RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
By Islem Bouzenia, Prem Devanbu, Michael Pradel. International Conference on Software Engineering, 2024
387 citations recorded by the source corpus.
Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper introduces Repair Agent, the first work to address the program repair challenge through an autonomous agent based on a large language model (LLM). Unlike existing deep learning-based approaches, which prompt a model with a fixed prompt or in a fixed feedback loop, our work treats the LLM as an agent capable of autonomously planning and executing actions to fix bugs by invoking suitable tools. Repair Agent freely interleaves gathering information about the bug, gathering repair ingredients, and validating fixes, while deciding which tools to invoke based on the gathered information and feedback from previous fix attempts. Key contributions that enable Repair Agent include a set of tools that are useful for program repair, a dynamically updated prompt format that allows the LLM to interact with these tools, and a finite state machine that guides the agent in invoking the tools. Our evaluation on the popular Defects4J dataset demonstrates Repair Agent's effectiveness in autonomously repairing 164 bugs, including 39 bugs not fixed by prior techniques. Interacting with the LLM imposes an average cost of 270k tokens per bug, which, under the current pricing of OpenAI's GPT-3.5 model, translates to 14 cents per bug. To the best of our knowledge, this work is the first to present an autonomous, LLM-based agent for program repair, paving the way for future agent-based techniques in software engineering.
Subfields: Artificial Intelligence, Computer Networks and Communications
View Paper: https://www.semanticscholar.org/paper/b7f46c9f01d9f649d18b709e2e88b3b97bebd016
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Networks and Communications
Citations in the corpus
- Agentless: Demystifying LLM-based Software Engineering Agents (2024, methodology): “To solve the challenging real-world software development problems from SWE-bench, inspired by the Devin AI Software Engineer [7], there has been a significant body of work from both academia and industry focusing on developing agent-based approaches [108, 37, 101, 30, 64, 29].”
- Agentic Software Issue Resolution with Large Language Models: A Survey (2025, unknown): “In recent years, LLMs have achieved significant success in multiple areas of software engineering [10, 20, 165] due to their rapid advancements in code understanding [138], reasoning [57, 162], and generation [73], paving the way for automated issue resolution.”