Preprint
Aug 2026
Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?
Evaluating mainstream coding agents on DEPBENCH, a benchmark consisting of 203 real-world dependency-upgrade tasks across five package ecosystems spanning five language communities, each involving hidden code-level changes that require source code adaptation.
Zi-Jian Luo, Runzhi He, Peng-Fei Gao et al.
· 0 citations