TCSE logo 
 Sigsoft logo
Sustainability badge

This program is tentative and subject to change.

Fri 2 May 2025 12:00 - 12:15 at 207 - Human and Social using AI 2

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.

This program is tentative and subject to change.

Fri 2 May

Displayed time zone: Eastern Time (US & Canada) change

11:00 - 12:30
Human and Social using AI 2Research Track / SE In Practice (SEIP) / Demonstrations at 207
11:00
15m
Talk
Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models
SE In Practice (SEIP)
Hao Li Queen's University, Cor-Paul Bezemer University of Alberta, Ahmed E. Hassan Queen’s University
11:15
15m
Talk
FairLay-ML: Intuitive Debugging of Fairness in Data-Driven Social-Critical Software
Demonstrations
Normen Yu Penn State, Luciana Carreon University of Texas at El Paso, Gang (Gary) Tan Pennsylvania State University, Saeid Tizpaz-Niari University of Illinois Chicago
11:30
15m
Talk
Dear Diary: A randomized controlled trial of Generative AI coding tools in the workplace
SE In Practice (SEIP)
Jenna L. Butler Microsoft Research, Jina Suh Microsoft Research, Sankeerti Haniyur Microsoft Corporation, Constance Hadley Institute for Work Life
11:45
15m
Talk
Exploring GenAI in Software Development: Insights from a Case Study in a Large Brazilian Company
SE In Practice (SEIP)
Guilherme Vaz Pereira School of Technology, PUCRS, Brazil, Victoria Jackson University of California, Irvine, Rafael Prikladnicki School of Technology at PUCRS University, Andre van der Hoek University of California, Irvine, Luciane Fortes Globo, Carolina Araújo Globo, André Coelho Globo, Ligia Chelli Globo, Diego Ramos Globo
Pre-print
12:00
15m
Talk
Human-In-the-Loop Software Development Agents
SE In Practice (SEIP)
Wannita Takerngsaksiri Monash University, Jirat Pasuksmit Atlassian, Patanamon Thongtanunam University of Melbourne, Kla Tantithamthavorn Monash University, Ruixiong Zhang Atlassian, Fan Jiang Atlassian, Jing Li Atlassian, Evan Cook Atlassian, Kun Chen Atlassian, Ming Wu Atlassian
12:15
15m
Talk
Measuring the Runtime Performance of C++ Code Written by Humans using GitHub Copilot
Research Track
Daniel Erhabor University of Waterloo, Sreeharsha Udayashankar University of Waterloo, Mei Nagappan University of Waterloo, Samer Al-Kiswany University of Waterloo
Pre-print
:
:
:
: