跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20049 · v1

The Frontier Must Grow - Self-proposed, interpreter-labelled training roughly doubles a 4B model's accuracy on a fresh exam as its verified frontier grows

首次提交 2026-11-15 22:53
版本更新 2026-11-15 22:53
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

A model can learn from problems it poses itself when an executable oracle supplies the answers. Qwen3-4B proposed Lua 5.1 programs; those it predicted wrong at least once in four samples joined a pool labelled by the interpreter, each round adding twice as many programs as the last (300, 900, 2100 in total), and each round trained a fresh adapter from the base on the pool. On the original exam the procedure met its registered criterion, an item-level test of each adapter against its predecessor. On a 2340-item exam drawn afterwards, accuracy rose from 8.3% to 16.7%; that follow-up's registered criteria were not met because round 1 gained nothing, while rounds 2 and 3 added 5.0 and 2.9 points on average, both intervals above zero. One fit on the same amount of base-proposed frontier data reached 14.6%, so the rounds' 2.1-point advantage is inconclusive. Three earlier registered series met no per-lineage criterion, and the same loop showed no gain on repository tasks or for a 27B agent in those configurations.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 22:53 · 最新观测版本

The Frontier Must Grow - Self-proposed, interpreter-labelled training roughly doubles a 4B model's accuracy on a fresh exam as its verified frontier grows

A model can learn from problems it poses itself when an executable oracle supplies the answers. Qwen3-4B proposed Lua 5.1 programs; those it predicted wrong at least once in four samples joined a pool labelled by the interpreter, each round adding twice as many programs as the last (300, 900, 2100 in total), and each round trained a fresh adapter from the base on the pool. On the original exam the procedure met its registered criterion, an item-level test of each adapter against its predecessor. On a 2340-item exam drawn afterwards, accuracy rose from 8.3% to 16.7%; that follow-up's registered criteria were not met because round 1 gained nothing, while rounds 2 and 3 added 5.0 and 2.9 points on average, both intervals above zero. One fit on the same amount of base-proposed frontier data reached 14.6%, so the rounds' 2.1-point advantage is inconclusive. Three earlier registered series met no per-lineage criterion, and the same loop showed no gain on repository tasks or for a 27B agent in those configurations.

查看此版本解读 →查看此版本原文 ↗