MAAICLJan 5, 2024

AFSPP: Agent Framework for Shaping Preference and Personality with Large Language Models

arXiv:2401.02870v16 citationsh-index: 1
Originality Incremental advance
AI Analysis

This work addresses the need for more realistic and dynamic agent behavior in sociological and psychological research, offering incremental improvements by integrating iterative development and environmental influences into existing LLM-based agent frameworks.

The paper tackles the problem of emulating human-like preference and personality development in LLM-based agents by proposing AFSPP, a framework that incorporates social networks and subjective consciousness, successfully replicating key human personality experiments and identifying factors like plan making and social networking as influential in preference shaping.

The evolution of Large Language Models (LLMs) has introduced a new paradigm for investigating human behavior emulation. Recent research has employed LLM-based Agents to create a sociological research environment, in which agents exhibit behavior based on the unfiltered characteristics of large language models. However, these studies overlook the iterative development within a human-like setting - Human preferences and personalities are complex, shaped by various factors and subject to ongoing change as a result of environmental and subjective influences. In light of this observation, we propose Agent Framework for Shaping Preference and Personality (AFSPP), exploring the multifaceted impact of social networks and subjective consciousness on LLM-based Agents' preference and personality formation. With AFSPP, we have, for the first time, successfully replicated several key findings from human personality experiments. And other AFSPP-based experimental results indicate that plan making, sensory perceptions and social networking with subjective information, wield the most pronounced influence on preference shaping. AFSPP can significantly enhance the efficiency and scope of psychological experiments, while yielding valuable insights for Trustworthy Artificial Intelligence research for strategies to prevent undesirable preference and personality development.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes