用结构化记忆提升LLM代理效率，大幅降低上下文成本
Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents
- 将对话转为紧凑语义三元组，实现精准检索与连贯推理
- 在LoCoMo上达81.95%准确率，每查询仅用1294令牌（约全上下文5%）
- 适合需跨会话记忆的高效部署场景，尤其关注成本优化者
随着大语言模型演变为自主代理，API层的持久记忆对于实现跨会话的上下文感知行为至关重要。现有方法导致厂商绑定，并依赖注入大量原始对话至提示词中，造成高令牌开销和性能下降。我们提出Memori，一种LLM无关的持久记忆层，将记忆视为数据结构问题。其高级增强管道将非结构化对话转化为紧凑的语义三元组与对话摘要，支持精确检索与连贯推理。在LoCoMo基准测试中，Memori达到81.95%的准确率，每查询仅使用1,294个令牌（约全上下文的5%），相比竞争方案减少67%令牌，比完整上下文方法节省超20倍。结果表明，有效记忆依赖结构化表示而非更大上下文窗口，推动可扩展、低成本部署。
原文摘要 · Abstract (English)
As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely on injecting large volumes of raw conversation into prompts, leading to high token costs and degraded performance. We introduce Memori, an LLM-agnostic persistent memory layer that treats memory as a data structuring problem. Its Advanced Augmentation pipeline converts unstructured dialogue into compact semantic triples and conversation summaries, enabling precise retrieval and coherent reasoning. Evaluated on the LoCoMo benchmark, Memori achieves 81.95% accuracy, outperforming existing memory systems while using only 1,294 tokens per query (~5% of full context). This results in substantial cost reductions, including 67% fewer tokens than competing approaches and over 20x savings compared to full-context methods. These results show that effective memory in LLM agents depends on structured representations instead of larger context windows, enabling scalable and cost-efficient deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。