# How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations

## TL;DR

This study explores how the anchoring cognitive bias influences large language models during price negotiations, revealing that LLMs are affected similarly to humans and that reasoning capabilities can mitigate this bias.

## Contribution

It provides the first systematic analysis of the anchoring effect in LLMs and shows how reasoning models reduce susceptibility to this bias.

## Key findings

- LLMs are influenced by the anchoring effect like humans.
- Reasoning models are less prone to the anchoring effect.
- No significant correlation between personality traits and bias susceptibility.

## Abstract

Cognitive biases, well-studied in humans, can also be observed in LLMs, affecting their reliability in real-world applications. This paper investigates the anchoring effect in LLM-driven price negotiations. To this end, we instructed seller LLM agents to apply the anchoring effect and evaluated negotiations using not only an objective metric but also a subjective metric. Experimental results show that LLMs are influenced by the anchoring effect like humans. Additionally, we investigated the relationship between the anchoring effect and factors such as reasoning and personality. It was shown that reasoning models are less prone to the anchoring effect, suggesting that the long chain of thought mitigates the effect. However, we found no significant correlation between personality traits and susceptibility to the anchoring effect. These findings contribute to a deeper understanding of cognitive biases in LLMs and to the realization of safe and responsible application of LLMs in society.