BWBo Wang

Bo Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bo Wang has a total of 108 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    A Comprehensive Study on Large Language Models for Mutation Testing

    by Bo Wang, Mingda Chen, Ming Deng, Youfang Lin, Mark Harman, Mike Papadakis, Jie M. Zhang

    Large Language Models (LLMs) have recently been used to generate mutants both in the research community and in industrial practice. However, there has been no comprehensive empirical study of their performance for this increasingly important LLM-based Software Engineering application. To address this, we conduct a comprehensive empirical study evaluating both a wide range of traditional approaches and LLM-based approaches. Particularly, we evaluate BugFarm, LLMorpheus, and our newly designed prompt for mutant generation. The experiments cover both leading open and closed source LLMs, on 851 real bugs from 2 Java real-world bug benchmarks. Our results reveal that, compared to existing traditional approaches, LLMs generate more diverse mutants that are behaviorally closer to real bugs and, most importantly, achieve a 1.8 \(\times\) improvement in real bug detection, defined as the proportion of real bugs whose faulty behaviors can be mimicked by at least one generated mutant. Specifically, LLM-based approaches reach a detection rate of 77.4%, compared to 41.6% for rule-based techniques, representing an absolute gain of 35.8 percentage points. Nevertheless, our results also reveal that these impressive improvements in effectiveness come at a cost: LLM-generated mutants exhibit worse non-compilability, duplication, and equivalent mutant rates than rule-based approaches by 25.9, 7.1, and 2.6 percentage points, respectively. These findings provide actionable insights for both research and practice. They allow practitioners to have greater confidence in deploying LLM-based mutation, while researchers now have a baseline for the state-of-the-art, with which they can research techniques to further improve effectiveness and reduce cost.


  • Open Access

    Verifier-in-the-Loop LLM Solving of Heap Constraints for Concolic Execution

    by Shaoran Xia, Leyi Cheng, Caihua Dong, Dongdong She, Bo Wang, Xin Peng, Zhen Dong

    Concolic execution systematically explores program paths by solving symbolic constraints, but in object-oriented software its practical effectiveness is often limited by heap constraints over objects and heap structure, such as nullness, aliasing, runtime types, and field reachability. These constraints form a systematic bottleneck in real-world software because satisfying them requires constructing a concrete heap model rather than merely computing primitive valuations, which existing SMT-based concolic engines and symbolic heap techniques do not handle effectively. We present COHEC, a hybrid concolic architecture that decomposes each target path condition into a primitive component solved by an SMT solver and a heap component handled by a Heap Constraint Solver (HCS). Given extracted heap constraints, HCS uses an LLM to propose candidate heap models and initialization code, while a trusted verifier executes and verifies the generated code, admitting only models whose initialization code constructs states that satisfy all constraints and keeping the LLM outside the trusted computing base. We implement COHEC on top of JDart/JPF and evaluate it on 6,750 APIs from ten Java libraries, together with a stratified sample from commons-lang3 against the LLM-assisted baseline CONCOLLMIC. The results show that COHEC substantially improves path exploration and concrete valuation generation over native JDart, while achieving higher coverage than CONCOLLMIC at lower time and token cost. Overall, the findings indicate that treating heap constraint solving as verified heap model construction is a practical and effective way to extend concolic execution to the object-sensitive behaviors pervasive in modern software.

  • Open Access

    Hidden Licensing Risks in the PTMware Ecosystem

    by Bo Wang, Yueyang Chen, Jieke Shi, Minghui Li, Yunbo Lyu, Yinan Wu, Youfang Lin, Zhou Yang

    Pre-trained Models (PTMs) have been increasingly integrated into software systems, giving rise to a new class of software referred to as PTMware. In addition to traditional software components composed solely of source code, PTMware also embeds or interacts with PTMs that depend on other models and datasets, forming complex supply chains involving open-source software (OSS) libraries, PTMs, and datasets. However, the licensing issues arising from these intertwined dependencies remain largely unexplored. Leveraging GitHub and Hugging Face, two premier hubs for code and models, we curate a large-scale dataset capturing the supply chains of PTMware. Our dataset comprises 12,180 OSS repositories from GitHub, 3,988 PTMs, and 708 datasets from Hugging Face. We analyze license distributions in the PTMware ecosystem and find that licensing practices differ markedly from those in traditional OSS communities. We further examine license-related issues and identify license selection and maintenance as the primary pain points, with 84% of cases involving discussions about adding appropriate licenses or resolving conflicts in existing ones. We then study license incompatibility in PTMware and evaluate the state-of-the-art approaches, finding that they perform poorly in this setting and achieve only 58% and 76% F1 scores, respectively. These results motivate us to propose LiAgent, which explores the potential of LLM-based agents for ecosystem-level license compatibility analysis, achieves an F1 score of 87%, and improves performance by 14 percentage points over prior approaches. We submit 60 license incompatibility issues detected by LiAgent, of which developers have confirmed 11. Two PTMs with license conflicts have more than 107 million and 5 million downloads on Hugging Face, respectively, suggesting that the issues may affect many downstream applications. We conclude by discussing implications and providing recommendations to support the healthy growth of the PTMware ecosystem.

  • Open Access

    From Greedy Steps to Global Optimization: Learning Sequential Test Suite Generation

    by Guoqing Wang, Chengran Yang, Xiaoxuan Zhou, Zeyu Sun, Bo Wang, David Lo, Dan Hao

    With the rapid evolution of Large Language Models (LLMs), automated software testing is witnessing a paradigm shift. While proprietary models like GPT-4o demonstrate impressive capabilities, their high deployment costs and data privacy concerns make open-source LLMs the practical imperative for many academic and industrial scenarios. In the field of automated test generation, it has evolved to iterative workflows to construct test suites based on LLMs. When utilizing open-source LLMs, we empirically observe they lack a suite-level perspective, suffering from structural myopia—failing to generate new tests with large marginal gain based on the current covered status. In this paper, from the perspective of sequences, we formalize test suite generation as a Markov Decision Process (MDP) and demonstrate that its objective exhibits monotone submodularity, which enables an effective relaxation of this NP-hard global optimization into a tractable step-wise greedy procedure. Guided by this insight, we propose TestDecision, which transforms LLMs into neural greedy experts. TestDecision consists of two synergistic components: (1) an inference framework which implements test suite construction following a step-wise greedy strategy; and (2) a training pipeline of reinforcement learning which equips the base LLM with sequential test generation ability to maximize marginal gain. Comprehensive evaluations on the ULT benchmark demonstrate that TestDecision significantly outperforms existing advanced methods. It brings an improvement between 38.15-52.37% in branch coverage and 298.22-558.88% in execution pass rate over all base models, achieving a comparable performance on 7B backbone with a much larger proprietary LLM GPT-5.2. Furthermore, TestDecision can find 58.43-95.45% more bugs than vanilla base LLMs and exhibit superior generalization on LiveCodeBench, proving its capability to construct high-quality test suites.

  • Open Access

    Boosting LLMs for Mutation Generation

    by Bo Wang, Ming Deng, Mingda Chen, Chengran Yang, Youfang Lin, Mark Harman, Mike Papadakis, Jie M. Zhang

    LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutants as few-shot examples or none at all. This can result in generic low-quality mutants, missed context-specific mutation patterns, substantial numbers of redundant and non-compilable mutants, and limited semantic similarity to real bugs. To overcome these limitations, we introduce SMART (Semantic Mutation with Adaptive Retrieval and Tuning). SMART integrates retrieval-augmented generation (RAG) on a vectorized dataset of real-world bugs, focused code chunking, and supervised fine-tuning using mutants coupled with real-world bugs. We conducted an extensive empirical study of SMART using 1,991 real-world Java bugs from the Defects4J and ConDefects datasets, comparing SMART to the state-of-the-art LLM-based approaches, LLMut and LLMorpheus. The results reveal that SMART substantially improves mutation validity, effectiveness, and efficiency (even enabling 7B-scale models to match or even surpass large models like GPT-4o). We also demonstrate that SMART significantly improves downstream software engineering applications, including test case prioritization and fault localization. More specifically, SMART improves validity (weighted average generation rate) from 42.89% to 65.6%. It raises the non-duplicate rate from 87.38% to 95.62%, and the compilable rate from 88.85% to 90.21%. In terms of effectiveness, it achieves a real bug detection rate of 92.61% (vs. 57.86% for LLMut) and improves the average Ochiai coefficient from 25.61% to 38.44%. For fault localization, SMART ranks 64 more bugs as Top-1 under MUSE and 57 more under Metallaxis.


  • Open Access

    Hidden Licensing Risks in the LLMware Ecosystem

    by Bo Wang, Yueyang Chen, Jieke Shi, Minghui Li, Yunbo Lyu, Yinan Wu, Youfang Lin, Zhou Yang

    Large Language Models (LLMs) are increasingly integrated into software systems, giving rise to a new class of systems referred to as LLMware. Beyond traditional source-code components, LLMware embeds or interacts with LLMs that depend on other models and datasets, forming complex supply chains across open-source software (OSS), models, and datasets. However, licensing issues emerging from these intertwined dependencies remain largely unexplored. Leveraging GitHub and Hugging Face, we curate a large-scale dataset capturing LLMware supply chains, including 12,180 OSS repositories, 3,988 LLMs, and 708 datasets. Our analysis reveals that license distributions in LLMware differ substantially from traditional OSS ecosystems. We further examine license-related discussions and find that license selection and maintenance are the dominant concerns, accounting for 84% of cases. To understand incompatibility risks, we analyze license conflicts along supply chains and evaluate state-of-the-art detection approaches, which achieve only 58% and 76% F1 scores in this setting. Motivated by these limitations, we propose LiAgent, an LLM-based agent framework for ecosystem-level license compatibility analysis. LiAgent achieves an F1 score of 87%, improving performance by 14 percentage points over prior methods. We reported 60 incompatibility issues detected by LiAgent, 11 of which have been confirmed by developers. Notably, two conflicted LLMs have over 107 million and 5 million downloads on Hugging Face, respectively, indicating potentially widespread downstream impact. We conclude with implications and recommendations to support the sustainable growth of the LLMware ecosystem.

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

    by Xuemeng Cai, Jiakun Liu, Xiping Huang, Yijun Yu, Haitao Wu, Chunmiao Li, Bo Wang, Imam Nur Bani Yusuf, Lingxiao Jiang


  • Open Access

    Fuzzing C++ Compilers via Type-Driven Mutation

    by Bo Wang, Chong Chen, Ming Deng, Junjie Chen, Xing Zhang, Youfang Lin, Dan Hao, Jun Sun

    C++ is a system-level programming language for modern software development, which supports multiple programming paradigms, including object-oriented, generic, and functional programming. The intrinsic complexity of these paradigms and their interactions grants C++ powerful expressiveness while posing significant challenges for compilers in correctly implementing its type system. A type system encompasses various aspects such as type inference, type checking, subtyping, type conversions, generics, scoping, and binding. However, systematic testing of the type systems of C++ compilers remains largely underexplored in existing studies. In this work, we present TyMut, the first approach specifically designed to test the C++ type system. TyMut is a mutation-based compiler fuzzer equipped with advanced type-driven mutation operators, carefully crafted to target intricate type-related features such as template generics, type conversions, and inheritance. Beyond differential testing, TyMut introduces enhanced test oracles through a must analysis that partially confirms the validity of generated programs. Specifically, mutation operators are classified into well-formed and not-well-formed: Programs generated by well-formed mutation operators are valid and must be accepted by compilers. Programs generated by not-well-formed operators are validated against a set of well-formedness rules. Any violation indicates the program is invalid and must be rejected. For programs that pass the rules but lack a definitive oracle, TyMut applies differential testing to identify behavioral inconsistencies across compilers. The testing campaign took about 32 hours to generate and test 250584 programs. The must analysis provides definite test oracles for nearly 80% of all generated programs. TyMut uncovered 102 bugs in the recent versions of GCC and Clang, with 56 confirmed as new bugs by compiler developers. Among the confirmed bugs, 26 of them cause compiler crashes, and more than 50% cause miscompilation. Additionally, 7 of them had remained hidden for over 20 years, 22 for over 10 years, and 39 for over 5 years. One long-standing bug discovered by TyMut was later confirmed as the root cause of a real-world issue in TensorFlow. Before submitting this paper, 13 bugs were fixed, most of which were fixed within 60 days. Notably, some unconfirmed bugs have led to in-depth discussions among developers. For instance, one bug led a compiler developer to submit a new issue to the C++ language standard, showing that we uncovered ambiguities in the language specification.