跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24470 · v1

When to Refine: Selective Search for Frozen Visual World Models

首次提交 2026-11-18 22:08
版本更新 2026-11-18 22:08
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Planning with a visual world model requires deciding both which actions to execute and how long to search for them. We introduce Selective CEM Refinement (SCR), a learned rule for deciding whether to continue cross-entropy method (CEM) search with a frozen LeWorldModel. After five it- erations, the gate measures how far the mean first action chunk has moved, how much the mean terminal cost of elite plans has fallen, and how widely their first chunks vary. It returns the current plan for execution or continues the same search for ten more iterations. The gate requires no addi- tional world-model rollout. On 16 PushT scenes evaluated with two planning seeds, SCR succeeded in 25 of 32 trials, compared with 28 of 32 for fixed 15-iteration search (Fixed-15). All 25 SCR suc- cesses occurred in trials that Fixed-15 also solved, yield- ing 89.29% paired success retention. Across complete episodes, including replanning, SCR evaluated 23.81% fewer candidate plans and reduced mean controller time per eight-environment batch by 17.22%. Its observed suc- cess rate was 5.36 percentage points above an analytic mix- ture of the two fixed-depth controllers at the same expected candidate workload, although the difference changed sign across planning seeds. Compared with gating only at the initial solve under the same random-draw padding proto- col, gating again at replanning produced nine additional early exits. This reduced total candidate evaluations by 15.79%, while successes fell from 27 to 25.

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 · 2026-11-18 22:08 · 最新观测版本

When to Refine: Selective Search for Frozen Visual World Models

Planning with a visual world model requires deciding both which actions to execute and how long to search for them. We introduce Selective CEM Refinement (SCR), a learned rule for deciding whether to continue cross-entropy method (CEM) search with a frozen LeWorldModel. After five it- erations, the gate measures how far the mean first action chunk has moved, how much the mean terminal cost of elite plans has fallen, and how widely their first chunks vary. It returns the current plan for execution or continues the same search for ten more iterations. The gate requires no addi- tional world-model rollout. On 16 PushT scenes evaluated with two planning seeds, SCR succeeded in 25 of 32 trials, compared with 28 of 32 for fixed 15-iteration search (Fixed-15). All 25 SCR suc- cesses occurred in trials that Fixed-15 also solved, yield- ing 89.29% paired success retention. Across complete episodes, including replanning, SCR evaluated 23.81% fewer candidate plans and reduced mean controller time per eight-environment batch by 17.22%. Its observed suc- cess rate was 5.36 percentage points above an analytic mix- ture of the two fixed-depth controllers at the same expected candidate workload, although the difference changed sign across planning seeds. Compared with gating only at the initial solve under the same random-draw padding proto- col, gating again at replanning produced nine additional early exits. This reduced total candidate evaluations by 15.79%, while successes fell from 27 to 25.

查看此版本解读 →查看此版本原文 ↗