REVIEW 6 cited by
The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents
read the original abstract
Large language models (LLMs) excel in both closed tasks (including problem-solving, and code generation) and open tasks (including creative writing), yet existing explanations for their capabilities lack connections to real-world human intelligence. To fill this gap, this paper systematically investigates LLM intelligence through the lens of ``human simulation'', addressing three core questions: (1) \textit{How do personality traits affect problem-solving in closed tasks?} (2) \textit{How do traits shape creativity in open tasks?} (3) \textit{How does single-agent performance influence multi-agent collaboration?} By assigning Big Five personality traits to LLM agents and evaluating their performance in single- and multi-agent settings, we reveal that specific traits significantly influence reasoning accuracy (closed tasks) and creative output (open tasks). Furthermore, multi-agent systems exhibit collective intelligence distinct from individual capabilities, driven by distinguishing combinations of personalities.
Forward citations
Cited by 6 Pith papers
-
Agents with Feelings? Personality and Emotion in Multi-Agent Software Teams
Personality and emotion profiles substantially change multi-agent LLM team pass rates, review scores, revision behavior, and token cost on code generation and code review, with mixed profiles often beating shared ones.
-
When Does Personality Composition Matter for Multi-Agent LLM Teams?
Low agreeableness massively shifts multi-agent LLM communication yet barely hurts coding milestones, while the same prompt sharply degrades research milestones and collapses bargaining agreements.
-
Multi-agent AI systems outperform human teams in creativity
Multi-agent LLM teams outperform human teams in creativity (d=1.50) across tasks by producing more novel ideas, with distinct semantic exploration patterns predicting success for each group.
-
The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
Sycophancy is persona-conditional: a strongly-aligned model stays within 5pp across personas while a lightly-aligned one spans 45pp, so persona safety requires per-model auditing.
-
When Does Personality Composition Matter for Multi-Agent LLM Teams?
Empirical study finds that personality composition in multi-agent LLM teams affects performance in a task-dependent manner, with minimal impact on coding milestones but substantial degradation in collaboration and bargaining.
-
Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies
In real human subjects, AI transparency impacts imperfectly cooperative interactions far more than personality traits, unlike simulations where both are comparably influential.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.