Patanamon (Pick) Thongtanunam

2025

1. ICSE

   Human-In-the-Loop Software Development Agents

   Wannita Takerngsaksiri, Jirat Pasuksmit, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, and 5 more authors

   In Proceedings of the ACM/IEEE International Conference on Software Engineering, 2025

   Abs Bib HTML PDF

   Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given issue to source code). However, existing work is evaluated based on historical benchmark datasets, does not consider human feedback at each stage of the automated software development process, and has not been deployed in practice. In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plans and source code for a given task. We design, implement, and deploy the HULA framework into Atlassian JIRA for internal uses. Through a multi-stage evaluation of the HULA framework, Atlassian software engineers perceive that HULA can minimize the overall development time and effort, especially in initiating a coding plan and writing code for straightforward tasks. On the other hand, challenges around code quality are raised to be solved in some cases. We draw lessons learned and discuss opportunities for future work, which will pave the way for the advancement of LLM-based agents in software development.

   @inproceedings{TakerngsaksiriICSE2025,
     title = {Human-In-the-Loop Software Development Agents},
     author = {Takerngsaksiri, Wannita and Pasuksmit, Jirat and Thongtanunam, Patanamon and Tantithamthavorn, Chakkrit and Zhang, Ruixiong and Jiang, Fan and Li, Jing and Cook, Evan and Chen, Kun and Wu, Ming},
     year = {2025},
     booktitle = {Proceedings of the ACM/IEEE International Conference on Software Engineering},
     pages = {to appear},
     doi = {},
     note = {},
   }

2. MSR

   Too Noisy To Learn: Enhancing Data Quality for Code Review Comment Generation

   Chunhua Liu, Hong Yi Lin, and Patanamon Thongtanunam

   In Proceedings of the ACM/IEEE International Conference on Mining software repositories, 2025

   Acceptance rate: 29% (44/161)

   Abs Bib HTML PDF

   Code review is an important practice in software development, yet it is time-consuming and requires substantial effort. While open-source datasets have been used to train neural models for automating code review tasks, including review comment generation, these datasets contain a significant amount of noisy comments (e.g., vague or non-actionable feedback) that persist despite cleaning methods using heuristics and machine learning approaches. Such remaining noise may lead models to generate low-quality review comments, yet removing them requires a complex semantic understanding of both code changes and natural language comments. In this paper, we investigate the impact of such noise on review comment generation and propose a novel approach using large language models (LLMs) to further clean these datasets. Based on an empirical study on a large-scale code review dataset, our LLM-based approach achieves 66-85% precision in detecting valid comments. Using the predicted valid comments to fine-tune the state-of-the-art code review models (cleaned models) can generate review comments that are 13.0% - 12.4% more similar to valid human-written comments than the original models. We also find that the cleaned models can generate more informative and relevant comments than the original models. Our findings underscore the critical impact of dataset quality on the performance of review comment generation. We advocate for further research into cleaning training data to enhance the practical utility and quality of automated code review.

   @inproceedings{LiuMSR2025,
     title = {Too Noisy To Learn: Enhancing Data Quality for Code Review Comment Generation},
     author = {Liu, Chunhua and Lin, Hong Yi and Thongtanunam, Patanamon},
     year = {2025},
     booktitle = {Proceedings of the ACM/IEEE International Conference on Mining software repositories},
     pages = {to appear},
     doi = {},
     note = {Acceptance rate: 29% (44/161)},
   }

3. MSR

   Human-In-The-Loop Software Development Agents: Challenges and Future Directions

   Jirat Pasuksmit, Wannita Takerngsaksiri, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, and 5 more authors

   In Proceedings of the ACM/IEEE International Conference on Mining software repositories, 2025

   Abs Bib HTML PDF

   Multi-agent LLM-driven systems for software development are rapidly gaining traction, offering new opportunities to enhance productivity. At Atlassian, we deployed Human-in-the-Loop Software Development Agents to resolve Jira work items and evaluated the generated code quality using functional correctness testing and GPT-based similarity scoring. This paper highlights two major challenges: the high computational costs of unit testing and the variability in LLM-based evaluations. We also propose future research directions to improve evaluation frameworks for Human-In-The-Loop software development tools.

   @inproceedings{PasuksmitMSR2025,
     title = {Human-In-The-Loop Software Development Agents: Challenges and Future Directions},
     author = {Pasuksmit, Jirat and Takerngsaksiri, Wannita and Thongtanunam, Patanamon and Tantithamthavorn, Chakkrit and Zhang, Ruixiong and Jiang, Fan and Li, Jing and Cook, Evan and Chen, Kun and Wu, Ming},
     year = {2025},
     booktitle = {Proceedings of the ACM/IEEE International Conference on Mining software repositories},
     pages = {to appear},
     doi = {},
     note = {},
   }

4. MSR

   Should Code Models Learn Pedagogically? A Preliminary Evaluation of Curriculum Learning for Real-World Software Engineering Tasks

   Kyi Shin Khant, Hong Yi Lin, and Patanamon Thongtanunam

   In Proceedings of the ACM/IEEE International Conference on Mining software repositories, 2025

   Acceptance rate: 29% (44/161)

   Abs Bib HTML PDF

   Learning-based techniques, especially advanced pre-trained models for code have demonstrated capabilities in code understanding and generation, solving diverse software engineering (SE) tasks. Despite the promising results, current training approaches may not fully optimize model performance, as they typically involve learning from randomly shuffled training data. Recent work shows that Curriculum Learning (CL) can improve performance on code-related tasks through incremental learning based on the difficulty of synthetic code. Yet, the effectiveness of CL with conventional difficulty measures in SE tasks remains largely unexplored. In this study, we explore two conventional code metrics: code length and cyclomatic complexity to determine the difficulty levels. We investigate how the pre-trained code model (CodeT5) learns under CL, through the tasks of code clone detection and code summarization. Our empirical study on the CodeXGLUE benchmark showed contrasting results to prior studies, where the model exhibited signs of catastrophic forgetting and shortcut learning. Surprisingly, model performance saturates after only the first quartile of training, potentially indicating a limit in the model’s representation capacity and/or the task’s inherent difficulty. Future work should further explore various CL strategies with different code models across a wider range of SE tasks for a more holistic understanding.

   @inproceedings{KhantMSR2025,
     title = {Should Code Models Learn Pedagogically? A Preliminary Evaluation of Curriculum Learning for Real-World Software Engineering Tasks},
     author = {Khant, Kyi Shin and Lin, Hong Yi and Thongtanunam, Patanamon},
     year = {2025},
     booktitle = {Proceedings of the ACM/IEEE International Conference on Mining software repositories},
     pages = {to appear},
     doi = {},
     note = {Acceptance rate: 29% (44/161)},
   }

1. 1,200,000 AUD

   CSIRO: Next Generation Graduates Programs

   Co-leading the Responsible AI Software Engineering (RAISE) program with 9 industry partners to train 11 graduates (7 Ph.D., 1 Master, and 3 Honours) addressing the urgent need for deep expertise and excellent skills in Responsible AI Software Engineering for digital health, transportation, and defence sectors.
2. 402,000 AUD

   ARC Discovery Early Career Researcher Award (DECRA)

   For 3 years (2021 - )

   ARC DECRA Fellowship is the competitive fund which is awarded to Early Career Researchers in Australia to support excellent basic and applied research. Success rate (DE21): 200/1173 (17.1%) across all disciplines; 56/331 (16.9%) for the Engineering, Information and Computing Sciences discipline.

   more

   Recent Awards

   1. MSR 2024 Ric Holt Early Career Achievement Award

      For their contributions to understanding and improving modern code review practices using mining software repositories techniques.
   2. CIS Excellence in Teaching & Education award (2023)

      For the outstanding leadership and service in the coordination of Master of Software Engeering program at the School of Computing and Information Systems, The University of Melbourne
   3. CIS Excellence in Engagement (ECR) award (2022)

      For the outstanding research achievements of Early Career Researchers at the School of Computing and Information Systems, The University of Melbourne

      more