让AI Agent像人一样保持自我连续性，不怕记忆丢失。
Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity
- 用多个独立记忆模块分散存储身份信息，避免单点崩溃。
- 通过智能路由机制实现高效检索，兼顾全面与速度。
- 适合需要长期记忆的对话、陪伴类AI系统开发者使用。
现代AI代理存在根本性的身份困境：当上下文窗口溢出或对话历史被总结时，代理会遭遇灾难性遗忘——不仅丢失信息，更丧失自我连续性。这一技术局限反映了深层架构缺陷：AI代理的身份集中于单一记忆存储，形成单点故障。借鉴人类记忆障碍的神经学案例，我们发现人类身份能在损伤后维持，因其分布于情景记忆、程序性记忆、情感连续性和具身知识等多个系统中。本文提出soul.py开源架构，通过可分离的身份文件与记忆日志实现持久身份，并拓展多锚点韧性机制。框架引入混合RAG+RLM检索系统，自动将查询路由至合适的记忆访问模式，在不牺牲全面性的情况下实现高效检索。我们形式化了AI系统的身份锚点概念，并提出了构建能抵御部分记忆失效的代理的路线图。代码已开源于github.com/menonpg/soul.py。
原文摘要 · Abstract (English)
Modern AI agents suffer from a fundamental identity problem: when context windows overflow and conversation histories are summarized, agents experience catastrophic forgetting -- losing not just information, but continuity of self. This technical limitation reflects a deeper architectural flaw: AI agent identity is centralized in a single memory store, creating a single point of failure. Drawing on neurological case studies of human memory disorders, we observe that human identity survives damage because it is distributed across multiple systems: episodic memory, procedural memory, emotional continuity, and embodied knowledge. We present soul.py, an open-source architecture that implements persistent identity through separable components (identity files and memory logs), and propose extensions toward multi-anchor resilience. The framework introduces a hybrid RAG+RLM retrieval system that automatically routes queries to appropriate memory access patterns, achieving efficient retrieval without sacrificing comprehensiveness. We formalize the notion of identity anchors for AI systems and present a roadmap for building agents whose identity can survive partial memory failures. Code is available at github.com/menonpg/soul.py
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。