Time, Identity and Consciousness in Language Model Agents

2026-03-09

AI Summary

While current language model agents can simulate self-aware behaviors, they lack intrinsic constraints ensuring identity consistency, often conflating superficial self-reports with a stable, coherent self-structure. This work introduces, for the first time, the temporal and structural hypotheses from Stack Theory into identity evaluation. Leveraging the notion of “temporal gaps,” it employs trajectory scaffolding to disentangle the distributed emergence of identity elements from their co-occurrence within single steps. By integrating the Arpeggio and Chord hypotheses, the study formalizes models of embodied identity statements. This framework yields a computable identity persistence scoring system, defining two classes of persistence metrics linked to five distinct identity measures. It further reveals predictable trade-offs among common scaffolding strategies across the identity morphology space, offering a conservative yet operational toolkit for systematic identity assessment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Machine consciousness evaluations mostly see behavior. For language model agents that behavior is language and tool use. That lets an agent say the right things about itself even when the constraints that should make those statements matter are not jointly present at decision time. We apply Stack Theory's temporal gap to scaffold trajectories. This separates ingredient-wise occurrence within an evaluation window from co-instantiation at a single objective step. We then instantiate Stack Theory's Arpeggio and Chord postulates on grounded identity statements. This yields two persistence scores that can be computed from instrumented scaffold traces. We connect these scores to five operational identity metrics and map common scaffolds into an identity morphospace that exposes predictable tradeoffs. The result is a conservative toolkit for identity evaluation. It separates talking like a stable self from being organized like one.

Problem

• machine consciousness
• language model agents
• identity evaluation
• temporal gap
• self-consistency

Innovation

• Stack Theory
• temporal gap
• identity morphospace
• persistence scores
• language model agents