mlsanityData to 14 Oct 2026

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

arXiv 2607.04212 ↗First posted 5 Jul 2026cs.SEcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

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.

Key facts. Cited by 1 paper 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.

Builds on

9 of 21 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025A Survey on Code Generation with LLM-based Agents31 Jul
  2. 2024AFlow: Automating Agentic Workflow Generation14 Oct
  3. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead7 Apr

Other references · 6

  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  2. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
  3. 2023Large Language Models for Software Engineering: Survey and Open Problemscited by 181
  4. 2023Self-planning Code Generation with Large Language Modelscited by 124
  5. 2024AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodologycited by 46
  6. 2024HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generationcited by 39

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
  2. 2026CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
  3. 2026E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
  4. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  5. 2025Evaluating Software Process Models for Multi-Agent Class-Level Code Generation
  6. 2025NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
  7. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  8. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation