mlsanityData to 14 Oct 2026

Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation

arXiv 2510.19868 ↗First posted 22 Oct 2025cs.SEcited by 0

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

Abstract (arXiv)

Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods perform inadequately in large-scale application-level software code generation, failing to ensure reasonable orga- nizational structures of project code and making it difficult to maintain the code generation process. To address this, this paper envisions a Knowledge-Guided Application-Level Code Generation framework named KGACG, which aims to trans- form software requirements specification and architectural design document into executable code through a collaborative closed- loop of the Code Organization & Planning Agent (COPA), Coding Agent (CA), and Testing Agent (TA), combined with a feedback mechanism. We demonstrate the collaborative process of the agents in KGACG in a Java Tank Battle game case study while facing challenges. KGACG is dedicated to advancing the automation of application-level software development.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 26 of its 37 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

26 of 37 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generation24 May
  2. 2025AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation5 Apr
  3. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation14 Jan
  4. 2024CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models7 Nov
  5. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solving18 May
  6. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization2 Apr
  7. 2024SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents23 Mar
  8. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges14 Jan
  9. 2023ChatDev: Communicative Agents for Software Development16 Jul
  10. 2023Self-collaboration Code Generation via ChatGPT15 Apr

Other references · 16

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  3. 2023Teaching Large Language Models to Self-Debugcited by 988
  4. 2024A Survey on Large Language Models for Code Generationcited by 658
  5. 2023Self-planning Code Generation with Large Language Modelscited by 124
  6. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 111
  7. 2024Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Codecited by 107
  8. 2023CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulescited by 58
  9. 2024MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmeticcited by 53
  10. 2024LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluationcited by 49
  11. 2023ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarificationcited by 38
  12. 2024AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testingcited by 35
4 more
  1. 2023LLMs for Science: Usage for Code Generation and Data Analysiscited by 34
  2. 2024A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinementcited by 21
  3. 2024A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loopscited by 13
  4. 2024Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handlingcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling
  2. 2025A Survey on Code Generation with LLM-based Agents
  3. 2026WiseSpec: Requirements-Driven Agents for Code Generation
  4. 2025Knowledge-Guided Multi-Agent Framework for Automated Requirements Development: A Vision
  5. 2026CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
  6. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
  7. 2024CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
  8. 2025Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision