English(EN) Test-Time Memory Construction

新的T2Mem框架在推理过程中构建LLM内存

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员推出T$^2$Mem，一种用于在大型语言模型（LLM）中构建内存的新颖框架，该框架将过程推迟到推理时进行。与传统的离线构建内存的方法不同，T$^2$Mem在LLM进行推理时逐步构建内存，使其能够适应特定的查询需求。该方法使用轻量级的离线分集级别元数据来捕获关键事件和时间关联，同时保留与原始交互的链接。在LoCoMo和LongMemEval上的实验表明，T$^2$Mem的有效性优于基线，并降低了内存构建的开销。 AI

影响这种方法可以通过使内存构建更有效和自适应来提高LLM在需要长期上下文的任务上的性能。

排序理由该集群包含一篇详细介绍LLM内存构建新方法的论文。[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: 11 / 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内存构建新方法的论文。[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, infra; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zijun Wang, Yifan Ji, Haidong Xin, Zhenghao Liu, Yukun Yan, Zulong Chen, Yu Gu, Ge Yu, Maosong Sun · 2026-10-12 04:00

测试时内存构建

arXiv:2610.13348v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to answer questions over long interaction histories, where relevant evidence may be scattered across distant sessions. Existing memory systems typically construct and maintain sophisticated memo…

本文如何被排名

报道来源 [1]

测试时内存构建

相关实体

相关话题