CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning.

Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we…