English(EN) Memory as Code: Declarative Retrieval over Codified Long-Term Memory

新的“Memory as Code”框架增强了LLM的长期记忆

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员推出了一种名为“Memory as Code”（MaC）的新型框架，旨在增强大型语言模型（LLM）代理的长期记忆能力。MaC使用共享的代码抽象统一了记忆的构建和检索，从原子函数进展到模块化组合。这种方法允许声明式检索，将查询转换为在内存结构上操作的结构化程序。在基准数据集上的实验表明，与现有方法相比，LLM-judge的准确性显著提高，并且令牌消耗减少。 AI

影响该框架通过提高LLM代理回忆和组合信息的能力，有望使其能够处理更复杂、跨度更长的任务。

排序理由该集群包含一篇详细介绍LLM内存系统新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM内存系统新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 6 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Aoting Zeng, Yuxin Du, Jianwei Wang, Yizhang He, Shan Jiang, Xuemin Lin, Kai Wang · 2026-10-21 04:00

内存即代码：代码化长期内存上的声明式检索

arXiv:2610.27700v1 Announce Type: new Abstract: In long-term memory systems, memories are constructed from interaction histories and retrieved in response to queries, enhancing the reasoning ability of LLM agents. In complex scenarios, facts are scattered across sessions and thei…

本文如何被排名

报道来源 [1]

内存即代码：代码化长期内存上的声明式检索

相关实体

相关话题