SERA is a new, low-cost way to train coding helpers (agents) that learn the style and secrets of your own codebase.
Coding agents waste most of their tokens just reading giant files, which makes them slow and expensive.
SWE-EVO is a new test (benchmark) that checks if AI coding agents can upgrade real software projects over many steps, not just fix one small bug.
This paper introduces the Confucius Code Agent (CCA), a coding helper built to handle huge real-world codebases with long tasks and many tools.