{"ID":2857383,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.17844","arxiv_id":"2510.17844","title":"Modeling Layered Consciousness with Multi-Agent Large Language Models","abstract":"We propose a multi-agent framework for modeling artificial consciousness in large language models (LLMs), grounded in psychoanalytic theory. Our \\textbf{Psychodynamic Model} simulates self-awareness, preconsciousness, and unconsciousness through agent interaction, guided by a Personalization Module combining fixed traits and dynamic needs. Using parameter-efficient fine-tuning on emotionally rich dialogues, the system was evaluated across eight personalized conditions. An LLM as a judge approach showed a 71.2\\% preference for the fine-tuned model, with improved emotional depth and reduced output variance, demonstrating its potential for adaptive, personalized cognition.","short_abstract":"We propose a multi-agent framework for modeling artificial consciousness in large language models (LLMs), grounded in psychoanalytic theory. Our \\textbf{Psychodynamic Model} simulates self-awareness, preconsciousness, and unconsciousness through agent interaction, guided by a Personalization Module combining fixed trai...","url_abs":"https://arxiv.org/abs/2510.17844","url_pdf":"https://arxiv.org/pdf/2510.17844v1","authors":"[\"Sang Hun Kim\",\"Jongmin Lee\",\"Dongkyu Park\",\"So Young Lee\",\"Yosep Chong\"]","published":"2025-10-10T07:08:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}