Abstraction Agent：用大语言模型零样本构建信息抽象

AI 摘要

arXiv 论文提出 Abstraction Agent，一种零样本流水线，利用大语言模型从自然语言游戏描述中发现连续战略特征，对私有状态打分并聚类，无需游戏专用评估器或博弈树遍历。在 HUNL turn endgames 上相比期望手牌强度基线将利用度降低 62%，并成功迁移到多种扑克变体和麻将。该方法将 LLM 参数中的隐性战略知识转化为显式数值特征，代码已开源。

正文节选

Abstraction Agent Abstract Information abstraction, which groups strategically similar private states into a tractable number of buckets, is essential for scaling game-solving algorithms to large imperfect-information games. Constructing effective abstractions, however, has traditionally required domain-specific evaluators such as hand-strength calculators or equity estimators, which demand expert knowledge and engineering effort and are unavailable for most less-studied games. We propose the Ab

发布时间：2026-09-07 12:00

抓取时间：2026-09-07 12:52

来源机构：arXiv