Gang Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gang Huang has a total of 212 co-authors. Here are the top co-authors by number of shared publications:
- Xuanzhe Liu
Peking University
28 shared publications - Yun Ma
Peking University
14 shared publications - Mengwei Xu
Beijing University of Posts and Telecommunications
12 shared publications - Daliang Xu
Beijing University of Posts and Telecommunications, Beijing, China
9 shared publications - Tong Jia
Peking University, Beijing, China
7 shared publications - Xin Jin
School of Computer Science, Peking University, Beijing, China
7 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4028-4037
HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4028-4037
Open AccessHalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (11) , 3496-3511
IEEF: Enhancing Commit Message Generation by Segmenting Key Information in High-Quality Data
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (11) , 3496-3511
IEEF: Enhancing Commit Message Generation by Segmenting Key Information in High-Quality Data
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6946-6957
StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6946-6957
Open AccessStepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems
- Open Access
- 26 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Can Large Language Models Reason About Complex Execution Paths? An Empirical Study on Python
Execution path reasoning is a key step towards program semantics understanding. It is crucial for generating test cases that cover certain branches/paths, or detecting bugs that are triggered by some paths without actually executing the program. Traditionally, execution path reasoning can be achieved by symbolic execution techniques, but existing SMT-based symbolic execution approaches struggle with complex data structures and external API calls. This challenge is even more pronounced in languages with highly flexible syntax, such as Python, resulting in a lack of widely adopted tools for reasoning on execution paths. Therefore, reasoning execution paths with AI-based approaches become a promising direction. In this paper, we investigate the feasibility of adopting large language models (LLMs) for execution path reasoning on Python, where traditional path-based symbolic execution tools are unavailable. We conduct an empirical study on two types of path reasoning tasks: generation tasks for test case generation and classification tasks for bug detection. We build new evaluation pipelines and benchmarks from both competition-level programs and real-world repositories. Our results show that state-of-theart LLMs can perform correct reasoning on execution paths and improve test coverage on real-world software, though models with stronger reasoning abilities do not always outperform weaker ones. These findings highlight the potential of utilizing LLMs as a complementary heuristic for path-aware code reasoning, especially in program languages lacking mature symbolic execution tools. We have released our benchmark and evaluation scripts at https://github.com/jacobwwh/llm-path-study .
- 26 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessCan Large Language Models Reason About Complex Execution Paths? An Empirical Study on Python
Execution path reasoning is a key step towards program semantics understanding. It is crucial for generating test cases that cover certain branches/paths, or detecting bugs that are triggered by some paths without actually executing the program. Traditionally, execution path reasoning can be achieved by symbolic execution techniques, but existing SMT-based symbolic execution approaches struggle with complex data structures and external API calls. This challenge is even more pronounced in languages with highly flexible syntax, such as Python, resulting in a lack of widely adopted tools for reasoning on execution paths. Therefore, reasoning execution paths with AI-based approaches become a promising direction. In this paper, we investigate the feasibility of adopting large language models (LLMs) for execution path reasoning on Python, where traditional path-based symbolic execution tools are unavailable. We conduct an empirical study on two types of path reasoning tasks: generation tasks for test case generation and classification tasks for bug detection. We build new evaluation pipelines and benchmarks from both competition-level programs and real-world repositories. Our results show that state-of-theart LLMs can perform correct reasoning on execution paths and improve test coverage on real-world software, though models with stronger reasoning abilities do not always outperform weaker ones. These findings highlight the potential of utilizing LLMs as a complementary heuristic for path-aware code reasoning, especially in program languages lacking mature symbolic execution tools. We have released our benchmark and evaluation scripts at https://github.com/jacobwwh/llm-path-study .
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 294-308
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 294-308
Open AccessShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 854-867
VLMCache: Efficient On-Device Vision-Language Model Inference
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 854-867
Open AccessVLMCache: Efficient On-Device Vision-Language Model Inference
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1780-1796
Serverless Replication of Object Storage across Multi-Vendor Clouds and Regions
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1780-1796
Open AccessServerless Replication of Object Storage across Multi-Vendor Clouds and Regions
- Open Access
- 11 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (4) , 1-33
Automatically Deriving Developers’ Technical Expertise from the GitHub Social Network
Developers’ technical expertise is crucial for numerous tasks within open-source communities, such as identifying suitable developers and maintainers. Despite its significance, GitHub, the world’s largest open-source code hosting platform, does not explicitly display developers’ technical expertise. Existing methods fall short in capturing the multi-faceted and dynamic nature of developers’ skills and knowledge. To address this gap, we propose a novel approach that leverages graph neural networks (GNNs) to express developers’ technical expertise. Our method constructs a comprehensive GitHub social network that integrates various social and development activities. We then employ a GNN model to learn a low-dimensional representation vector for each developer, encapsulating their technical expertise across different dimensions. We assess the effectiveness of our model by comparing it against five baselines on three GitHub social relationship recommendation tasks, including SimDeveloper, ContributionRepo, and RepoMaintainer. Our proposed method outperforms these baselines, achieving improvements of 5.6–9.5% on Hit Ratio@10 and 3.4–11.1% on F1 score. These results demonstrate promising performance in predicting technical preferences for both repositories and developers. This research contributes to a more nuanced understanding of developer expertise in open-source communities and has potential implications for improving collaboration and project management on platforms like GitHub.
- 11 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (4) , 1-33
Open AccessAutomatically Deriving Developers’ Technical Expertise from the GitHub Social Network
Developers’ technical expertise is crucial for numerous tasks within open-source communities, such as identifying suitable developers and maintainers. Despite its significance, GitHub, the world’s largest open-source code hosting platform, does not explicitly display developers’ technical expertise. Existing methods fall short in capturing the multi-faceted and dynamic nature of developers’ skills and knowledge. To address this gap, we propose a novel approach that leverages graph neural networks (GNNs) to express developers’ technical expertise. Our method constructs a comprehensive GitHub social network that integrates various social and development activities. We then employ a GNN model to learn a low-dimensional representation vector for each developer, encapsulating their technical expertise across different dimensions. We assess the effectiveness of our model by comparing it against five baselines on three GitHub social relationship recommendation tasks, including SimDeveloper, ContributionRepo, and RepoMaintainer. Our proposed method outperforms these baselines, achieving improvements of 5.6–9.5% on Hit Ratio@10 and 3.4–11.1% on F1 score. These results demonstrate promising performance in predicting technical preferences for both repositories and developers. This research contributes to a more nuanced understanding of developer expertise in open-source communities and has potential implications for improving collaboration and project management on platforms like GitHub.
- Top Cited PapersOpen Access
- 21 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (2) , 1-25
DrWASI : LLM-assisted Differential Testing for WebAssembly System Interface Implementations
WebAssembly (Wasm) is an emerging binary format that serves as a compilation target for over 40 programming languages. Wasm runtimes provide execution environments that enhance portability by abstracting away operating systems and hardware details. A key component in these runtimes is the WebAssembly System Interface (WASI), which manages interactions with operating systems, like file operations. Considering the critical role of Wasm runtimes, the community has aimed to detect their implementation bugs. However, no work has focused on WASI-specific bugs that can affect the original functionalities of running Wasm binaries and cause unexpected results. To fill the void, we present DrWASI , the first general-purpose differential testing framework for WASI implementations. Our approach uses a large language model to generate seeds and applies variant and environment mutation strategies to expand and enrich the test case corpus. We then perform differential testing across major Wasm runtimes. By leveraging dynamic and static information collected during and after the execution, DrWASI can identify bugs. Our evaluation shows that DrWASI uncovered 33 unique bugs, with all confirmed and 7 fixed by developers. This research represents a pioneering step in exploring a promising yet under-explored area of the Wasm ecosystem, providing valuable insights for stakeholders.
- 21 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (2) , 1-25
Top Cited PapersOpen AccessDrWASI : LLM-assisted Differential Testing for WebAssembly System Interface Implementations
WebAssembly (Wasm) is an emerging binary format that serves as a compilation target for over 40 programming languages. Wasm runtimes provide execution environments that enhance portability by abstracting away operating systems and hardware details. A key component in these runtimes is the WebAssembly System Interface (WASI), which manages interactions with operating systems, like file operations. Considering the critical role of Wasm runtimes, the community has aimed to detect their implementation bugs. However, no work has focused on WASI-specific bugs that can affect the original functionalities of running Wasm binaries and cause unexpected results. To fill the void, we present DrWASI , the first general-purpose differential testing framework for WASI implementations. Our approach uses a large language model to generate seeds and applies variant and environment mutation strategies to expand and enrich the test case corpus. We then perform differential testing across major Wasm runtimes. By leveraging dynamic and static information collected during and after the execution, DrWASI can identify bugs. Our evaluation shows that DrWASI uncovered 33 unique bugs, with all confirmed and 7 fixed by developers. This research represents a pioneering step in exploring a promising yet under-explored area of the Wasm ecosystem, providing valuable insights for stakeholders.
- Open Access
Can Large Language Models Solve Path Constraints in Symbolic Execution?
Symbolic execution is an important software analysis technique which benefits downstream tasks such as software testing and debugging. However, several limitations hinder symbolic execution from application on real-world software. One of the limitations is the inability to solve diverse execution path constraints: traditional symbolic execution based on SMT solvers is difficult to handle execution paths with complex data structures or external API calls. In this paper, we focus on investigating the possibility of adopting large language models (LLM) for path constraint solving instead of traditional solver-based techniques in symbolic execution. We conduct an empirical study to evaluate the ability of LLMs in two types of path constraint solving: generating test inputs to facilitate an execution path, and determining whether a given execution path can be satisfied without triggering any bugs. We build new evaluation pipelines and benchmarks for two tasks: test case generation and path classification, which include data sources from both competition-level programs and real-world repositories. Our experiment results show that state-of-the-art LLMs are able to solve path constraints in both generation and classification tasks, with 60% of generated test cases that accurately cover the given execution path. Moreover, LLMs are capable of improving test coverage by covering execution paths in real-world repositories where traditional symbolic execution tools cannot be applied. These findings highlight the possibility of extending symbolic execution techniques with LLMs in the future to improve the ability and generalizability of symbolic execution.
Open AccessCan Large Language Models Solve Path Constraints in Symbolic Execution?
Symbolic execution is an important software analysis technique which benefits downstream tasks such as software testing and debugging. However, several limitations hinder symbolic execution from application on real-world software. One of the limitations is the inability to solve diverse execution path constraints: traditional symbolic execution based on SMT solvers is difficult to handle execution paths with complex data structures or external API calls. In this paper, we focus on investigating the possibility of adopting large language models (LLM) for path constraint solving instead of traditional solver-based techniques in symbolic execution. We conduct an empirical study to evaluate the ability of LLMs in two types of path constraint solving: generating test inputs to facilitate an execution path, and determining whether a given execution path can be satisfied without triggering any bugs. We build new evaluation pipelines and benchmarks for two tasks: test case generation and path classification, which include data sources from both competition-level programs and real-world repositories. Our experiment results show that state-of-the-art LLMs are able to solve path constraints in both generation and classification tasks, with 60% of generated test cases that accurately cover the given execution path. Moreover, LLMs are capable of improving test coverage by covering execution paths in real-world repositories where traditional symbolic execution tools cannot be applied. These findings highlight the possibility of extending symbolic execution techniques with LLMs in the future to improve the ability and generalizability of symbolic execution.