两篇新研究论文MemTrace和T-Mem，引入了改进大语言模型代理长期记忆的新方法。MemTrace侧重于通过知识点而非单个问题来评估记忆，揭示了证据使用而非检索是主要瓶颈。T-Mem提出了一种通过排练过往经历来预见未来上下文的架构，实现了描述性和联想性回忆，并在相关基准测试中取得了最先进的成果。 AI
影响 这些论文通过关注记忆的评估和利用方式，为改进大语言模型代理能力指明了新方向，有望带来更连贯、更具适应性的对话代理。
排序理由 两篇在arXiv上发表的学术论文，介绍了改进大语言模型记忆的新方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Because this approach scores question rows independently, …
arXiv:2606.15405v1 Announce Type: cross Abstract: Long-term memory is essential for conversational agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their behaviour to each user. Current LLM-backed long-term c…