arXiv subjects

Kisub Kim

Publications and source records attributed to Kisub Kim.

At least 19 recordsLinked to original sources

arXiv2026

A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents

Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs. Yet existing repository-level benchmarks typically evaluate only whether the final patch passes tests. Satisfying a user request requires a long chain of interdependent reasoning and decisions: an agent must recover explicit and implicit requirements, formulate a repository-grounded implementation plan, and translate it into correct code. A pass/fail outcome cannot characterize how an unsuccessful trajectory diverges from the requirements and implementation process needed for a correct patch. To address this gap, we introduce SWE-RPG, a repository-level benchmark that combines executable patch evaluation with validated ground-truth references (GTs) for (1) Requirement Clarification and (2) Implementation Planning. These intermediate GTs support retrospective, GT-aligned diagnosis of complete coding-agent trajectories across clarification, planning, code generation, and artifact submission. SWE-RPG comprises 163 tasks from 31 Python and Java repositories, including 113 bug fixes and 50 feature additions. We evaluate 3 coding agents, including Claude Code, Codex, and OpenCode, with 6 large language model backends, including Claude-Sonnet-5 and GPT-5.6-Terra. Results show that the evaluated popular coding agents still struggle to implement user requests in existing repositories, achieving an average resolved rate of only 31.5% on SWE-RPG. Intermediate-GT diagnosis further identifies implicit requirement recovery as the main bottleneck, accounting for 24.5%--46.0% of agent runs. This result suggests implicit-requirement recovery as a key candidate direction for improving coding agents. The benchmark data and evaluation code are available at https://github.com/Xin-Zhou-smu/SWE-RPG-Bench.

cs.SE↗

arXiv2025

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts

Code review is an essential process to ensure the quality of software that identifies potential software issues at an early stage of software development. Among all software issues, security issues are the most important to identify, as they can easily lead to severe software crashes and service disruptions. Recent research efforts have been devoted to automated approaches to reduce the manual efforts required in the secure code review process. Despite the progress, current automated approaches on secure code review, including static analysis, deep learning models, and prompting approaches, still face the challenges of limited precision and coverage, and a lack of comprehensive evaluation. To mitigate these challenges, we propose iCodeReviewer, which is an automated secure code review approach based on large language models (LLMs). iCodeReviewer leverages a novel mixture-of-prompts architecture that incorporates many prompt experts to improve the coverage of security issues. Each prompt expert is a dynamic prompt pipeline to check the existence of a specific security issue. iCodeReviewer also implements an effective routing algorithm to activate only necessary prompt experts based on the code features in the input program, reducing the false positives induced by LLM hallucination. Experiment results in our internal dataset demonstrate the effectiveness of iCodeReviewer in security issue identification and localization with an F1 of 63.98%. The review comments generated by iCodeReviewer also achieve a high acceptance rate up to 84% when it is deployed in production environments.

cs.SE↗

arXiv2025

Curiosity-Driven Testing for Sequential Decision-Making Process

Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent advances in Deep Learning (DL) have led to mature solutions for solving these complex problems, SDMs remain vulnerable to learning unsafe behaviors, posing significant risks in safety-critical applications. However, developing a testing framework for SDMs that can identify a diverse set of crash-triggering scenarios remains an open challenge. To address this, we propose CureFuzz, a novel curiosity-driven black-box fuzz testing approach for SDMs. CureFuzz proposes a curiosity mechanism that allows a fuzzer to effectively explore novel and diverse scenarios, leading to improved detection of crashtriggering scenarios. Additionally, we introduce a multi-objective seed selection technique to balance the exploration of novel scenarios and the generation of crash-triggering scenarios, thereby optimizing the fuzzing process. We evaluate CureFuzz on various SDMs and experimental results demonstrate that CureFuzz outperforms the state-of-the-art method by a substantial margin in the total number of faults and distinct types of crash-triggering scenarios. We also demonstrate that the crash-triggering scenarios found by CureFuzz can repair SDMs, highlighting CureFuzz as a valuable tool for testing SDMs and optimizing their performance.

cs.SE↗

arXiv2025

An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks

Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patches, and comments. However, accurately assessing the correctness of these generated artifacts remains a significant challenge. On one hand, human evaluation provides high accuracy but is labor-intensive and lacks scalability. On the other hand, many automatic evaluation metrics are scalable and require minimal human effort, but they often fail to accurately reflect the actual correctness of generated software artifacts. In this paper, we present SE-Jury, the first evaluation metric for LLM-as-Ensemble-Judge specifically designed to accurately assess the correctness of generated software artifacts. SE-Jury first defines five distinct evaluation strategies, each implemented by an independent judge. A dynamic team selection mechanism then identifies the most appropriate subset of judges as a team to produce a final correctness score through ensembling. We evaluate SE-Jury across a diverse set of software engineering (SE) benchmarks that span three popular SE tasks: code generation, automated program repair, and code summarization. Results demonstrate that SE-Jury consistently achieves a higher correlation with human judgments, with improvements ranging from 29.6% to 140.8% over existing automatic metrics. SE-Jury reaches agreement levels with human annotators that are close to inter-annotator agreement in code generation and program repair. These findings underscore SE-Jury's potential as a scalable and reliable alternative to human evaluation in these SE tasks.

cs.SE↗

arXiv2024

DetectBERT: Towards Full App-Level Representation Learning to Detect Android Malware

Recent advancements in ML and DL have significantly improved Android malware detection, yet many methodologies still rely on basic static analysis, bytecode, or function call graphs that often fail to capture complex malicious behaviors. DexBERT, a pre-trained BERT-like model tailored for Android representation learning, enriches class-level representations by analyzing Smali code extracted from APKs. However, its functionality is constrained by its inability to process multiple Smali classes simultaneously. This paper introduces DetectBERT, which integrates correlated Multiple Instance Learning (c-MIL) with DexBERT to handle the high dimensionality and variability of Android malware, enabling effective app-level detection. By treating class-level features as instances within MIL bags, DetectBERT aggregates these into a comprehensive app-level representation. Our evaluation demonstrates that DetectBERT not only surpasses existing state-of-the-art detection methods but also adapts to evolving malware threats. Moreover, the versatility of the DetectBERT framework holds promising potential for broader applications in app-level analysis and other software engineering tasks, offering new avenues for research and development.

cs.SE↗

arXiv2024

Representation Learning for Stack Overflow Posts: How Far are We?

The tremendous success of Stack Overflow has accumulated an extensive corpus of software engineering knowledge, thus motivating researchers to propose various solutions for analyzing its content.The performance of such solutions hinges significantly on the selection of representation model for Stack Overflow posts. As the volume of literature on Stack Overflow continues to burgeon, it highlights the need for a powerful Stack Overflow post representation model and drives researchers' interest in developing specialized representation models that can adeptly capture the intricacies of Stack Overflow posts. The state-of-the-art (SOTA) Stack Overflow post representation models are Post2Vec and BERTOverflow, which are built upon trendy neural networks such as convolutional neural network (CNN) and Transformer architecture (e.g., BERT). Despite their promising results, these representation methods have not been evaluated in the same experimental setting. To fill the research gap, we first empirically compare the performance of the representation models designed specifically for Stack Overflow posts (Post2Vec and BERTOverflow) in a wide range of related tasks, i.e., tag recommendation, relatedness prediction, and API recommendation. To find more suitable representation models for the posts, we further explore a diverse set of BERT-based models, including (1) general domain language models (RoBERTa and Longformer) and (2) language models built with software engineering-related textual artifacts (CodeBERT, GraphCodeBERT, and seBERT). However, it also illustrates the ``No Silver Bullet'' concept, as none of the models consistently wins against all the others. Inspired by the findings, we propose SOBERT, which employs a simple-yet-effective strategy to improve the best-performing model by continuing the pre-training phase with the textual artifact from Stack Overflow.

cs.SE↗

arXiv2024

PatchZero: Zero-Shot Automatic Patch Correctness Assessment

Automated Program Repair (APR) techniques have shown more and more promising results in fixing real-world bugs. Despite the effectiveness, APR techniques still face an overfitting problem: a generated patch can be incorrect although it passes all tests. It is time-consuming to manually evaluate the correctness of generated patches that can pass all tests. To address this problem, many approaches have been proposed to automatically assess the correctness of patches generated by APR techniques. These approaches are mainly evaluated within the cross-validation setting. However, for patches generated by a new or unseen APR tool, users are implicitly required to manually label a significant portion of these patches in the cross-validation setting before inferring the remaining patches. To mitigate the issue, in this study, we propose \toolname, the patch correctness assessment by adopting a large language model for code. Specifically, for patches generated by a new or unseen APR tool, \toolname does not need labeled patches of this new or unseen APR tool for training but directly queries the large language model for code to get predictions on the correctness labels without training. In this way, \toolname can reduce the manual labeling effort when building a model to automatically assess the correctness of generated patches of new APR tools. \toolname prioritizes labeled patches from existing APR tools that exhibit semantic similarity to those generated by new APR tools, enhancing the accuracy achieved by \toolname for patches from new APR tools. Our experimental results showed that \toolname can achieve an accuracy of 84.4% and an F1-score of 86.5% on average although no labeled patch of the new or unseen APR tool is available. In addition, our proposed technique outperformed the prior state-of-the-art by a large margin.

cs.SE↗

arXiv2024

Multi-LLM Collaboration + Data-Centric Innovation = 2x Better Vulnerability Repair

The advances of deep learning (DL) have paved the way for automatic software vulnerability repair approaches, which effectively learn the mapping from the vulnerable code to the fixed code. Nevertheless, existing DL-based vulnerability repair methods face notable limitations: 1) they struggle to handle lengthy vulnerable code, 2) they treat code as natural language texts, neglecting its inherent structure, and 3) they do not tap into the valuable expert knowledge present in the expert system. To address this, we propose VulMaster, a Transformer-based neural network model that excels at generating vulnerability repairs through data-centric innovation. Specifically, VulMaster introduces the utilization and combination of various types of input data, including complete vulnerable code of any size, vulnerable code structures, and expert knowledge from the CWE system. Additionally, VulMaster leverages the collaboration between two Large Language Models (LLMs), CodeT5 and ChatGPT: CodeT5 acts as the customizable backbone LLM, fine-tuned with the training data, while ChatGPT supplements by providing missing relevant inputs to CodeT5. We evaluated VulMaster on a real-world C/C++ vulnerability repair dataset comprising 1,754 projects with 5,800 vulnerable functions. The experimental results demonstrated that VulMaster exhibits substantial improvements compared to the learning-based state-of-the-art vulnerability repair approach. Specifically, VulMaster improves the EM, BLEU, and CodeBLEU scores from 10.2\% to 20.0\%, 21.3\% to 29.3\%, and 32.5\% to 40.9\%, respectively.

cs.SE↗

arXiv2024

CodeAgent: Autonomous Communicative Agents for Code Review

Code review, which aims at ensuring the overall quality and reliability of software, is a cornerstone of software development. Unfortunately, while crucial, Code review is a labor-intensive process that the research community is looking to automate. Existing automated methods rely on single input-output generative models and thus generally struggle to emulate the collaborative nature of code review. This work introduces \tool{}, a novel multi-agent Large Language Model (LLM) system for code review automation. CodeAgent incorporates a supervisory agent, QA-Checker, to ensure that all the agents' contributions address the initial review question. We evaluated CodeAgent on critical code review tasks: (1) detect inconsistencies between code changes and commit messages, (2) identify vulnerability introductions, (3) validate code style adherence, and (4) suggest code revision. The results demonstrate CodeAgent's effectiveness, contributing to a new state-of-the-art in code review automation. Our data and code are publicly available (\url{https://github.com/Code4Agent/codeagent}).

cs.SE↗

arXiv2023

Just-in-Time Detection of Silent Security Patches

Open-source code is pervasive. In this setting, embedded vulnerabilities are spreading to downstream software at an alarming rate. While such vulnerabilities are generally identified and addressed rapidly, inconsistent maintenance policies may lead security patches to go unnoticed. Indeed, security patches can be {\em silent}, i.e., they do not always come with comprehensive advisories such as CVEs. This lack of transparency leaves users oblivious to available security updates, providing ample opportunity for attackers to exploit unpatched vulnerabilities. Consequently, identifying silent security patches just in time when they are released is essential for preventing n-day attacks, and for ensuring robust and secure maintenance practices. With LLMDA we propose to (1) leverage large language models (LLMs) to augment patch information with generated code change explanations, (2) design a representation learning approach that explores code-text alignment methodologies for feature combination, (3) implement a label-wise training with labelled instructions for guiding the embedding based on security relevance, and (4) rely on a probabilistic batch contrastive learning mechanism for building a high-precision identifier of security patches. We evaluate LLMDA on the PatchDB and SPI-DB literature datasets and show that our approach substantially improves over the state-of-the-art, notably GraphSPD by 20% in terms of F-Measure on the SPI-DB benchmark.

cs.CR↗

arXiv2023

The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models

Learning-based techniques, especially advanced Large Language Models (LLMs) for code, have gained considerable popularity in various software engineering (SE) tasks. However, most existing works focus on designing better learning-based models and pay less attention to the properties of datasets. Learning-based models, including popular LLMs for code, heavily rely on data, and the data's properties (e.g., data distribution) could significantly affect their behavior. We conducted an exploratory study on the distribution of SE data and found that such data usually follows a skewed distribution (i.e., long-tailed distribution) where a small number of classes have an extensive collection of samples, while a large number of classes have very few samples. We investigate three distinct SE tasks and analyze the impacts of long-tailed distribution on the performance of LLMs for code. Our experimental results reveal that the long-tailed distribution has a substantial impact on the effectiveness of LLMs for code. Specifically, LLMs for code perform between 30.0\% and 254.0\% worse on data samples associated with infrequent labels compared to data samples of frequent labels. Our study provides a better understanding of the effects of long-tailed distributions on popular LLMs for code and insights for the future development of SE automation.

cs.SE↗

arXiv2023

DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode

The automation of a large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). Central to applying ML to software artifacts (like source or executable code) is converting them into forms suitable for learning. Traditionally, researchers have relied on manually selected features, based on expert knowledge which is sometimes imprecise and generally incomplete. Representation learning has allowed ML to automatically choose suitable representations and relevant features. Yet, for Android-related tasks, existing models like apk2vec focus on whole-app levels, or target specific tasks like smali2vec, which limits their applicability. Our work is part of a new line of research that investigates effective, task-agnostic, and fine-grained universal representations of bytecode to mitigate both of these two limitations. Such representations aim to capture information relevant to various low-level downstream tasks (e.g., at the class-level). We are inspired by the field of Natural Language Processing, where the problem of universal representation was addressed by building Universal Language Models, such as BERT, whose goal is to capture abstract semantic information about sentences, in a way that is reusable for a variety of tasks. We propose DexBERT, a BERT-like Language Model dedicated to representing chunks of DEX bytecode, the main binary format used in Android applications. We empirically assess whether DexBERT is able to model the DEX language and evaluate the suitability of our model in three distinct class-level software engineering tasks: Malicious Code Localization, Defect Prediction, and Component Type Classification. We also experiment with strategies to deal with the problem of catering to apps having vastly different sizes, and we demonstrate one example of using our technique to investigate what information is relevant to a given task.

cs.SE↗

arXiv2023

How are We Detecting Inconsistent Method Names? An Empirical Study from Code Review Perspective

Proper naming of methods can make program code easier to understand, and thus enhance software maintainability. Yet, developers may use inconsistent names due to poor communication or a lack of familiarity with conventions within the software development lifecycle. To address this issue, much research effort has been invested into building automatic tools that can check for method name inconsistency and recommend consistent names. However, existing datasets generally do not provide precise details about why a method name was deemed improper and required to be changed. Such information can give useful hints on how to improve the recommendation of adequate method names. Accordingly, we construct a sample method-naming benchmark, ReName4J, by matching name changes with code reviews. We then present an empirical study on how state-of-the-art techniques perform in detecting or recommending consistent and inconsistent method names based on ReName4J. The main purpose of the study is to reveal a different perspective based on reviewed names rather than proposing a complete benchmark. We find that the existing techniques underperform on our review-driven benchmark, both in inconsistent checking and the recommendation. We further identify potential biases in the evaluation of existing techniques, which future research should consider thoroughly.

cs.SE↗

arXiv2023

On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code

Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream tasks. However, the dynamic nature of software codebases poses a challenge to the effectiveness and robustness of PLMs. In particular, world-realistic scenarios potentially lead to significant differences between the distribution of the pre-training and test data, i.e., distribution shift, resulting in a degradation of the PLM's performance on downstream tasks. In this paper, we stress the need for adapting PLMs of code to software data whose distribution changes over time, a crucial problem that has been overlooked in previous works. The motivation of this work is to consider the PLM in a non-stationary environment, where fine-tuning data evolves over time according to a software evolution scenario. Specifically, we design a scenario where the model needs to learn from a stream of programs containing new, unseen APIs over time. We study two widely used PLM architectures, i.e., a GPT2 decoder and a RoBERTa encoder, on two downstream tasks, API call and API usage prediction. We demonstrate that the most commonly used fine-tuning technique from prior work is not robust enough to handle the dynamic nature of APIs, leading to the loss of previously acquired knowledge i.e., catastrophic forgetting. To address these issues, we implement five continual learning approaches, including replay-based and regularization-based methods. Our findings demonstrate that utilizing these straightforward methods effectively mitigates catastrophic forgetting in PLMs across both downstream tasks while achieving comparable or superior performance.

cs.SE↗

arXiv2023

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

Large language models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in a zero-shot manner, i.e., without the need for specific fine-tuning. While prior studies have highlighted the advantages of fine-tuning LLMs, this process incurs high computational costs, making it impractical in resource-scarce environments, particularly for models with billions of parameters. To address these challenges, previous research explored in-context learning (ICL) and retrieval-augmented generation (RAG) as strategies to guide the LLM generative process with task-specific prompt examples. However, ICL and RAG introduce inconveniences, such as the need for designing contextually relevant prompts and the absence of learning task-specific parameters, thereby limiting downstream task performance. In this context, we foresee parameter-efficient fine-tuning (PEFT) as a promising approach to efficiently specialize LLMs to task-specific data while maintaining reasonable resource consumption. In this paper, we deliver a comprehensive study of PEFT techniques for LLMs in the context of automated code generation. Our comprehensive investigation of PEFT techniques for LLMs reveals their superiority and potential over ICL and RAG across a diverse set of LLMs and three representative Python code generation datasets: Conala, CodeAlpacaPy, and APPS. Furthermore, our study highlights the potential for tuning larger LLMs and significant reductions in memory usage by combining PEFT with quantization. Therefore, this study opens opportunities for broader applications of PEFT in software engineering scenarios. Our code is available at https://github.com/martin-wey/peft-llm-code/.

cs.SE↗

arXiv2023

Are We Ready to Embrace Generative AI for Software Q&A?

Stack Overflow, the world's largest software Q&A (SQA) website, is facing a significant traffic drop due to the emergence of generative AI techniques. ChatGPT is banned by Stack Overflow after only 6 days from its release. The main reason provided by the official Stack Overflow is that the answers generated by ChatGPT are of low quality. To verify this, we conduct a comparative evaluation of human-written and ChatGPT-generated answers. Our methodology employs both automatic comparison and a manual study. Our results suggest that human-written and ChatGPT-generated answers are semantically similar, however, human-written answers outperform ChatGPT-generated ones consistently across multiple aspects, specifically by 10% on the overall score. We release the data, analysis scripts, and detailed results at https://anonymous.4open.science/r/GAI4SQA-FD5C.

cs.SE↗

arXiv2023

APISENS- Sentiment Scoring Tool for APIs with Crowd-Knowledge

Utilizing pre-existing software artifacts, such as libraries and Application Programming Interfaces (APIs), is crucial for software development efficiency. However, the abundance of artifacts that provide similar functionality can lead to confusion among developers, resulting in a challenge for proper selection and implementation. Through our preliminary investigation, we found that utilizing the collective knowledge of a crowd can greatly assist developers in acquiring a thorough and complete understanding of the complexities involved in the software development process. Especially as emotions are an inseparable part of human nature, it influences developers' activities. In this regard, we attempt to build a tool that can retrieve sentiment information for software APIs so that developers can determine APIs to utilize for their tasks. We employ the dataset from the most popular platforms (i.e., Twitter and YouTube) to build our research prototype. The source code, tool, and demo video are available on GitHub at \url{https://github.com/FalconLK/APISens}.

cs.SE↗

arXiv2023

APIHarvest: Harvesting API Information from Various Online Sources

Using APIs to develop software applications is the norm. APIs help developers to build applications faster as they do not need to reinvent the wheel. It is therefore important for developers to understand the APIs that they plan to use. Developers should also make themselves aware of relevant information updates about APIs. In order to do so, developers need to find and keep track of relevant information about the APIs that they are concerned with. Yet, the API information is scattered across various online sources, which makes it difficult to track by hand. Moreover, identifying content that is related to an API is not trivial. Motivated by these challenges, in this work, we introduce a tool named \tool that aims to ease the process of finding API information from various online sources. \tool is built on works that link APIs or libraries to various online sources. It supports finding API information on GitHub repositories, Stack Overflow's posts, tweets, YouTube videos, and common vulnerability and exposure (CVE) entries; and is extensible to support other sources.

cs.SE↗