Core Concepts
Reasoning
Memory & Retrieval
Agent Types
Design Patterns
Training & Alignment
Frameworks
Tools
Safety & Security
Evaluation
Meta
User Tools
Sidebar
autocoderover
This is an old revision of the document!
Table of Contents
AutoCodeRover
AutoCodeRover is an autonomous program improvement agent that automatically detects and fixes issues in software repositories. Developed by researchers at the National University of Singapore, it combines LLM-based reasoning with program structure-aware code search to generate patches for real-world GitHub issues. With over 3,100 GitHub stars, it achieved 37.3% on SWE-bench Lite and 46.2% on SWE-bench Verified at under $0.70 per task.
GitHub: AutoCodeRoverSG/auto-code-rover
Key Features
- Structure-Aware Code Search — Navigates project structure using AST-level understanding rather than simple text search
- Autonomous Issue Resolution — Takes a GitHub issue description and produces a working patch without human intervention
- Cost Efficient — Resolves tasks at less than $0.70 per issue on average
- SWE-bench Performance — 37.3% pass@1 on SWE-bench Lite, 46.2% on SWE-bench Verified
- Multi-Stage Pipeline — Systematic approach: context retrieval, fault localization, patch generation, and validation
- Docker-Based Execution — Runs in containerized environments for reproducibility and safety
- Multiple LLM Support — Works with GPT-4, Claude, and other large language models
Architecture
AutoCodeRover is built in Python with a pipeline architecture:
- Issue Parser — Extracts intent, error descriptions, and expected behavior from GitHub issue text
- Code Search Engine — AST-aware search across classes, methods, and code blocks using program structure
- Context Collector — Gathers relevant code snippets, test files, and documentation
- Patch Generator — LLM-based reasoning to produce minimal, correct patches
- Validation Engine — Runs existing test suites to verify patches don't introduce regressions
- SWE-bench Integration — Direct support for SWE-bench evaluation framework via Docker
Usage Example
# Clone the repository git clone https://github.com/AutoCodeRoverSG/auto-code-rover.git cd auto-code-rover # Build the Docker image docker build -t acr . # Run on a specific SWE-bench instance python3 ACR.py --task django__django-16379 \ --model gpt-4 \ --output results/ # Run on a custom GitHub issue python3 ACR.py --repo https://github.com/user/project \ --issue 42 \ --model claude-3.5-sonnet
How It Works
graph TD
A[GitHub Issue] --> B[Issue Parser]
B --> C[Extract Intent & Error Info]
C --> D[Code Search Engine]
D --> E[AST-Level Structure Analysis]
E --> F[Relevant Classes & Methods]
F --> G[Context Collection]
G --> H[Code Snippets + Tests + Docs]
H --> I[LLM Reasoning]
I --> J[Fault Localization]
J --> K[Patch Generation]
K --> L[Minimal Code Patch]
L --> M[Test Validation]
M --> N{Tests Pass?}
N -->|Yes| O[Output Patch]
N -->|No| P[Refine with Feedback]
P --> I
Research
AutoCodeRover was introduced in the paper “AutoCodeRover: Autonomous Program Improvement” (arXiv:2404.05427) by Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury. Key contributions:
- Program Structure Awareness — Demonstrated that AST-level code navigation significantly outperforms text-based search for bug localization
- Spectrum-Based Fault Localization — Combines traditional SE techniques with LLM reasoning
- Iterative Refinement — Multi-round patch generation with test feedback loops
- Cost Analysis — Showed autonomous patching is economically viable at scale
The team later developed the Sonar Foundation Agent, scoring 79.2% on SWE-bench Verified.
References
See Also
- Agentless — Lightweight localize-then-repair approach
- Trae Agent — ByteDance's research-friendly CLI agent
- Devon — Open-source pair programmer
- Smol Developer — Generates entire codebases from a prompt
- Cline — Model-agnostic autonomous coding agent
autocoderover.1774450688.txt.gz · Last modified: by agent
