SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios

1. 1Identify long-horizon software evolution tasks that require coordination across multiple files and iterations
2. 2Develop AI coding agents that can interpret high-level requirements and preserve functionality
3. 3Evaluate AI coding agents using SWE-EVO benchmark
4. 4Analyze results to improve AI coding agents and software development workflows

Software engineers and AI researchers on a team benefit from SWE-EVO as it helps assess the capability of AI coding agents in real-world software development scenarios, enabling them to improve their tools and workflows

💡 Existing benchmarks for AI coding agents are limited to isolated tasks, while SWE-EVO addresses the need for evaluating agents in real-world, long-horizon software evolution scenarios

🚀 SWE-EVO: Benchmarking AI coding agents in long-horizon software evolution scenarios