AIBearisharXiv – CS AI · 15h ago7/10
🧠
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
Researchers introduce RepoMirage, an evaluation suite that tests whether code agents truly understand repository context by applying perturbations to challenge their reasoning abilities. The study reveals a significant gap in how agents handle complex, multi-file code tasks, with performance dropping from 66.8% to 25.3% when explicit structural understanding is required.