Open access
Jun 2026
RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models
RepoReasoner is introduced, a benchmark for evaluating repository-level code reasoning that assesses two complementary abilities: Output Prediction, which measures fine-grained, stateful execution reasoning across files, and Call Chain Prediction, which evaluates high-level architectural dependency understanding under noisy context.
Yanlin Wang, Suiquan Wang, Yanlin Wang et al.
· Proceedings of the ACM on So... · 2 citations