Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment

ArXi:2603.21558v1 Announce Type: new Recursive self-improvement--where a model iteratively trains on its own outputs--promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations, errors in intermediate reasoning compound, leading to mode collapse and performance degradation. We propose Neuro-Symbolic Recursive Self-Alignment (NSRSA), which stabilizes iterative self-