arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.20183cs.CL
收藏

双簇记忆智能体:解决优化问题求解中的多范式歧义

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving

School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院);Ministry of Education Key Laboratory of Intelligent Networks and Network Security, China(教育部智能网络与网络security重点实验室);Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, China(陕西省大数据知识工程重点实验室)

Xinyu Zhang, Yuchen Wan, Boxuan Zhang, Zesheng Yang, Lingling Zhang, Bifan Wei, Jun Liu

AI总结:

提出双簇记忆智能体(DCM-Agent),通过无训练方式利用历史解决方案构建双簇记忆,并采用记忆增强推理动态导航解路径,在七个优化基准上平均性能提升11%-21%。

摘要:

大型语言模型(LLMs)在优化问题中常面临结构歧义,即单个问题存在多个相关但冲突的建模范式,阻碍了有效解的生成。为解决此问题,我们提出双簇记忆智能体(DCM-Agent),以无训练方式利用历史解决方案提升性能。其核心是双簇记忆构建:该智能体将历史解决方案分配到建模和编码两个簇中,然后将每个簇的内容提炼为三种结构化类型:方法、检查表和陷阱。该过程推导出可泛化的指导知识。此外,该智能体引入记忆增强推理,以动态导航解路径、检测并修复错误,并利用结构化知识自适应切换推理路径。在七个优化基准上的实验表明,DCM-Agent平均性能提升11%-21%。值得注意的是,我们的分析揭示了“知识继承”现象:由更大模型构建的记忆可以引导较小模型获得更优性能,凸显了该框架的可扩展性和效率。

英文摘要:

Large Language Models (LLMs) often struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation. To address this, we propose Dual-Cluster Memory Agent (DCM-Agent) to enhance performance by leveraging historical solutions in a training-free manner. Central to this is Dual-Cluster Memory Construction. This agent assigns historical solutions to modeling and coding clusters, then distills each cluster's content into three structured types: Approach, Checklist, and Pitfall. This process derives generalizable guidance knowledge. Furthermore, this agent introduces Memory-augmented Inference to dynamically navigate solution paths, detect and repair errors, and adaptively switch reasoning paths with structured knowledge. The experiments across seven optimization benchmarks demonstrate that DCM-Agent achieves an average performance improvement of 11%- 21%. Notably, our analysis reveals a ``knowledge inheritance'' phenomenon: memory constructed by larger models can guide smaller models toward superior performance, highlighting the framework's scalability and efficiency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑