cs.AI, cs.MA, cs.SE

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

arXiv:2512.18470v5 Announce Type: replace-cross
Abstract: Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavo…