At a time when there's keen public interest in AI that can make itself better, researchers here have tackled one of the central challenges affecting its development. The research team, which includes collaborators from NVIDIA and Flower Labs, have come up with a new method for recursive self-improving AI agents to continue improving themselves (by repeatedly testing and enhancing their own code) without hitting the evaluation ceiling that they frequently encounter.  Their method also suggests a way of cutting the costs of the computational resource needed for the development of such AI agents. While agents can already improve themselves by editing their own code, testing variants, and keeping changes that perform better, this process is usually limited by a fixed evaluator, benchmark, or test suite. Once the agent has learned everything that fixed signal can distinguish, improvement slows or stalls.…