ASE 2024
Sun 27 October - Fri 1 November 2024 Sacramento, California, United States

This program is tentative and subject to change.

Tue 29 Oct 2024 15:45 - 16:00 at Camellia - Code generation 1 Chair(s): Denys Poshyvanyk

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a strategy that significantly controls development complexity and enhances software quality. Inspired by this, we present a self-collaboration framework for code generation employing LLMs, exemplified by ChatGPT. Specifically, through role instructions, 1) Multiple LLM agents act as distinct `experts’, each responsible for a specific subtask within a complex task; 2) Specify the way to collaborate and interact, so that different roles form a virtual team to facilitate each other’s work, ultimately the virtual team addresses code generation tasks collaboratively without the need for human intervention. To effectively organize and manage this virtual team, we incorporate software-development methodology into the framework. Thus, we assemble an elementary team consisting of three LLM roles (i.e., analyst, coder, and tester) responsible for software development’s analysis, coding, and testing stages. We conduct comprehensive experiments on various code-generation benchmarks. Experimental results indicate that self-collaboration code generation relatively improves 29.9%-47.1% Pass@1 compared to the base LLM agent. Moreover, we showcase that self-collaboration could potentially enable LLMs to efficiently handle complex repository-level tasks that are not readily solved by the single LLM agent.

This program is tentative and subject to change.

Tue 29 Oct

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

15:30 - 16:30
Code generation 1Journal-first Papers / Research Papers / Industry Showcase at Camellia
Chair(s): Denys Poshyvanyk William & Mary
15:30
15m
Talk
AACEGEN: Attention Guided Adversarial Code Example Generation for Deep Code Models
Research Papers
Zhong Li , Chong Zhang Nanjing University, Minxue Pan Nanjing University, Tian Zhang Nanjing University, Xuandong Li Nanjing University
15:45
15m
Talk
Self-collaboration Code Generation via ChatGPT
Journal-first Papers
Yihong Dong Peking University, Xue Jiang , Zhi Jin Peking University, Ge Li Peking University
16:00
15m
Talk
Vehicle Domain-Specific Language: Unifying Modeling and Code Generation for Low-Code Automotive Development
Industry Showcase
Lei Liao GAC R&D Center, Junjie Wang Institute of Software at Chinese Academy of Sciences, Zhensheng Xu GAC R&D Center, Fangwen Mu Institute of Software, Chinese Academy of Sciences, Yukun Yang GAC R&D Center
16:15
15m
Talk
ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code
Research Papers
jiafeng University of Electronic Science and Technology of China, Jiachen Liu Harbin Institute of Technology, Shenzhen, Cuiyun Gao Harbin Institute of Technology, Chun Yong Chong Huawei, Chaozheng Wang The Chinese University of Hong Kong, Shan Gao Huawei, Xin Xia Huawei
Link to publication DOI Pre-print Media Attached
Hide past events