Seokhyeon Moon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seokhyeon Moon has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Yoon-Chan Jhi
Samsung SDS, Seoul, Republic of Korea
4 shared publications - Hakjoo Oh
Korea University, Seoul, Republic of Korea
3 shared publications - Myungho Lee
Samsung SDS, Seoul, Republic of Korea
3 shared publications - Jihoon Cho
Samsung SDS, Seoul, Republic of Korea
1 shared publication - Jihun Kim
Samsung SDS, Seoul, Republic of Korea
1 shared publication - Jiseong Bak
Korea University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4376-4388
EvoLLM: High-Coverage, Readable, and Token-Efficient Unit Test Generation for Industrial Java Codebases
Adopting automated Java unit-test generation in industrial settings requires high coverage, readability, token efficiency, and modern-Java deployability. No existing technique meets all four: search-based test generators struggle with readability and modern-Java deployability, LLM-centric generators consume tens of millions of tokens, and prior LLM-based test refactoring methods drop baseline coverage by 8–21 percentage points (pp) in our controlled setups. We report on EvoLLM, a hybrid Java unit-test generator we built and deployed to address all four requirements. EvoLLM combines EvoSuiteng—a failure-analysis-driven hardening of EvoSuite that resolves deployability issues and strengthens baseline coverage—with cluster-wise LLM-based refactoring that groups tests by coverage goals and rewrites each cluster in a single LLM call grounded in compact program-under-test context. Across six open-source and three industrial projects, EvoLLM outperforms six state-of-the-art baselines, improving line coverage by 8.2–20.7 pp, branch coverage by 6.2–19.4 pp, and mutation score by 6.8–24.5 pp, while reducing LLM token usage by 47.3%–93.0%. In addition, the test generation stage of EvoLLM demonstrates robust deployability across target projects built with JDKs 8, 11, and 17, while achieving strong effectiveness on a Spring-core release requiring JDK 17. Finally, a 14-participant developer survey further suggests that EvoLLM-generated tests ranked higher in readability than those from prior tools and developer-written tests.
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4376-4388
Open AccessEvoLLM: High-Coverage, Readable, and Token-Efficient Unit Test Generation for Industrial Java Codebases
Adopting automated Java unit-test generation in industrial settings requires high coverage, readability, token efficiency, and modern-Java deployability. No existing technique meets all four: search-based test generators struggle with readability and modern-Java deployability, LLM-centric generators consume tens of millions of tokens, and prior LLM-based test refactoring methods drop baseline coverage by 8–21 percentage points (pp) in our controlled setups. We report on EvoLLM, a hybrid Java unit-test generator we built and deployed to address all four requirements. EvoLLM combines EvoSuiteng—a failure-analysis-driven hardening of EvoSuite that resolves deployability issues and strengthens baseline coverage—with cluster-wise LLM-based refactoring that groups tests by coverage goals and rewrites each cluster in a single LLM call grounded in compact program-under-test context. Across six open-source and three industrial projects, EvoLLM outperforms six state-of-the-art baselines, improving line coverage by 8.2–20.7 pp, branch coverage by 6.2–19.4 pp, and mutation score by 6.8–24.5 pp, while reducing LLM token usage by 47.3%–93.0%. In addition, the test generation stage of EvoLLM demonstrates robust deployability across target projects built with JDKs 8, 11, and 17, while achieving strong effectiveness on a Spring-core release requiring JDK 17. Finally, a 14-participant developer survey further suggests that EvoLLM-generated tests ranked higher in readability than those from prior tools and developer-written tests.
- Open Access
- 3 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 209-214
SCOUT: A Scenario-Guided Unit Test Generation Tool for Compact Open-Source LLMs
Large language models (LLMs) have shown promising performance in automated unit test generation, but existing approaches often rely on large proprietary or reasoning-oriented models, limiting their practicality for users with limited computational resources. We present SCOUT, a scenario-guided unit test generation tool designed for compact open-source LLMs. Rather than requiring LLMs to reason over raw source code, SCOUT extracts program information through static analysis and progressively provides concise, task-specific contexts for specialized reasoning tasks, including scenario construction and unit test generation. The tool further validates and refines generated tests using compilation, execution, and coverage feedback. Built on an extensible multi-agent architecture, SCOUT provides a fully automated workflow that enables practical unit test generation with locally deployed open-source LLMs on commodity hardware.
- 3 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 209-214
Open AccessSCOUT: A Scenario-Guided Unit Test Generation Tool for Compact Open-Source LLMs
Large language models (LLMs) have shown promising performance in automated unit test generation, but existing approaches often rely on large proprietary or reasoning-oriented models, limiting their practicality for users with limited computational resources. We present SCOUT, a scenario-guided unit test generation tool designed for compact open-source LLMs. Rather than requiring LLMs to reason over raw source code, SCOUT extracts program information through static analysis and progressively provides concise, task-specific contexts for specialized reasoning tasks, including scenario construction and unit test generation. The tool further validates and refines generated tests using compilation, execution, and coverage feedback. Built on an extensible multi-agent architecture, SCOUT provides a fully automated workflow that enables practical unit test generation with locally deployed open-source LLMs on commodity hardware.
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1044-1056
Effective Unit Test Generation for Java Null Pointer Exceptions
In this experience paper, we share our experience on enhancing automatic unit test generation to more effectively find Java null pointer exceptions (NPEs). NPEs are among the most common and critical errors in Java applications. However, as we demonstrate in this paper, existing unit test generation tools such as Randoop and EvoSuite are not sufficiently effective at catching NPEs. Specifically, their primary strategy of achieving high code coverage does not necessarily result in triggering diverse NPEs in practice. In this paper, we detail our observation on the limitations of current state-of-the-art unit testing tools in terms of NPE detection and introduce a new strategy to improve their effectiveness. Our strategy utilizes both static and dynamic analyses to guide the test case generator to focus specifically on scenarios that are likely to trigger NPEs. We implemented this strategy on top of EvoSuite, and evaluated our tool, NpeTest, on 108 NPE benchmarks collected from 96 real-world projects. The results show that our NPE-guidance strategy can increase EvoSuite's reproduction rate of the NPEs from 56.9% to 78.9%, a 38.7% improvement. Furthermore, NpeTest successfully detected 89 previously unknown NPEs from an industry project.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1044-1056
Open AccessEffective Unit Test Generation for Java Null Pointer Exceptions
In this experience paper, we share our experience on enhancing automatic unit test generation to more effectively find Java null pointer exceptions (NPEs). NPEs are among the most common and critical errors in Java applications. However, as we demonstrate in this paper, existing unit test generation tools such as Randoop and EvoSuite are not sufficiently effective at catching NPEs. Specifically, their primary strategy of achieving high code coverage does not necessarily result in triggering diverse NPEs in practice. In this paper, we detail our observation on the limitations of current state-of-the-art unit testing tools in terms of NPE detection and introduce a new strategy to improve their effectiveness. Our strategy utilizes both static and dynamic analyses to guide the test case generator to focus specifically on scenarios that are likely to trigger NPEs. We implemented this strategy on top of EvoSuite, and evaluated our tool, NpeTest, on 108 NPE benchmarks collected from 96 real-world projects. The results show that our NPE-guidance strategy can increase EvoSuite's reproduction rate of the NPEs from 56.9% to 78.9%, a 38.7% improvement. Furthermore, NpeTest successfully detected 89 previously unknown NPEs from an industry project.
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 63-64
EvoFuzz at the SBFT 2024 Tool Competition
EvoFuzz is an automated fuzzing tool that integrates fuzzing techniques into EvoSuite to improve code coverage. It first uses EvoSuite to generate a test suite, which is then utilized for fuzzing. During this process, EvoFuzz ensures the generated test suite is executable by performing strict code validity checks. Additionally, EvoFuzz actively explores new variables/values to achieve more code coverage. Our experimental results on the SBFT2024 benchmark demonstrate that EvoFuzz outperforms EvoSuite in both code coverage and mutation kill ratio.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 63-64
Open AccessEvoFuzz at the SBFT 2024 Tool Competition
EvoFuzz is an automated fuzzing tool that integrates fuzzing techniques into EvoSuite to improve code coverage. It first uses EvoSuite to generate a test suite, which is then utilized for fuzzing. During this process, EvoFuzz ensures the generated test suite is executable by performing strict code validity checks. Additionally, EvoFuzz actively explores new variables/values to achieve more code coverage. Our experimental results on the SBFT2024 benchmark demonstrate that EvoFuzz outperforms EvoSuite in both code coverage and mutation kill ratio.