Once Upon a Team: Investigating Bias in LLM-Driven Software Team Composition and Task Allocation

2026-01-07

arXiv.org

AI Summary

This study investigates how large language models (LLMs) may introduce systematic biases in socially sensitive software engineering decisions, such as team formation and task assignment. It presents the first joint analysis of the interactive effects of multiple demographic attributes—including nationality and pronouns—on LLM-driven recommendations. Through 3,000 controlled simulation trials and quantitative bias assessments, the fairness of three leading LLMs is evaluated in assigning technical and leadership roles. Findings reveal that even when professional competence is held constant, demographic attributes significantly influence both selection likelihood and role type, exposing implicit stereotypes that risk exacerbating group-based inequities in software development. These results provide empirical grounding for designing more equitable AI systems in collaborative engineering contexts.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Humans and AI: Teamwork, Team formation
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

LLMs are increasingly used to boost productivity and support software engineering tasks. However, when applied to socially sensitive decisions such as team composition and task allocation, they raise concerns of fairness. Prior studies have revealed that LLMs may reproduce stereotypes; however, these analyses remain exploratory and examine sensitive attributes in isolation. This study investigates whether LLMs exhibit bias in team composition and task assignment by analyzing the combined effects of candidates'country and pronouns. Using three LLMs and 3,000 simulated decisions, we find systematic disparities: demographic attributes significantly shaped both selection likelihood and task allocation, even when accounting for expertise-related factors. Task distributions further reflected stereotypes, with technical and leadership roles unevenly assigned across groups. Our findings indicate that LLMs exacerbate demographic inequities in software engineering contexts, underscoring the need for fairness-aware assessment.

Problem

• bias
• LLM
• team composition
• task allocation
• fairness

Innovation

• bias in LLMs
• team composition
• task allocation
• fairness-aware AI
• demographic disparities