The Agentic Digital Twin-Led Assessment System (ATLAS): A new architecture for psychological assessment in the era of agentic AI
Система оценки на основе агентных цифровых двойников (ATLAS): новая архитектура психологической оценки в эпоху агентного искусственного интеллекта
2026-07-09
SCID: 54.1/yq33ejw8
Discuss with AI
agentic AIdigital twinsprecision psychologypsychological assessmentswarm intelligence
Figures from the paper
Abstract (AI)
Psychological assessment has spent a century refining a single architecture. A person sits down, to complete an instrument designed for everyone, and receives a score positioned against a population mean. Each technological wave has improved this architecture without replacing it. But digital twins, agentic AI, and swarm intelligence now make it possible to specify a different assessment architecture: one in which the model of the person is built first, the assessment is generated on demand from that model, and evaluation preserves disagreement as diagnostic signal rather than averaging it away. This paper introduces the Agentic Digital Twin-Led Assessment System as a five-layer conceptual architecture coupled by a continuous feedback loop, with the AI-IARA framework functioning as a set of engineering-grade design constraints. This shifts psychology’s role from validating instruments after they are built to specifying assessment infrastructures that protect validity, and agency. ATLAS offers a conceptual architecture for precision psychology.
Key Findings
1
A continuous feedback loop couples the architecture’s five layers, with AI-IARA providing engineering-grade design constraints.
2
ATLAS proposes a five-layer conceptual architecture for psychological assessment built around an individual’s digital twin rather than standardized instruments.
3
ATLAS uses agentic AI and swarm intelligence while preserving disagreement as diagnostic information instead of averaging it away.
4
The architecture generates assessments on demand from the person model, enabling personalized rather than population-normed evaluation.
5
The framework repositions psychology toward designing assessment infrastructures that protect validity and individual agency, supporting precision psychology.
Research Object
the Agentic Digital Twin-Led Assessment System (ATLAS) architecture for psychological assessment
Research Subject
the architecture, feedback coupling, and validity-preserving assessment processes that model an individual first, generate assessments on demand, and retain disagreement as diagnostic information
Publication Details
Publication Date
2026-07-09
Journal
Publisher
ISSN
Cited by
2
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
Social Cognitive Theory: An Agentic Perspective2001
Algorithms at Work: The New Contested Terrain of Control2019
A survey on large language model based autonomous agents2024
Generative Agents: Interactive Simulacra of Human Behavior2023
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate2024
The critiques and criticisms of positive psychology: a systematic review2023
The AI-IARA framework: How to cultivate human agency before artificial intelligence optimizes it a(ny)way2026