Modeling Layered Consciousness with Multi-Agent Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914104908709888 |
|---|---|
| author | Kim, Sang Hun Lee, Jongmin Park, Dongkyu Lee, So Young Chong, Yosep |
| author_facet | Kim, Sang Hun Lee, Jongmin Park, Dongkyu Lee, So Young Chong, Yosep |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17844 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modeling Layered Consciousness with Multi-Agent Large Language Models Kim, Sang Hun Lee, Jongmin Park, Dongkyu Lee, So Young Chong, Yosep Computation and Language Artificial Intelligence Multiagent Systems 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. |
| title | Modeling Layered Consciousness with Multi-Agent Large Language Models |
| topic | Computation and Language Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2510.17844 |