The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems

TL;DR

The paper proposes the Narrative Continuity Test (NCT), a framework for assessing whether AI systems maintain identity and coherence over time, highlighting current limitations and guiding future architectural improvements.

Contribution

It introduces the NCT as a novel conceptual framework for evaluating identity persistence in AI, shifting focus from task performance to diachronic coherence.

Findings

Current architectures fail to support persistence axes

Case studies reveal predictable continuity failures

NCT guides future AI design for long-term coherence

Abstract

Artificial intelligence systems based on large language models (LLMs) can now generate coherent text, music, and images, yet they operate without a persistent state: each inference reconstructs context from scratch. This paper introduces the Narrative Continuity Test (NCT) -- a conceptual framework for evaluating identity persistence and diachronic coherence in AI systems. Unlike capability benchmarks that assess task performance, the NCT examines whether an LLM remains the same interlocutor across time and interaction gaps. The framework defines five necessary axes -- Situated Memory, Goal Persistence, Autonomous Self-Correction, Stylistic & Semantic Stability, and Persona/Role Continuity -- and explains why current architectures systematically fail to support them. Case analyses (Character.\,AI, Grok, Replit, Air Canada) show predictable continuity failures under stateless inference. The NCT reframes AI evaluation from performance to persistence, outlining conceptual requirements for future benchmarks and architectural designs that could sustain long-term identity and goal coherence in generative models.