AI RESEARCH
EvoDev: An Iterative Feature-Driven Framework for End-to-End Software Development with LLM-based Agents
arXiv CS.AI
•
ArXi:2511.02399v2 Announce Type: replace-cross Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requirements. However, existing approaches largely adopt linear, waterfall-style pipelines, which oversimplify the iterative nature of real-world development and struggle with complex, large-scale projects. To address these limitations, we propose EvoDe, an iterative software development framework inspired by feature-driven development.