====== 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.((https://arxiv.org/abs/2404.05427|AutoCodeRover: Autonomous Program Improvement (arXiv:2404.05427)))

GitHub: [[https://github.com/AutoCodeRoverSG/auto-code-rover|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((https://arxiv.org/abs/2404.05427|AutoCodeRover: Autonomous Program Improvement (arXiv:2404.05427)))
  * **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 =====

<code bash>
# 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
</code>

===== How It Works =====

<mermaid>
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
</mermaid>

===== 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:((https://arxiv.org/abs/2404.05427|AutoCodeRover: Autonomous Program Improvement (arXiv:2404.05427)))

  * **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.

===== See Also =====

  * [[agentless|Agentless]] — Lightweight localize-then-repair approach
  * [[trae_agent|Trae Agent]] — ByteDance's research-friendly CLI agent
  * [[devon|Devon]] — Open-source pair programmer
  * [[smol_developer|Smol Developer]] — Generates entire codebases from a prompt
  * [[cline|Cline]] — Model-agnostic autonomous coding agent

===== References =====