研究人员开发了TAGGRAPH，一个用于评估LLM智能体记忆系统的新颖框架。该系统使用具有共享对话记忆的受控评估框架，采用局部图配置和个性化PageRank扩散。虽然AdaptiveGraph在LongMemEval-S基准测试中表现强劲，但传统的BM25和OpenClaw方法最终获得了更高的检索分数。研究强调了词汇归一化和提取质量对图检索的显著影响，表明检索策略应与记忆设置和稳健的词汇基线结合进行评估。 AI
影响 提供了一种标准化方法来比较LLM智能体记忆系统，可能加速开发并提高智能体的一致性。
排序理由 该集群包含一篇学术论文，详细介绍了LLM智能体记忆系统的新框架和评估方法。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2609.38353v1 Announce Type: cross Abstract: Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in representation, indexing, retrieval, and evaluation. We present a c…
Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in representation, indexing, retrieval, and evaluation. We present a controlled evaluation framework based on shared 5W-…
Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in representation, indexing, retrieval, and evaluation. We present a controlled evaluation framework based on shared 5W-…