation metrics. Our findings highlight the significant influence of various prompt factors, show the performance of open-source LLMs compared to the commercial GPT-4 and the traditional Evosuite, and identify limitations in LLM-based unit test generation. We then derive a series of implications from our study to guide future research and practical use of LLM-based unit test generation.

cs.SE↗

arXiv2024

Agents in Software Engineering: Survey, Landscape, and Vision

In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field. We find that many studies combining LLMs with SE have employed the concept of agents either explicitly or implicitly. However, there is a lack of an in-depth survey to sort out the development context of existing works, analyze how existing works combine the LLM-based agent technologies to optimize various tasks, and clarify the framework of LLM-based agents in SE. In this paper, we conduct the first survey of the studies on combining LLM-based agents with SE and present a framework of LLM-based agents in SE which includes three key modules: perception, memory, and action. We also summarize the current challenges in combining the two fields and propose future opportunities in response to existing challenges. We maintain a GitHub repository of the related papers at: https://github.com/DeepSoftwareAnalytics/Awesome-Agent4SE.

cs.SE↗

arXiv2024

GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model

The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit less satisfactory performance on repository-level completion due to the lack of repository-specific knowledge in these LLMs. To address this problem, we propose GraphCoder, a retrieval-augmented code completion framework that leverages LLMs' general code knowledge and the repository-specific knowledge via a graph-based retrieval-generation process. In particular, GraphCoder captures the context of completion target more accurately through code context graph (CCG) that consists of control-flow, data- and control-dependence between code statements, a more structured way to capture the completion target context than the sequence-based context used in existing retrieval-augmented approaches; based on CCG, GraphCoder further employs a coarse-to-fine retrieval process to locate context-similar code snippets with the completion target from the current repository. Experimental results demonstrate both the effectiveness and efficiency of GraphCoder: Compared to baseline retrieval-augmented methods, GraphCoder achieves higher exact match (EM) on average, with increases of +6.06 in code match and +6.23 in identifier match, while using less time and space.

cs.SE↗

arXiv2024

SWE-bench-java: A GitHub Issue Resolving Benchmark for Java

GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia. Within this task, SWE-bench has been released to evaluate issue resolving capabilities of large language models (LLMs), but has so far only focused on Python version. However, supporting more programming languages is also important, as there is a strong demand in industry. As a first step toward multilingual support, we have developed a Java version of SWE-bench, called SWE-bench-java. We have publicly released the dataset, along with the corresponding Docker-based evaluation environment and leaderboard, which will be continuously maintained and updated in the coming months. To verify the reliability of SWE-bench-java, we implement a classic method SWE-agent and test several powerful LLMs on it. As is well known, developing a high-quality multi-lingual benchmark is time-consuming and labor-intensive, so we welcome contributions through pull requests or collaboration to accelerate its iteration and refinement, paving the way for fully automated programming.

cs.SE↗

arXiv2024

CodeR: Issue Resolving with Multi-Agent and Task Graphs

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.

cs.CL↗

arXiv2024

CompVPD: Iteratively Identifying Vulnerability Patches Based on Human Validation Results with a Precise Context

Applying security patches in open source software timely is critical for ensuring the security of downstream applications. However, it is challenging to apply these patches promptly because notifications of patches are often incomplete and delayed. To address this issue, existing approaches employ deep-learning (DL) models to identify additional vulnerability patches by determining whether a code commit addresses a vulnerability. Nonetheless, these approaches suffer from low accuracy due to the imprecise context provided for the patches. To provide precise context for patches, we propose a multi-granularity slicing algorithm and an adaptive-expanding algorithm to accurately identify code related to the patches. Additionally, the precise context enables to design an iterative identification framework, CompVPD, which utilizes the human validation results, and substantially improve the effectiveness. We empirically compare CompVPD with four state-of-the-art/practice (SOTA) approaches in identifying vulnerability patches. The results demonstrate that CompVPD improves the F1 score by 20% compared to the best scores of the SOTA approaches. Additionally, CompVPD contributes to security practice by helping identify 20 vulnerability patches and 18 fixes for high-risk bugs from 2,500 recent code commits in five highly popular open-source projects.

cs.CR↗

arXiv2024

VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model

Security practitioners maintain vulnerability reports (e.g., GitHub Advisory) to help developers mitigate security risks. An important task for these databases is automatically extracting structured information mentioned in the report, e.g., the affected software packages, to accelerate the defense of the vulnerability ecosystem. However, it is challenging for existing work on affected package identification to achieve a high accuracy. One reason is that all existing work focuses on relatively smaller models, thus they cannot harness the knowledge and semantic capabilities of large language models. To address this limitation, we propose VulLibGen, the first method to use LLM for affected package identification. In contrast to existing work, VulLibGen proposes the novel idea to directly generate the affected package. To improve the accuracy, VulLibGen employs supervised fine-tuning (SFT), retrieval augmented generation (RAG) and a local search algorithm. The local search algorithm is a novel postprocessing algorithm we introduce for reducing the hallucination of the generated packages. Our evaluation results show that VulLibGen has an average accuracy of 0.806 for identifying vulnerable packages in the four most popular ecosystems in GitHub Advisory (Java, JS, Python, Go) while the best average accuracy in previous work is 0.721. Additionally, VulLibGen has high value to security practice: we submitted 60 pairs to GitHub Advisory (covers four ecosystems). 34 of them have been accepted and merged and 20 are pending approval. Our code and dataset can be found in the attachments.

cs.CR↗

arXiv2024

CodeS: Natural Language to Code Repository via Multi-Layer Sketch

The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task.

cs.CL↗

arXiv2024

CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models

Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models such as Codex, CodeGen, and PanGu-Coder. To evaluate the effectiveness of these models, multiple existing benchmarks are proposed, including only cases of generating a standalone function, i.e., a function that may invoke or access only built-in functions and standard libraries. However, non-standalone functions, which typically are not included in the existing benchmarks, constitute more than 70% of the functions in popular open-source projects, and evaluating models' effectiveness on standalone functions cannot reflect these models' effectiveness on pragmatic code generation scenarios. To help bridge the preceding gap, in this paper, we propose a benchmark named CoderEval, consisting of 230 Python and 230 Java code generation tasks carefully curated from popular real-world open-source projects and a self-contained execution platform to automatically assess the functional correctness of generated code. CoderEval supports code generation tasks from six levels of context dependency, where context refers to code elements such as types, APIs, variables, and consts defined outside the function under generation but within the dependent third-party libraries, current class, file, or project. CoderEval can be used to evaluate the effectiveness of models in generating code beyond only standalone functions. By evaluating three code generation models on CoderEval, we find that the effectiveness of these models in generating standalone functions is substantially higher than that in generating non-standalone functions. Our analysis highlights the current progress and pinpoints future directions to further improve a model's effectiveness by leveraging contextual information for pragmatic code generation.

cs.SE↗

arXiv2023

Identifying Vulnerable Third-Party Java Libraries from Textual Descriptions of Vulnerabilities and Libraries

To address security vulnerabilities arising from third-party libraries, security researchers maintain databases monitoring and curating vulnerability reports. Application developers can identify vulnerable libraries by directly querying the databases with their used libraries. However, the querying results of vulnerable libraries are not reliable due to the incompleteness of vulnerability reports. Thus, current approaches model the task of identifying vulnerable libraries as a named-entity-recognition (NER) task or an extreme multi-label learning (XML) task. These approaches suffer from highly inaccurate results in identifying vulnerable libraries with complex and similar names, e.g., Java libraries. To address these limitations, in this paper, we propose VulLibMiner, the first to identify vulnerable libraries from textual descriptions of both vulnerabilities and libraries, together with VulLib, a Java vulnerability dataset with their affected libraries. VulLibMiner consists of a TF-IDF matcher to efficiently screen out a small set of candidate libraries and a BERT-FNN model to identify vulnerable libraries from these candidates effectively. We evaluate VulLibMiner using four state-of-the-art/practice approaches of identifying vulnerable libraries on both their dataset named VeraJava and our VulLib dataset. Our evaluation results show that VulLibMiner can effectively identify vulnerable libraries with an average F1 score of 0.657 while the state-of-the-art/practice approaches achieve only 0.521.

cs.CR↗

arXiv2023

Can Programming Languages Boost Each Other via Instruction Tuning?

When human programmers have mastered a programming language, it would be easier when they learn a new programming language. In this report, we focus on exploring whether programming languages can boost each other during the instruction fine-tuning phase of code large language models. We conduct extensive experiments of 8 popular programming languages (Python, JavaScript, TypeScript, C, C++, Java, Go, HTML) on StarCoder. Results demonstrate that programming languages can significantly improve each other. For example, CodeM-Python 15B trained on Python is able to increase Java by an absolute 17.95% pass@1 on HumanEval-X. More surprisingly, we found that CodeM-HTML 7B trained on the HTML corpus can improve Java by an absolute 15.24% pass@1. Our training data is released at https://github.com/NL2Code/CodeM.

cs.CL↗

arXiv2023

PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback

Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the code generation performance of pre-trained Code LLMs, such as supervised fine-tuning, instruction tuning, reinforcement learning, etc. In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark. Furthermore, through an extensive evaluation on CoderEval and LeetCode benchmarks, we show that PanGu-Coder2 consistently outperforms all previous Code LLMs.

cs.CL↗