Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.
-
Updated
Sep 22, 2025 - Python
Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.
Generalist Software Agents to Solve Soware Engineering Tasks
Gemini CLI for repo-level operations
To associate your repository with the repo-level topic, visit your repo's landing page and select "manage topics."