軟體工程人工智慧的挑戰與發展路徑

Challenges and Paths Towards AI for Software Engineering

March 28, 2025

作者: Alex Gu, Naman Jain, Wen-Ding Li, Manish Shetty, Yijia Shao, Ziyang Li, Diyi Yang, Kevin Ellis, Koushik Sen, Armando Solar-Lezama

cs.AI

摘要

AI在軟體工程領域的應用近期取得了顯著進展，已成為生成式AI中的一個重要成功案例。然而，在自動化軟體工程充分發揮其潛力之前，仍有許多挑戰亟待解決。我們應能實現高度的自動化，讓人類專注於決定要構建什麼以及如何平衡複雜的取捨，而將大部分例行開發工作交由自動化處理。要達到這種自動化水平，需要學術界和產業界投入大量的研究和工程努力。本文旨在從三個方面探討這一目標的進展。首先，我們提供了一個結構化的分類法，涵蓋AI在軟體工程中的具體任務，強調除了代碼生成和補全之外，軟體工程中還有許多其他任務。其次，我們概述了限制當前方法的幾個關鍵瓶頸。最後，我們提供了一份帶有觀點的列表，列出了在這些瓶頸上取得進展的潛在研究方向，希望能激發這一快速成熟領域的未來研究。

English

AI for software engineering has made remarkable progress recently, becoming a notable success within generative AI. Despite this, there are still many challenges that need to be addressed before automated software engineering reaches its full potential. It should be possible to reach high levels of automation where humans can focus on the critical decisions of what to build and how to balance difficult tradeoffs while most routine development effort is automated away. Reaching this level of automation will require substantial research and engineering efforts across academia and industry. In this paper, we aim to discuss progress towards this in a threefold manner. First, we provide a structured taxonomy of concrete tasks in AI for software engineering, emphasizing the many other tasks in software engineering beyond code generation and completion. Second, we outline several key bottlenecks that limit current approaches. Finally, we provide an opinionated list of promising research directions toward making progress on these bottlenecks, hoping to inspire future research in this rapidly maturing field.