让对话智能体记住过往，实现持续个性化对话
Cognis: Context-Aware Memory for Conversational AI Agents
- 双存储架构融合关键词与向量搜索，用倒数排名融合提升召回精度
- 在两个基准测试中表现领先，支持8种生成模型，保持记忆一致性
- 适合需要长期记忆的对话系统开发者，开源且已投入生产
大型语言模型代理缺乏持久记忆，导致每次会话重置，无法实现长期个性化。我们提出 Lyzr Cognis，一种统一的记忆架构，通过多阶段检索流程解决此问题。Cognis 结合 OpenSearch BM25 关键词匹配与 Matryoshka 向量相似性搜索，采用倒数排名融合（Reciprocal Rank Fusion）进行结果整合。其上下文感知的摄入管道在提取前检索已有记忆，实现智能版本追踪，在保留完整记忆历史的同时维持存储一致性。时间增强机制提升时效性查询效果，BGE-2 跨编码器重排序器优化最终结果质量。我们在两个独立基准（LoCoMo 与 LongMemEval）上，针对八种答案生成模型进行评估，均达到当前最优性能。该系统开源并已部署于生产环境，服务于实际对话型 AI 应用。
原文摘要 · Abstract (English)
LLM agents lack persistent memory, causing conversations to reset each session and preventing personalization over time. We present Lyzr Cognis, a unified memory architecture for conversational AI agents that addresses this limitation through a multi-stage retrieval pipeline. Cognis combines a dual-store backend pairing OpenSearch BM25 keyword matching with Matryoshka vector similarity search, fused via Reciprocal Rank Fusion. Its context-aware ingestion pipeline retrieves existing memories before extraction, enabling intelligent version tracking that preserves full memory history while keeping the store consistent. Temporal boosting enhances time-sensitive queries, and a BGE-2 cross-encoder reranker refines final result quality. We evaluate Cognis on two independent benchmarks -- LoCoMo and LongMemEval -- across eight answer generation models, demonstrating state-of-the-art performance on both. The system is open-source and deployed in production serving conversational AI applications.
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。