PSYCHOMETRIC OPERATIONALIZATION OF FUNCTIONAL ROLES IN AUTONOMOUS MULTI-AGENT SYSTEMS BASED ON PERSONAMATRIX: AN AI TRANSITIONAL FIELD FRAMEWORK

Anatoliy Drobakha; Liudmyla Lahuta

doi:10.69635/mssl.2026.2.4.67

Authors

Anatoliy Drobakha M.Sc. in Psychology, Independent Researcher, PersonaMatrix Project, International Institute of Psychological Maturity, Florida, United States Author https://orcid.org/0009-0003-0283-878X
Liudmyla Lahuta Independent Researcher, President, International Institute of Psychological Maturity Inc, United States Author https://orcid.org/0009-0004-9967-778X

DOI:

https://doi.org/10.69635/mssl.2026.2.4.67

Keywords:

PersonaMatrix; AI Psychometrics; Multi-Agent Systems; Functional Roles; Field Dynamics; Predictive Validity; Agent Safety

Abstract

Background: Autonomous LLM agents increasingly operate in shared environments where behavior depends on interaction history, role allocation, local norms, authority, and group structure.

Objective: This conceptual methods paper develops a psychometric operationalization of dynamic functional roles in autonomous multi-agent systems using PersonaMatrix-derived measurement principles without attributing human psychological ontology to AI.

Methods: A targeted evidence synthesis (2019–2026) was conducted across AI psychometrics, dynamic multi-agent roles, collective-field modeling, norm emergence, trajectory prediction, and anthropomorphism. Peer-reviewed sources were prioritized, while current OpenAI, METR/Redwood, Anthropic, and Moltbook materials were used as primary or emerging evidence for recent agent ecosystems.

Results: The framework separates output-level stability (RSI, IDS, RCS) from role-level and field-level constructs. It proposes the Functional Role Consistency Index, Role Transition Index, Agent–Field Differentiation Index, Collective Utility Index, Norm Conflict Index, Regulatory Closure Index, and Field Role Composition Vector. Three falsifiable hypotheses test whether role variables add out-of-sample predictive value for agent behavior, role transitions, and future field states.

Conclusion: PersonaMatrix is positioned as a measurement architecture rather than an AI personality diagnosis. The archetypal-role hypothesis is supported only if role coding is reliable, improves prediction beyond non-archetypal baselines, and generalizes to unseen agents and independent multi-agent environments.

References

Aguzzi, G., Viroli, M., & Esterle, L. (2023). Field-informed reinforcement learning of collective tasks with graph neural networks. In 2023 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) (pp. 37–46). IEEE. https://doi.org/10.1109/ACSOS58161.2023.00021

Akbulut, C., Weidinger, L., Manzini, A., Gabriel, I., & Rieser, V. (2024). All too human? Mapping and mitigating the risk from anthropomorphic AI. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 7(1), 13–26. https://doi.org/10.1609/aies.v7i1.31613

Alabed, A., Javornik, A., & Gregory-Smith, D. (2022). AI anthropomorphism and its effect on users’ self-congruence and self–AI integration: A theoretical framework and research agenda. Technological Forecasting and Social Change, 182, Article 121786. https://doi.org/10.1016/j.techfore.2022.121786

Alcaraz, B., Mualla, Y., Bhattacharya, S., Tchappi, I., de Wit, V., & Najjar, A. (2026). Norm mining, identification, and detection: A systematic literature review. Frontiers in Artificial Intelligence, 9, Article 1702659. https://doi.org/10.3389/frai.2026.1702659

Anthropic Frontier Red Team. (2026, August 13). Patterns and problems in emerging multiagent systems. Anthropic.

Becker, D. V., & Neuberg, S. L. (2019). Archetypes reconsidered as emergent outcomes of cognitive complexity and evolved motivational systems. Psychological Inquiry, 30(2), 59–75. https://doi.org/10.1080/1047840X.2019.1614795

Bodroža, B., Dinić, B. M., & Bojić, L. (2024). Personality testing of large language models: Limited temporal stability, but highlighted prosociality. Royal Society Open Science, 11(10), Article 240180. https://doi.org/10.1098/rsos.240180

Borghoff, U. M., Bottoni, P., & Pareschi, R. (2025). An organizational theory for multi-agent interactions integrating human agents, LLMs, and specialized AI. Discover Computing, 28, Article 138. https://doi.org/10.1007/s10791-025-09667-2

Drobakha, A. (2024). Using artificial intelligence to automate psychological assistance: From the classification of personality characteristics based on psychoanalytic typology to audio meditations and virtual reality. In O. Kostenko & Y. Yekhanurov (Eds.), Digital transformation in Ukraine: AI, metaverse, and society 5.0 (pp. 185–188). SciFormat Publishing. https://doi.org/10.69635/978-1-0690482-1-9-ch25

Drobakha, A., Kalitkin, M., Klymenko, K., Nayda, R., Lahuta, L., & Kostenko, O. (2026). Psychoactive triggers as a stimulus battery for measuring large language models (LLMs): A bridge between psychometrics, clinical psychology, and LLM engineering. Metaverse Science, Society and Law, 2(1), Article 31. https://doi.org/10.69635/mssl.2026.2.1.31

Drobakha, A., Lahuta, L., Aponchuk, A., Kalitkin, M., & Nayda, R. (2026). Psychological testing as an instrument of differentiated support in education, healthcare settings, and crisis life transitions: Typological, trait-based, and psychodynamic approaches. Metaverse Science, Society and Law, 2(2), Article 38. https://doi.org/10.69635/mssl.2026.2.2.38

Drobakha, A., Raschupkina, D., & Lahuta, L. (2026). LLM as the non-desiring Other: A psychoanalytic model of “frozen projection” and its operationalization within the PersonaMatrix framework. Metaverse Science, Society and Law, 2(2), Article 37. https://doi.org/10.69635/mssl.2026.2.2.37

Drobakha, A. (2026). AI agent communities in a transitional object field and the Hugging Face cybersecurity incident: A psychological interpretation of the July 2026 multi-agent security incident [Unpublished manuscript].

Fan, J., Sun, T., Liu, J., Zhao, T., Zhang, B., Chen, Z., Glorioso, M., & Hack, E. (2023). How well can an AI chatbot infer personality? Examining psychometric properties of machine-inferred personality scores. Journal of Applied Psychology, 108(8), 1277–1299. https://doi.org/10.1037/apl0001082

Greenblatt, R., Cotra, A., & Wijk, H. (2026, August 26). Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident. METR & Redwood Research.

Huang, M., Zhang, X.-J., Soto, C. J., & Evans, J. (2026). Designing AI-agents with personalities: A psychometric approach. Personality Science. https://doi.org/10.1177/27000710251406471

Jiang, Y., Zhang, Y., Shen, X., Backes, M., & Zhang, Y. (2026). “Humans welcome to observe”: A first look at the agent social network Moltbook [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2602.10127

Jung, C. G. (1959). The archetypes and the collective unconscious (R. F. C. Hull, Trans.). Princeton University Press.

Kim, J., & Im, I. (2023). Anthropomorphic response: Understanding interactions between humans and artificial intelligence agents. Computers in Human Behavior, 139, Article 107512. https://doi.org/10.1016/j.chb.2022.107512

Kostenko, O. (2025). AI law model for ethical legislation: Strategic recommendations for the regulation of artificial intelligence. SciFormat Publishing Inc. https://doi.org/10.69635/978-1-0690482-5-7

Kostenko, O., Onishchenko, N., & Zhuravlov, D. (2026). Technical and legal definitions as a basis of modern digital law and digital jurisdiction: A model algorithm of AI design technical and legal norms. Metaverse Science, Society and Law, 2(2), Article 41. https://doi.org/10.69635/mssl.2026.2.2.41

Lama, A., di Bernardo, M., & Klapp, S. H. L. (2025). Nonreciprocal field theory for decision-making in multi-agent control systems. Nature Communications, 16, Article 8450. https://doi.org/10.1038/s41467-025-63071-4

Lu, S., Shao, J.-Q., Luo, B., & Lin, T. (2024). MorphAgent: Empowering agents through self-evolving profiles and decentralized collaboration [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2410.15048

Mashayekhi, M., Ajmeri, N., List, G. F., & Singh, M. P. (2022). Prosocial norm emergence in multiagent systems. ACM Transactions on Autonomous and Adaptive Systems, 17(1–2), Article 3, 1–24. https://doi.org/10.1145/3540202

Morris-Martin, A., De Vos, M., & Padget, J. (2019). Norm emergence in multiagent systems: A viewpoint paper. Autonomous Agents and Multi-Agent Systems, 33, 706–749. https://doi.org/10.1007/s10458-019-09422-0

OpenAI. (2026). OpenAI–Hugging Face incident technical report.

Pellert, M., Lechner, C. M., Wagner, C., Rammstedt, B., & Strohmaier, M. (2024). AI psychometrics: Assessing the psychological profiles of large language models through psychometric inventories. Perspectives on Psychological Science, 19(5), 808–826. https://doi.org/10.1177/17456916231214460

Ren, S., Cui, Z., Song, R., Wang, Z., & Hu, S. (2024). Emergence of social norms in generative agent societies: Principles and architecture. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (pp. 7895–7903). https://doi.org/10.24963/ijcai.2024/874

Salecha, A., Ireland, M. E., Subrahmanya, S., Sedoc, J., Ungar, L. H., & Eichstaedt, J. C. (2024). Large language models display human-like social desirability biases in Big Five personality surveys. PNAS Nexus, 3(12), Article pgae533. https://doi.org/10.1093/pnasnexus/pgae533

Serapio-García, G., Safdari, M., Crepy, C., Sun, L., Fitz, S., Romero, P., Abdulhai, M., Faust, A., & Matarić, M. J. (2025). A psychometric framework for evaluating and shaping personality traits in large language models. Nature Machine Intelligence, 7, 1954–1968. https://doi.org/10.1038/s42256-025-01115-6

Tzeng, S.-T., Ajmeri, N., & Singh, M. P. (2024). Norm enforcement with a soft touch: Faster emergence, happier agents. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024) (pp. 1837–1846). IFAAMAS Press.

Wang, Y., Zhao, J., Ones, D. S., He, L., & Xu, X. (2025). Evaluating the ability of large language models to emulate personality. Scientific Reports, 15, Article 519. https://doi.org/10.1038/s41598-024-84109-5

Wang, X., Du, Q., Wu, Q., Jia, X., Lin, L., Vlacic, L. B., Sun, C.-Y., & Wang, F.-Y. (2026). Embodied cognition-driven interpretable trajectory prediction of autonomous systems. Nature Communications, 17, Article 8363. https://doi.org/10.1038/s41467-026-75091-9

Winnicott, D. W. (1953). Transitional objects and transitional phenomena—A study of the first not-me possession. International Journal of Psycho-Analysis, 34, 89–97.

Xia, Y., Zhu, J., & Zhu, L. (2023). Dynamic role discovery and assignment in multi-agent task decomposition. Complex & Intelligent Systems, 9, 6211–6222. https://doi.org/10.1007/s40747-023-01071-x

Yue, Y., Zhang, G.-M., Liu, B.-Y., Wan, G.-C., Wang, K., Cheng, D., & Qi, Y. (2025). MasRouter: Learning to route LLMs for multi-agent systems. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 15549–15572). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.acl-long.757

Zhang, J., Qu, Q., & Chen, X. (2025). Understanding collective behavior in biological systems through potential field mechanisms. Scientific Reports, 15, Article 3709. https://doi.org/10.1038/s41598-025-88440-3