How Personality Traits Influence Negotiation Outcomes? A Simulation based on Large Language Models

TL;DR

A simulation framework centered on Large Language Model agents endowed with synthesized personality traits that investigates the alignment between the linguistic and economic capabilities of LLM agents and offers empirical insights into the strategic impact of Big-Five personality traits on the outcomes of bilateral negotiations.

Abstract

Psychological evidence reveals the influence of personality traits on decision-making. For instance, agreeableness is generally associated with positive outcomes in negotiations, whereas neuroticism is often linked to less favorable outcomes. This paper introduces a simulation framework centered on Large Language Model (LLM) agents endowed with synthesized personality traits. The agents negotiate within bargaining domains and possess customizable personalities and objectives. The experimental results show that the behavioral tendencies of LLM-based simulations could reproduce behavioral patterns observed in human negotiations. The contribution is twofold. First, we propose a simulation methodology that investigates the alignment between the linguistic and economic capabilities of LLM agents. Secondly, we offer empirical insights into the strategic impact of Big-Five personality traits on the outcomes of bilateral negotiations. We also provide a case study based on synthesized bargaining dialogues to reveal intriguing behaviors, including deceitful and compromising behaviors.

Figures (5)

• Figure 1: Overview of the LLM-based negotiation simulation framework.
• Figure 2: (Left) Positive and negative relationships between personality traits and strategies. Darker cells indicate higher statistical significance. (Right) Impact of strategies on the joint utility of the agreement price $p_{deal}$. Labels on the $y$ axes list the most common strategies among agents, occurring more than $20$ times within the entire negotiations.
• Figure 3: (Left) Relationship between personality traits and strategies. Darker cells indicate higher statistical significance. (Right) Impact of strategies on intrinsic utility gains. Labels on the $y$ axes list the most common strategies, occurring more than $20$ times within the entire negotiations.
• Figure 4: The relations between the product prices and the number of negotiation rounds (Left) and the number of words (Right). The product prices are in log scale.
• Figure 5: IPIP Personality test results of different personality levels.