#trajectory-balance

1 articles

01 ·Large Language Models·★ MEMBER·PAPER·13 min read Paper Explained: FlowBalance — Verifier-Grounded Self-Improvement from a Model's Own Reasoning Learning from your own answers breaks in two ways: the grading is too sparse, or you believe your own confidence. FlowBalance fixes both with one move — let the verifier decide the sign of the dense self-score — and learns a normalized distribution over whole responses. Explained from first principles.