mlsanityData to 14 Oct 2026

Agent-Driven Automatic Software Improvement

arXiv 2406.16739 ↗First posted 24 Jun 2024cs.SEcited by 1

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

Abstract (arXiv)

With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore innovative solutions by focusing on the deployment of agents powered by Large Language Models (LLMs) to perform software maintenance tasks. The iterative nature of agents, which allows for continuous learning and adaptation, can help surpass common challenges in code generation. One distinct challenge is the last-mile problems, errors at the final stage of producing functionally and contextually relevant code. Furthermore, this project aims to surpass the inherent limitations of current LLMs in source code through a collaborative framework where agents can correct and learn from each other's errors. We aim to use the iterative feedback in these systems to further fine-tune the LLMs underlying the agents, becoming better aligned to the task of automated software improvement. Our main goal is to achieve a leap forward in the field of automatic software improvement by developing new tools and frameworks that can enhance the efficiency and reliability of software development.

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 27 of its 37 references that are in the map. First posted on arXiv 24 Jun 2024.

Builds on

27 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023GameGPT: Multi-agent Collaborative Framework for Game Development12 Oct

Other references · 26

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  5. 2023Teaching Large Language Models to Self-Debugcited by 988
  6. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
  7. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  8. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  9. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  10. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 431
  11. 2024Understanding the planning of LLM agents: A surveycited by 421
  12. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
14 more
  1. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308
  2. 2023Large Language Model Alignment: A Surveycited by 243
  3. 2023Don't Make Your LLM an Evaluation Benchmark Cheatercited by 194
  4. 2023Software Testing with Large Language Models: Survey, Landscape, and Visioncited by 166
  5. 2020Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metricscited by 158
  6. 2023Large Language Models for Code: Security Hardening and Adversarial Testingcited by 155
  7. 2023Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPTcited by 125
  8. 2023A Survey of Learning-based Automated Program Repaircited by 55
  9. 2022Data-Centric Green AI: An Exploratory Empirical Studycited by 25
  10. 2023An Empirical Comparison of Pre-Trained Models of Source Codecited by 25
  11. 2023More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatorycited by 18
  12. 2022Neurosymbolic Repair for Low-Code Formula Languagescited by 12
  13. 2018The Coming Era of AlphaHacking? A Survey of Automatic Software Vulnerability Detection, Exploitation and Patching Techniquescited by 5
  14. 2023An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Codecited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 86

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Code Generation with LLM-based Agents
  2. 2024Agentless: Demystifying LLM-based Software Engineering Agents
  3. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  4. 2024Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
  5. 2024An Empirical Study on LLM-based Agents for Automated Bug Fixing
  6. 2025AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation
  7. 2025Evaluating Software Process Models for Multi-Agent Class-Level Code Generation
  8. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation