# Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework

arXiv: https://arxiv.org/abs/2511.02399 · HTML: https://mlsanity.com/paper/2511.02399/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 16 of 16)

- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [OpenAGI: When LLM Meets Domain Experts](https://mlsanity.com/paper/2304.04370/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Self-Evolving Multi-Agent Collaboration Networks for Software Development](https://mlsanity.com/paper/2410.16946/) (2024)
- [Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration](https://mlsanity.com/paper/2406.01422/) (2024)
- [AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology](https://mlsanity.com/paper/2406.11912/) (2024)
- [STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis](https://mlsanity.com/paper/2406.10018/) (2024)
- [RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation](https://mlsanity.com/paper/2509.16198/) (2025)
- [Experimenting a New Programming Practice with LLMs](https://mlsanity.com/paper/2401.01062/) (2024)
- [Toward Improved Deep Learning-based Vulnerability Detection](https://mlsanity.com/paper/2403.03024/) (2024)
- [Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation](https://mlsanity.com/paper/2501.10200/) (2025)
- [Generative AI to Generate Test Data Generators](https://mlsanity.com/paper/2401.17626/) (2024)
- [Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development](https://mlsanity.com/paper/2510.16395/) (2025)
- [AndroEvolve: Automated Update for Android Deprecated-API Usages](https://mlsanity.com/paper/2012.07259/) (2020)
- [On the Generalizability of Deep Learning-based Code Completion Across Programming Language Versions](https://mlsanity.com/paper/2403.15149/) (2024)
- [Explainability as a Compliance Requirement: What Regulated Industries Need from AI Tools for Design Artifact Generation](https://mlsanity.com/paper/2507.09220/) (2025)

## Built on by (most cited first, 2 of 2)

- [Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement](https://mlsanity.com/paper/2609.01481/) (2026)
- [FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation](https://mlsanity.com/paper/2609.26480/) (2026)

## Abstract (arXiv)

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 EvoDev, an iterative software development framework inspired by feature-driven development. EvoDev decomposes user requirements into a set of user-valued features and constructs a Feature Map, a directed acyclic graph that explicitly models dependencies between features. Each feature node in the feature map maintains multi-layer contexts, including business logic, software design, and code implementation, which are propagated along dependencies to provide context for subsequent development iterations. We evaluate EvoDev on challenging Android development tasks and show that it outperforms the best-performing baseline, Claude Code, by 57.3%, while improving single-agent performance by 16.0%-58.5% across different base LLMs, highlighting the importance of feature decomposition, dependency modeling, context propagation, and workflow-aware agent design for end-to-end software development. Moreover, our work summarizes practical insights for designing iterative, LLM-driven development frameworks and informs future training of base LLMs to better support iterative software development.