arXiv subjects

Jiakun Liu

Publications and source records attributed to Jiakun Liu.

At least 19 recordsLinked to original sources

arXiv2026

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limited insight into hallucination during repair. In APR, hallucination may arise not only in final patches but also in the intermediate artifacts that guide patch generation. To address this gap, we perform a multi-layered analysis of hallucination throughout the APR process. Specifically, we characterize hallucination as the production of patches or intermediate artifacts that are not faithfully grounded in the available repair evidence. We examine repair hallucination in final patches and understanding hallucination in intermediate artifacts through three tasks, namely triggering testcase identification, line coverage prediction, and additional testcase generation.We then evaluate three representative LLMs on 832 Defects4J bugs through automatic evaluation and manual analysis. Our results show that both repair and understanding hallucinations remain prevalent. Across models and settings, only 21.0%-55.9% of generated patches pass the developer-written test suite. Moreover, although more accurate intermediate artifacts are generally associated with successful repairs, this relationship does not always hold. Manual analysis of 812 sampled repairs identifies repair hallucinations in 72.7% of cases, including patches that pass all available tests; incorrect causal localization and incorrect repair strategies account for 45.9% and 18.5% of these hallucinations, respectively. Meanwhile, models frequently misidentify triggering testcases, mispredict line coverage involving branching control flow, and generate additional testcases with missing bug-triggering conditions or incorrect expected behavior.

cs.SE↗

arXiv2026

Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation

LLM-based repository-level code generation aims to generate code using the context available in a software repository, requiring LLMs to reason over complex code dependencies. Due to limited context windows and insufficient repository-specific understanding, LLMs typically rely on retrieval-augmented generation (RAG) to incorporate relevant code. Early RAG approaches primarily employ similarity-based retrieval, which often fails to retrieve code snippets that the target function depends on. Recent work introduces graph-based retrieval to model such dependencies, but typically relies on manually designed rules and static global graphs, leading to limited flexibility and high construction and maintenance costs. In contrast, human developers collect helpful context by implicitly constructing a partial dependency graph and iteratively inspecting along it. Inspired by this behavior, we propose DyRetriever, an efficient context retrieval method via partial dependency graphs. DyRetriever uses an LLM to first select a set of entry-point functions and then perform multi-hop reasoning along the code dependency graph. During multi-hop reasoning, it uses the LLM's semantic understanding to validate whether a function can help generate the target function, eliminating manually designed rules and enabling flexibility across scenarios. Instead of statically constructing a global dependency graph, DyRetriever builds a partial graph on demand and discards it after use, reducing construction and maintenance costs. We integrate DyRetriever with a similarity-based code retriever to build DyCoder and evaluate it on CoderEval and DevEval. Experimental results show that DyCoder achieves relative Pass@1 improvements of 25.63% and 59.73% on CoderEval and DevEval, respectively, compared with existing RAG-based methods, while being 7.4x faster than baselines based on static dependency graph construction.

cs.SE↗

arXiv2026

Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection

Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real CVEs, we find that 71.7% of vulnerable functions require evidence from outside the function to be classified correctly. Agentic reinforcement learning (RL) could close this gap by enabling a model to gather that evidence itself, but it lacks a reliable reward, since a reward defined on the final verdict alone can be obtained without performing any investigation. We propose VulAgentRL, an agentic RL framework for interprocedural vulnerability detection built on a Code Property Graph (CPG). The CPG serves two roles: at inference time the policy queries it for callers, callees, dataflow, and other queries, and at training time the same graph verifies the evidence the policy cites. Because every CPG node carries a persistent integer identifier, this verification is an exact comparison rather than a textual match, so the reward credits verdicts that are supported by evidence. We further initialize the policy by distilling teacher investigations, and show that this warm start is necessary, since RL cannot acquire tool-use behavior it never samples. Under a repository-level split that prevents leakage, VulAgentRL outperforms state-of-the-art baselines, including frontier models, on the strict pair-wise-correct metric while issuing fewer tool calls, and its advantage persists on an out-of-distribution corpus and under class imbalance.

cs.CR↗

arXiv2026

Multi-level Code Optimization via Mixture of Prompts

Runtime efficiency is a critical factor that impacts both software quality and user satisfaction. There are many approaches proposed for code optimization to improve runtime efficiency. Traditional code optimization methods operate on intermediate representations (IRs) during compilation for static languages. They are effective but struggle to handle dynamic languages that do not require compilation. Recently, large language models (LLMs) have been leveraged to directly optimize source code in dynamic languages. However, these methods fail to identify suitable optimization targets and usually conduct incomprehensive single-level optimization. To address these challenges, we propose Optimo, a multi-level LLM-based code optimization approach built on a novel Mixture-of-Prompts (MoP) architecture. In the MoP architecture, Optimo identifies time-critical code structures as performance bottlenecks via differential profiling. These structures are then routed to some optimization strategies, akin to expert models in MoE, each tailored to optimize specific code patterns. Unlike traditional approaches that focus only on statement-level optimizations, Optimo operates at four levels of abstraction, ranging from coarse-grained algorithmic improvements to fine-grained optimizations in API usage. We evaluate Optimo on two code efficiency benchmarks, COFFE and Effibench. Our results demonstrate that Optimo achieves an up to 57.48% opt%, i.e., the percentage of optimized programs that are correct and at least 10% faster than the original programs, and an up to 3.97x speedup when optimizing human-written code, and it consistently outperforms the best baseline by up to 96.51% in terms of opt%. Furthermore, Optimo achieves an up to 42.42% opt% and an up to 13.51x speedup when optimizing LLM-generated code.

cs.SE↗

arXiv2026

ATGBuilder: Feature-Assisted Graph Learning for Activity Transition Graph Construction with Seed Supervision

Android applications are organized around activities that provide visual Graphical User Interface (GUI) containers that host the UI and handle user interaction events. Activity Transition Graphs (ATGs) have been widely used to model apps' GUI navigation. However, the construction of high-quality ATGs is challenging: ATGs based on static analysis may miss acceptable transitions and may extract infeasible ones; while dynamically explored ATGs can yield incomplete transitions. Recent learning-based approaches can treat ATG construction as a seed-supervised link-prediction task. However, the use of activity-layout and widget-trigger information for ATG construction remains limited. We propose ATGBuilder, a feature-assisted graph-learning approach for seed-supervised ATG construction. ATGBuilder uses a Large Language Model (LLM) to summarize UI activity metadata from layouts into compact textual functionality summaries. ATGBuilder explicitly models widget-trigger information into the edge attribute: It then uses an auxiliary widget-attribute reconstruction objective on this information during model training. ATGBuilder's performance was evaluated across a series of ablations on the frontmatter corpus, and an experiment on benchmark using manually-checked ground-truth ATGs. Experiments on multiple benchmarks show that ATGBuilder significantly outperforms state-of-the-art methods. We further demonstrate its effectiveness by improving automated GUI exploration tools through better navigation guidance.

cs.SE↗

arXiv2026

Beyond the Tip of the Iceberg: Understanding SATD in Dockerfiles through the Lens of Co-evolution

Dockerfiles enable the creation of portable container-based execution environments for the application code, and have become an important part of the modern software development process. As Dockerfiles are a form of Infrastructure-as-Code (IaC), they can include temporary workarounds and other suboptimal implementations, leading to the accrual of technical debt that affects their reliability, security, and maintainability in the future. Prior work characterized self-admitted technical debt (SATD) in Dockerfile comments and the surrounding file chunks. This single-file view is incomplete since source code evolution involves changes across different types of software artifacts such as production, test, build, and other configuration files. Thus, we address this gap by studying SATD events in Dockerfiles alongside the related source code. We find that approximately 27% of admission events and 40% of repayment events are coupled to non-Dockerfile artifacts, and coupling sources are subtype-specific. We also observed that coupled SATD in general are repaid significantly faster overall (p = 0.0201), while coupled SATD regarding missing functionalities persists longer than its isolated counterparts; Lastly, we conducted open and axial coding of coupled SATD events, and we observe that external dependency issues, more particularly regarding unreleased upstream packages and bug fixes, are the most common cause of admission triggers in the source code; we also observe that architectural refactoring is the most common prerequisite for the repayment of SATD in Dockerfiles. These findings indicate that both practitioners (e.g. developers and project managers) and SATD researchers should integrate the source code-side co-evolution, rather than the single-file view, as the primary unit of analysis.

cs.SE↗

arXiv2026

MuMuTestUp: Mutation-based Multi-Agent Test Case Update

Modern software systems evolve rapidly under CI/CD practices, where tests are critical for quality. However, substantial code changes often render existing test cases obsolete, causing pipeline disruptions, reduced productivity, and compromised quality. Recent automatic test update approaches leverage LLMs to refine test cases via execution feedback and exact-matching context retrieval, prioritizing executability and line coverage but suffering three limitations: (1) neglecting test assertion adequacy, weakening fault detection; (2) relying on coarse line coverage instead of specific uncovered lines/branches; (3) using exact-matching retrieval, which fails for LLM hallucinated queries. To address these, we propose MuMuTestUp, a mutation-guided multi-agent framework with three specialized agents: Mutation Analysis (strengthens assertions via surviving mutants), Coverage Analysis (generates targeted repair instructions for uncovered lines/branches), and Semantic Retrieval (handles hallucinations via semantic-similarity search). We also construct PRBENCH, a 571-sample pull-request-level dataset from 10 open-source Java projects (validated for cross-commit update scenarios). Evaluations against state-of-the-art baselines use both open-source (Deepseek-V3.2) and closed-source (GPT-4.1) LLMs.

cs.SE↗

arXiv2026

Bayesian Sphere-on-Sphere Regression with Optimal Transport Maps

Spherical regression, in which both covariates and responses lie on the sphere, arises in many scientific applications and has attracted considerable methodological attention in recent years. Despite this progress, constructing flexible and expressive regression models between spherical domains remains challenging, particularly because a single global mapping is often insufficient to capture complex relationships across the entire sphere. A natural strategy is therefore to partition the spherical domain and allow distinct mappings within each region, though this introduces the additional challenge of modeling the partition structure itself. To address these issues, we propose an approach based on optimal transport to model spherical partitions, combined with parametric mappings defined locally within each region. We adopt a Bayesian framework to jointly model both the partitioning and the associated regression maps. This framework enables the identification of heterogeneous regions on the sphere while providing principled uncertainty quantification. Through real-data applications, we demonstrate that the proposed method achieves strong predictive performance, yields meaningful uncertainty estimates, and reveals interpretable clustering structure in spherical data.

stat.ME↗

arXiv2026

Optimal (partial) transport to non-convex polygonal domains

In this paper, we investigate optimal (partial) transport problems for which the target is a non-convex polygonal domain in \(\mathbb{R}^2\). For the complete optimal transport problem, we prove that the singular set is locally a smooth one-dimensional curve away from finitely many points. For the optimal partial transport problem, we prove that the free boundary is smooth away from finitely many singular points. In higher dimensions, we formulate two conjectures concerning the structure of singularities when the target is a non-convex polytope.

math.AP↗

arXiv2026

Text Tells the Cost: Predicting and Analyzing Repayment Effort of Self-Admitted Technical Debt

Technical debt refers to the consequences of sub-optimal decisions made during software development that prioritize short-term benefits over long-term maintainability. Self-Admitted Technical Debt (SATD) is a specific form of technical debt, explicitly documented by developers within software artifacts such as source code comments and commit messages. As SATD can hinder software development and maintenance, it is crucial to estimate the effort required to repay it so that we can effectively prioritize it. However, we currently lack an understanding of SATD repayment, and more importantly, we lack approaches that can automatically estimate the repayment effort of SATD based on its textual description. To bridge this gap, we have curated a comprehensive dataset of 341,740 SATD items from 2,568,728 commits across 1,060 Apache repositories and analyzed the repayment effort comparing SATD vs. non-SATD items, as well as different types of SATD items. Furthermore, we proposed an innovative approach for Predicting Repayment Effort of SATD using Textual Information, named PRESTI. Our findings show that different types of SATD require varying levels of repayment effort, with code/design, requirement, and test debt demanding greater effort compared to non-SATD items, while documentation debt requires less. We have evaluated our approaches, particularly BERT- and TextCNN-based models, which outperform traditional machine learning methods and the baseline in estimating repayment effort. Additionally, we summarize keywords associated with varying levels of repayment effort that occur during SATD repayment. Our work aims to enhance SATD repayment prioritization and resource allocation, thereby improving software development and maintainability.

cs.SE↗

arXiv2026

UniCoR: Modality Collaboration for Robust Cross-Language Hybrid Code Retrieval

Effective code retrieval is indispensable and it has become an important paradigm to search code in hybrid mode using both natural language and code snippets. Nevertheless, it remains unclear whether existing approaches can effectively leverage such hybrid queries, particularly in cross-language contexts. We conduct a comprehensive empirical study of representative code models and reveal three challenges: (1)insufficient semantic understanding; (2) inefficient fusion in hybrid code retrieval; and (3) weak generalization in cross-language scenarios. To address these challenges, we propose UniCoR, a novel self-supervised framework designed to learn Unified Code Representations that are semantically robust, modally collaborative, and language-agnostic. Firstly, we design a multi-perspective supervised contrastive learning module to enhance semantic understanding and modality fusion. It aligns representations from multiple perspectives, including code-to-code, natural language-to-code, and natural language-to-natural language, enforcing the model to capture a semantic essence among modalities. Secondly, we introduce a representation distribution consistency learning module to improve cross-language generalization, which explicitly aligns the feature distributions of different programming languages, enabling language-agnostic representation learning. Extensive experiments on both an empirical benchmark and a large-scale benchmark show that UniCoR outperforms all baseline models, achieving an average improvement of 8.64% in MRR and 11.54% in MAP over the best-performing baseline. Furthermore, UniCoR exhibits stability in hybrid code retrieval and generalization capability in cross-language scenarios.

cs.SE↗

arXiv2026

CovAgent: Overcoming the 30% Curse of Mobile Application Coverage with Agentic AI and Dynamic Instrumentation

Automated GUI testing is crucial for ensuring the quality and reliability of Android apps. However, the efficacy of existing UI testing techniques is often limited, especially in terms of coverage. Recent studies, including the state-of-the-art, struggle to achieve more than 30% activity coverage in real-world apps. This limited coverage can be attributed to a combination of factors such as failing to generate complex user inputs, unsatisfied activation conditions regarding device configurations and external resources, and hard-to-reach code paths that are not easily accessible through the GUI. To overcome these limitations, we propose CovAgent, a novel agentic AI-powered approach to enhance Android app UI testing. Our fuzzer-agnostic framework comprises an AI agent that inspects the app's decompiled Smali code and component transition graph, and reasons about unsatisfied activation conditions within the app code logic that prevent access to the activities that are unreachable by standard and widely adopted GUI fuzzers. Then, another agent generates dynamic instrumentation scripts that satisfy activation conditions required for successful transitions to those activities. We found that augmenting existing fuzzing approaches with our framework achieves a significant improvement in test coverage over the state-of-the-art, LLMDroid, and other baselines such as Fastbot and APE (e.g., 101.1%, 116.3% and 179.7% higher activity coverage, respectively). CovAgent also outperforms all the baselines in other metrics such as class, method, and line coverage. We also conduct investigations into components within CovAgent to reveal further insights regarding the efficacy of Agentic AI in the field of automated app testing such as the agentic activation condition inference accuracy, and agentic activity-launching success rate.

cs.SE↗

arXiv2025

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models (LLMs) and LLM-based agents have demonstrated remarkable capabilities in various software engineering (SE) tasks, enabling them to effectively address software security challenges such as vulnerability detection. However, systematic evaluation of the capabilities of LLMs and LLM-based agents in security patch detection remains limited. To bridge this gap, we conduct a comprehensive evaluation of the performance of LLMs and LLM-based agents for security patch detection. Specifically, we investigate three methods: Plain LLM (a single LLM with a system prompt), Data-Aug LLM (data augmentation based on the Plain LLM), and the ReAct Agent (leveraging the thought-action-observation mechanism). We also evaluate the performance of both commercial and open-source LLMs under these methods and compare these results with those of existing baselines. Furthermore, we analyze the detection performance of these methods across various vulnerability types, and examine the impact of different prompting strategies and context window sizes on the results. Our findings reveal that the Data-Aug LLM achieves the best overall performance, whereas the ReAct Agent demonstrates the lowest false positive rate (FPR). Although baseline methods exhibit strong accuracy, their false positive rates are significantly higher. In contrast, our evaluated methods achieve comparable accuracy while substantially reducing the FPR. These findings provide valuable insights into the practical applications of LLMs and LLM-based agents in security patch detection, highlighting their advantage in maintaining robust performance while minimizing false positive rates.

cs.CR↗

arXiv2025

Bamboo: LLM-Driven Discovery of API-Permission Mappings in the Android Framework

The permission mechanism in the Android Framework is integral to safeguarding the privacy of users by managing users' and processes' access to sensitive resources and operations. As such, developers need to be equipped with an in-depth understanding of API permissions to build robust Android apps. Unfortunately, the official API documentation by Android chronically suffers from imprecision and incompleteness, causing developers to spend significant effort to accurately discern necessary permissions. This potentially leads to incorrect permission declarations in Android app development, potentially resulting in security violations and app failures. Recent efforts in improving permission specification primarily leverage static and dynamic code analyses to uncover API-permission mappings within the Android framework. Yet, these methodologies encounter substantial shortcomings, including poor adaptability to Android SDK and Framework updates, restricted code coverage, and a propensity to overlook essential API-permission mappings in intricate codebases. This paper introduces a pioneering approach utilizing large language models (LLMs) for a systematic examination of API-permission mappings. In addition to employing LLMs, we integrate a dual-role prompting strategy and an API-driven code generation approach into our mapping discovery pipeline, resulting in the development of the corresponding tool, \tool{}. We formulate three research questions to evaluate the efficacy of \tool{} against state-of-the-art baselines, assess the completeness of official SDK documentation, and analyze the evolution of permission-required APIs across different SDK releases. Our experimental results reveal that \tool{} identifies 2,234, 3,552, and 4,576 API-permission mappings in Android versions 6, 7, and 10 respectively, substantially outprforming existing baselines.

cs.SE↗

arXiv2025

RDD Function: A Tradeoff Between Rate and Distortion-in-Distortion

In this paper, we propose a novel function named Rate Distortion-in-Distortion (RDD) function as an extension of the classical rate-distortion (RD) function, where the expected distortion constraint is replaced by a Gromov-type distortion. This distortion, integral to the Gromov-Wasserstein (GW) distance, effectively defines the similarity in spaces of possibly different dimensions even without a direct metric between them. While the RDD function qualifies as an informational RD function, encoding theorems substantiate its status as an operational RD function, thereby underscoring its potential applicability in real-world source coding. Due to the high computational complexity associated with Gromov-type distortion, in general, the RDD function cannot be evaluated analytically. Consequently, we develop an alternating mirror descent algorithm that significantly reduces computational complexity by employing decomposition, linearization, and relaxation techniques. Numerical results on classical sources and different grids demonstrate the effectiveness of the developed algorithm. By exploring the relationship between the RDD function and the RD function, we suggest that the RDD function may have potential applications in future scenarios.

cs.IT↗

arXiv2025

Regularity of singular set in optimal transportation

In this paper, we establish a regularity theory for the optimal transport problem when the target is composed of two disjoint convex domains. This is an important model in which singularities arise. Even though the singular set does not exhibit any form of convexity a priori, we prove its higher order regularity by developing novel methods, which also have many other applications. Notably, our results are achieved without requiring any convexity of the source domain. This aligns with Caffarelli's celebrated regularity theory.

math.AP↗

arXiv2025

LLM4SZZ: Enhancing SZZ Algorithm with Context-Enhanced Assessment on Large Language Models

The SZZ algorithm is the dominant technique for identifying bug-inducing commits and serves as a foundation for many software engineering studies, such as bug prediction and static code analysis. Researchers have proposed many variants to enhance the SZZ algorithm's performance since its introduction. The majority of them rely on static techniques or heuristic assumptions, making them easy to implement, but their performance improvements are often limited. Recently, a deep learning-based SZZ algorithm has been introduced to enhance the original SZZ algorithm. However, it requires complex preprocessing and is restricted to a single programming language. Additionally, while it enhances precision, it sacrifices recall. Furthermore, most of variants overlook crucial information, such as commit messages and patch context, and are limited to bug-fixing commits involving deleted lines. The emergence of large language models (LLMs) offers an opportunity to address these drawbacks. In this study, we investigate the strengths and limitations of LLMs and propose LLM4SZZ, which employs two approaches (i.e., rank-based identification and context-enhanced identification) to handle different types of bug-fixing commits. We determine which approach to adopt based on the LLM's ability to comprehend the bug and identify whether the bug is present in a commit. The context-enhanced identification provides the LLM with more context and requires it to find the bug-inducing commit among a set of candidate commits. In rank-based identification, we ask the LLM to select buggy statements from the bug-fixing commit and rank them based on their relevance to the root cause. Experimental results show that LLM4SZZ outperforms all baselines across three datasets, improving F1-score by 6.9% to 16.0% without significantly sacrificing recall.

cs.SE↗

arXiv2025

RustMap: Towards Project-Scale C-to-Rust Migration via Program Analysis and LLM

Migrating existing C programs into Rust is increasingly desired, as Rust offers superior memory safety while maintaining C's high performance. However, vastly different features between C and Rust--e.g., distinct definitions and usages of pointers and references--pose significant challenges beyond mere syntactic translation. Existing automated translation tools, such as C2Rust, may rely too much on syntactic, template-based translation and generate unsafe Rust code that is hard for human developers to read, maintain, or even compile. More semantic-aware translation that produces safer, idiomatic, and runnable Rust code is much needed. This paper introduces a novel dependency-guided and large language model (LLM)-based C-to-Rust translation approach, RustMap, based on three key ideas: (1) Utilize LLM capabilities to produce idiomatic Rust code from given small pieces of C code, (2) Mitigate LLM limitations in handling large codebases by breaking project-scale C programs into smaller units for translation according to their usage dependencies and composing them into a runnable Rust program, and (3) Enhance the correctness of the translated Rust program by using test cases to check input/output equivalence, isolate faulty code when execution states deviate, and iteratively refine the translation using feedback from compilation and test errors. We empirically evaluate RustMap on 126 real-world programs, including 125 from Rosetta Code and a 7000+ line bzip2 implementation using GPT-4o as the LLM. RustMap shows promising results, guiding GPT-4o to produce idiomatic, readable, and functional Rust code with significantly less unsafe code than other tools, and revealing non-trivial translation patterns reusable for future research.

cs.SE↗