Researchers introduced WideSWE, a benchmark for evaluating coding agents on coordinated changes across multiple repositories, arguing that existing coding-agent evaluation remains largely confined to a single codebase. The work targets multi-repository features and bug fixes, which the authors say are common in software ecosystems but not yet covered by current task-completion assessments.
Coding-agent evaluation has progressed from resolving individual issues to carrying out long-horizon development, yet task completion is still largely assessed within a single codebase. In software ecosystems, many features and bug fixes require coordinated changes across multiple repositories. We i
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.