読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニュースクイックテイク1 分で読めるDisconfirmAI 編集部

VERPO's token-level credit assignment avoids GRPO training collapse

Authors self-report VERPO beats GRPO baselines on five reasoning and tool-use tasks, with no independent reproduction.

2026-09-22 12:00 GMT+8

VERPO decomposes teacher guidance into token-level credit assignment, avoiding the optimization collapse caused by GRPO's sequence-level advantage estimation, and self-reports the highest multi-task average across five scientific reasoning and tool-use tasks.

Previously GRPO estimated advantages from whole-sequence scores, and the authors say this sequence-level granularity triggers optimization collapse.

The authors self-report larger gains on smaller models; this is a first-party benchmark with no independent reproduction.

The method includes a Fisher movement-cost controller and an FEC projection; version 4 was updated on September 23, and third-party validation is still pending.

ソース

  • arxiv.org↗
リサーチを続ける →
ログイン / 新規登録
読書リサーチレーダー投資フレームワーク