# Agent-Driven Automatic Software Improvement

arXiv: https://arxiv.org/abs/2406.16739 · HTML: https://mlsanity.com/paper/2406.16739/

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

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [Software Testing with Large Language Models: Survey, Landscape, and Vision](https://mlsanity.com/paper/2307.07221/) (2023)
- [Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics](https://mlsanity.com/paper/2006.06264/) (2020)
- [Large Language Models for Code: Security Hardening and Adversarial Testing](https://mlsanity.com/paper/2302.05319/) (2023)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [A Survey of Learning-based Automated Program Repair](https://mlsanity.com/paper/2301.03270/) (2023)
- [GameGPT: Multi-agent Collaborative Framework for Game Development](https://mlsanity.com/paper/2310.08067/) (2023)
- [Data-Centric Green AI: An Exploratory Empirical Study](https://mlsanity.com/paper/2204.02766/) (2022)
- [An Empirical Comparison of Pre-Trained Models of Source Code](https://mlsanity.com/paper/2302.04026/) (2023)
- [More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory](https://mlsanity.com/paper/2311.14646/) (2023)
- [Neurosymbolic Repair for Low-Code Formula Languages](https://mlsanity.com/paper/2207.11765/) (2022)
- [The Coming Era of AlphaHacking? A Survey of Automatic Software Vulnerability Detection, Exploitation and Patching Techniques](https://mlsanity.com/paper/1805.11001/) (2018)
- [An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code](https://mlsanity.com/paper/2307.02443/) (2023)

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

- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)

## 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.