返回全部动态
WMLLM：基于预测-行动世界建模的自进化优化智能体
原标题：WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling
AI 摘要
WMLLM 提出一种基于预测-行动世界建模的自进化优化智能体框架，利用 LLM 在生成候选前预测结果，并通过预测误差自我改进。在分子优化等黑箱优化任务中，该方法提升了样本效率和最终性能，并在多目标分子优化基准上达到最先进结果。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling Abstract Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficiency because they rely on direct candidate generation or trial-and-error refinement. A natural way to improve search efficiency is to use world modeling, which can help identify promising optimization directions before costly evaluation.
发布时间：2026-09-03 12:00
抓取时间：2026-09-03 12:09
来源机构：arXiv