Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915931222966272 |
|---|---|
| author | Menon, Prahlad G. |
| author_facet | Menon, Prahlad G. |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09588 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity Menon, Prahlad G. Artificial Intelligence Emerging Technologies Machine Learning I.2.7; H.3.3 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 |
| title | Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity |
| topic | Artificial Intelligence Emerging Technologies Machine Learning I.2.7; H.3.3 |
| url | https://arxiv.org/abs/2604.09588 |