AEGIS: An Agent-based Framework for Bug Reproduction from Issue Descriptions
Automatically reproducing bugs in issue descriptions helps developers pinpoint and fix bugs timely, greatly facilitating the software development and maintenance. Built upon the powerful understanding capabilities of large language models (LLMs), agent-based approaches have achieved the state-of-the-art performance in the task. They generally leverage LLMs as the central controller to first retrieve bug-related information as context and then generate bug reproduction scripts. During the script modification process, agent-based approaches modify the script iteratively until the execution information reflects the bug accurately or the iterative turns are exhausted. Nevertheless, the agent-based approaches still face the following challenges: (1) Lengthy retrieved bug-related information: The retrieved bug-related information is usually long in length and contains irrelevant snippets, which is hard to be well comprehended by LLMs. (2) Lack of guidance in bug reproduction script generation: They generally modify bug reproduction scripts randomly and tend to generate repeated or spurious modifications, leading to bug reproduction failure.
To address the above challenges, in this paper, we propose an automated bug reproduction script generation framework named AEGIS. AEGIS consists of two main modules: (1) Bug-related context summarization module, aiming at condensing the retrieved information into structural context through further reranking and summarization. (2) Finite state machine (FSM)-guided script generation module, which aims at guiding the script modification process with proposed FSM which contains predefined modification rules. Extensive experiments on SWE-Bench, one public benchmark dataset, and six baseline methods show that AEGIS achieves the best performance in the task, exceeding the best baseline by 19.0% with respect to the bug reproduction rate. Besides, we deploy AEGIS in five internal repositories of ByteDance. During the three-month deployment period, it successfully reproduces 12 bugs and assists developers in implementing fixes.
Wed 25 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
14:00 - 15:30 | AgentDemonstrations / Industry Papers / Research Papers at Cosmos 3B Chair(s): Chunyang Chen TU Munich | ||
14:00 10mTalk | A Multi-agent Onboarding Assistant based on Large Language Models, Retrieval Augmented Generation, and Chain-of-Thought Demonstrations Andrei Cristian Ionescu Delft University of Technology, Sergey Titov JetBrains Research, Maliheh Izadi Delft University of Technology | ||
14:10 20mTalk | Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration Industry Papers Yingwei Ma Tongyi Lab, Alibaba, Qingping Yang Tongyi Lab, Alibaba, Rongyu Cao Tongyi Lab, Alibaba, China, Binhua Li Tongyi Lab, Alibaba, China, Fei Huang Tongyi Lab, Alibaba, China, Yongbin Li Tongyi Lab, Alibaba, China | ||
14:30 20mTalk | Demystifying LLM-based Software Engineering Agents Research Papers Chunqiu Steven Xia University of Illinois at Urbana-Champaign, Yinlin Deng University of Illinois at Urbana-Champaign, Soren Dunn University of Illinois Urbana-Champaign, Lingming Zhang University of Illinois at Urbana-Champaign DOI | ||
14:50 20mTalk | AEGIS: An Agent-based Framework for Bug Reproduction from Issue Descriptions Industry Papers Xinchen Wang Harbin Institute of Technology, Pengfei Gao ByteDance, Xiangxin Meng Beihang University, Chao Peng ByteDance, Ruida Hu Harbin Institute of Technology, Shenzhen, Yun Lin Shanghai Jiao Tong University, Cuiyun Gao Harbin Institute of Technology, Shenzhen | ||
15:10 20mTalk | Enhancing Game AI Behaviors with Large Language Models and Agentic AI Industry Papers Ciprian Paduraru Gameloft, and University of Bucharest, Miruna Gabriela Paduraru University of Bucharest
, Alin Stefanescu University of Bucharest | ||
Cosmos 3B is the second room in the Cosmos 3 wing.
When facing the main Cosmos Hall, access to the Cosmos 3 wing is on the left, close to the stairs. The area is accessed through a large door with the number “3”, which will stay open during the event.