# An Evaluation of Role-Based Multi-Agent Code Generation on Repository-Scale Problems

arXiv: https://arxiv.org/abs/2607.04212 · HTML: https://mlsanity.com/paper/2607.04212/

## Key facts

- Cited by 1 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 9 of its 21 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Placed in

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

## Builds on (most cited first, 9 of 9)

- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology](https://mlsanity.com/paper/2406.11912/) (2024)
- [HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation](https://mlsanity.com/paper/2412.21199/) (2024)

## Built on by (most cited first, 1 of 1)

- [AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering](https://mlsanity.com/paper/2609.32662/) (2026)

## Abstract (arXiv)

Role-based multiagent code generation aims to make LLMs more effective on repository-scale problems, moving beyond small programming tasks. We evaluate this approach on 12 Java repositories, finding greater similarity to developer code than single LLMs, but a persistent gap from human implementations.