研究人员开发了一种新颖的神经符号框架，将大型语言模型（LLM）集成到多智能体系统（MAS）的模型检查过程中。该方法使用LLM作为策略生成预言机，提出候选策略，然后由MAS模型检查器进行形式化验证。使用Qwen3-32B模型的实验表明，这种生成-认证架构在一个包含4211个NatATL实例的新数据集上，在策略综合结果方面达到了92%的准确率。 AI
影响 这种神经符号方法可以显著提高多智能体系统中策略综合的效率和准确性。
排序理由 该集群包含一篇详细介绍新研究方法和数据集的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.17962v1 Announce Type: cross Abstract: Reasoning about what agents can achieve through strategic interaction is a core challenge in Multi-Agent Systems (MAS). Logics for strategic ability, such as ATL, provide rigorous methods, but their adoption is often hindered by t…
Reasoning about what agents can achieve through strategic interaction is a core challenge in Multi-Agent Systems (MAS). Logics for strategic ability, such as ATL, provide rigorous methods, but their adoption is often hindered by the computational cost of strategy synthesis. We in…