Skip to content
Log in

Towards Autonomous Software Development

Hao Wang Ruijie Meng Zhe Ye Alex Gu Naman Jain Xiaoyuan Liu Swarat Chaudhuri Thomas Zimmermann Sumit Gulwani Armando Solar-Lezama Ion Stoica Dawn Song U. Berkeley Cispa Cursor
· 0 citations · 143 references

TL;DR

A three-level taxonomy inspired by autonomous driving that distinguishes degrees of autonomy along a roadmap from today’s AI-assisted development workflows to fully autonomous software development in which AI systems autonomously identify demands and design, implement, verify, and maintain software without human oversight is introduced.

Semantic Scholar
View source

Similar papers

Preprint Aug 2026

The Specification Paradox: Rethinking Requirements Engineering in the Age of AI

The growing adoption of Large Language Models (LLMs) in Software Engineering has reinforced the expectation that coding activities can be largely automated. However, this perception may represent yet another historical search for a solution capable of eliminating the inherent challenges of software development. This article discusses the transition from a code-centered paradigm to Specification-Driven Development. We argue that artificial intelligence reduces some of the effort associated with writing source code, but it does not eliminate the complexity of developing professional software systems. Instead, it shifts this complexity toward domain understanding, requirements elicitation, specification development, validation, maintenance, and software evolution. Building on this perspective, we discuss the renewed centrality of Requirements Engineering, considering its implications for productivity and software quality, as well as risks associated with automation bias, ambiguity propagation, Specification Overfitting, and the accumulation of Specification Debt. Finally, we propose the Specification Paradox: the more capable artificial intelligence systems become at automatically generating software, the greater the dependence on correct, complete, verifiable, and explainable human-produced specifications. We conclude that the future of Software Engineering will depend not only on machines'ability to generate code, but also on humans'ability to correctly specify, evaluate, and evolve what is intended to be built.

T. Sirqueira, Jessica Faciroli · 0 citations
Open access Jul 2026

Integrating AI into Mobile Development Workflows: A System-Level Approach to Prompt-to-Code Engineering

This paper presents a layered architecture for AI-integrated development systems, encompassing prompt formulation, semantic interpretation, code generation, and validation mechanisms, and explores the dynamics of human–AI interaction, highlighting the importance of trust calibration, control boundaries, and iterative refinement in achieving reliable outcomes.

Yasin Arik · 0 citations
Book Open access Jul 2026

Autonomous Refactoring for Perfective Maintenance at Scale: The Agentic RACER System and its Empirical Evaluations

Developing a GenAI agent that autonomously formulates, prioritizes, and completes a limited set of code improvement tasks enterprise-wide is reported, and a Difference-in-Differences analysis found that automated improvements had an effect on the reduction of future maintenance effort that was as strong as or stronger than manual improvements confirming the feasibility of autonomous maintenance.

Audris Mockus, Arjun Singh Banga, Payal Bhuptani et al. · 0 citations
Review Open access Aug 2026

The Evolution of Quality Engineering: From Scripted Automation to AI Autonomy A Comprehensive Literature Review

Software testing is moving away from rigid, hand-written scripts toward AI systems that can adapt on their own. This review traces how quality engineering has changed, from rule-based automation to self-adjusting test frameworks, and looks at the technology behind Autonomous Quality Agents: Large Language Models (LLMs) that generate code from requirements, Computer Vision that handles visual regression, and Reinforcement Learning that drives exploratory testing. It also examines two ongoing problems: the difficulty of understanding how AI models make decisions, and the extra work needed to keep older, script-based automation running. The review closes with a proposed framework for where autonomous software assurance is headed next. This proposed framework, termed Autonomous Quality Assurance (AQA), is organised around three layers, perception (visual and DOM-based sensing), cognition (LLM-driven reasoning and test generation), and governance (interpretability and verification), intended to give practitioners and researchers a shared structure for locating where a given tool or technique sits today and what would need to mature before autonomous testing can be trusted at industrial scale.

Vanshita Agarwal · 0 citations
Preprint Jul 2026

How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests

This study characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle, offering a more nuanced understanding of their benefits and limitations in real-world practices.

Iren Mazloomzadeh, Mohammad Mehdi Morovati, F. Khomh · 0 citations
Review Aug 2026

Self-Evolving Coding Agents

This survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems.

H. Zhou, Haichuan Hu, Ye Shang et al. · 0 citations