The Future of AI-Driven Software Engineering

Abstract

A paradigm shift is underway in Software Engineering, with AI systems such as LLMs playing an increasingly important role in boosting software development productivity. This trend is anticipated to persist. In the next years, we expect a growing symbiotic partnership between human software developers and AI. The Software Engineering research community cannot afford to overlook this trend; we must address the key research challenges posed by the integration of AI into the software development process. In this paper, we present our vision of the future of software development in an AI-driven world and explore the key challenges that our research community should address to realize this vision.

**Note** Published in ACM Transactions on Software Engineering and Methodology (TOSEM)

References in corpus (17)

• Practical Program Repair in the Era of Large Pre-trained Language Models
• Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
• Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
• Large Language Models for Software Engineering: A Systematic Literature Review
• Using Large Language Models to Generate JUnit Tests: An Empirical Study
• Pynguin: Automated Unit Test Generation for Python
• An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation
• Software Testing with Large Language Models: Survey, Landscape, and Vision
• A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites
• GenMorph: Automatically Generating Metamorphic Relations via Genetic Programming
• MR-Scout: Automated Synthesis of Metamorphic Relations from Existing Test Cases
• LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead
• MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing
• On the Potential and Limitations of Few-Shot In-Context Learning to Generate Metamorphic Specifications for Tax Preparation Software
• Together or Apart? Investigating a mediator bot to aggregate bot's comments on pull requests
• "You still have to study" -- On the Security of LLM generated code

Cited by in corpus (4)

• A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AI
• LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops
• LLMORPH: Automated Metamorphic Testing of Large Language Models
• MultiMind: A Plug-in for the Implementation of Development Tasks Aided by AI Assistants