mlsanityData to 7 Oct 2026

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

arXiv 2510.24831 ↗First posted 28 Oct 2025cs.CY cs.AI cs.HCcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 57 of its 134 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

57 of 134 references.

References · 57

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  9. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  10. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  11. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  12. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
38 more
  1. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  2. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  3. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  4. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  5. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  6. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  7. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  8. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 405
  9. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  10. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 343
  11. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  12. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
  13. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  14. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138
  15. 2023Generative Language Models Exhibit Social Identity Biasescited by 107
  16. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  17. 2024Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?cited by 85
  18. 2024Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approachcited by 73
  19. 2024On Limitations of the Transformer Architecturecited by 63
  20. 2025M+: Extending MemoryLLM with Scalable Long-Term Memorycited by 51
  21. 2025Learning without training: The implicit dynamics of in-context learningcited by 41
  22. 2025SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signalscited by 29
  23. 2023Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answeringcited by 28
  24. 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?cited by 27
  25. 2024InfiniPot: Infinite Context Processing on Memory-Constrained LLMscited by 27
  26. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  27. 2024Examining Identity Drift in Conversations of LLM Agentscited by 25
  28. 2023FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledgecited by 24
  29. 2025Drift No More? Context Equilibria in Multi-Turn LLM Interactionscited by 21
  30. 2025Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Modelscited by 19
  31. 2024Know When To Stop: A Study of Semantic Drift in Text Generationcited by 18
  32. 2024On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Conceptcited by 16
  33. 2025An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainabilitycited by 15
  34. 2014The Lovelace 2.0 Test of Artificial Creativity and Intelligencecited by 13
  35. 2023On the Intersection of Self-Correction and Trust in Language Modelscited by 12
  36. 2024ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coveragecited by 12
  37. 2025RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledgecited by 10
  38. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026ATANT: An Evaluation Framework for AI Continuitycited by 3
  2. 2026CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboardingcited by 3
  3. 2026Understanding Cognition-Induced Risks in Agentic AI Systemscited by 0