---
id: 20260904-T0-13
title: "WMLLM：先预测后行动的世界模型，提升黑盒优化效率"
title_en: "WMLLM Uses Predict-Then-Act World Modeling for Black-Box Optimization"
url: https://ai.daily.yangsir.net/daily/20260904-T0-13
issue_date: 2026-09-04
publish_date: 2026-09-03T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2609.01608
---

# WMLLM：先预测后行动的世界模型，提升黑盒优化效率

arXiv新论文提出WMLLM框架，将黑盒优化问题重构为基于世界模型的预测-行动循环，以解决高维弱结构搜索空间中采样效率低的问题。该方法利用自进化优化代理，避免直接候选生成的高成本，在多个基准任务上展现出比传统贝叶斯优化等方法更优的样本效率。

## English Version

**WMLLM Uses Predict-Then-Act World Modeling for Black-Box Optimization**

A new arXiv paper presents WMLLM, a self-evolving optimization agent framework that employs a predict-then-act world modeling approach for black-box optimization. Designed for large, weakly structured, high-dimensional search spaces, WMLLM improves sample efficiency over direct candidate generation and trial-and-error methods, outperforming Bayesian optimization baselines across benchmarks.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2609.01608)

**详情页**：https://ai.daily.yangsir.net/daily/20260904-T0-13

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*