Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review

TL;DR

This rapid review examines fairness issues in multi-agent systems and large language models within software engineering, highlighting gaps in evaluation, generalization, and mitigation strategies affecting deployment.

Contribution

It provides a systematic analysis of recent fairness research in MAS for SDLC, identifying key gaps and proposing directions for future work.

Findings

Fairness is linked to trustworthy AI, bias reduction, and interactional dynamics.

Evaluation practices are fragmented and rarely MAS-specific.

Current research has limited generalization and weak mitigation mechanisms.

Abstract

Transformer-based large language models (LLMs) and multi-agent systems (MAS) are increasingly embedded across the software development lifecycle (SDLC), yet their fairness implications for developer-facing tools remain underexplored despite their growing role in shaping what code is written, reviewed, and released. We present a rapid review of recent work on fairness in MAS, emphasizing LLM-enabled settings and relevance to software engineering. Starting from an initial set of 350 papers, we screened and filtered the corpus for relevance, retaining 18 studies for final analysis. Across these 18 studies, fairness is framed as a combination of trustworthy AI principles, bias reduction across groups, and interactional dynamics in collectives, while evaluation spans accuracy metrics on bias benchmarks, demographic disparity measures, and emergent MAS-specific notions such as conformity and bias amplification. Reported harms include representational, quality-of-service, security and privacy, and governance failures, which we relate to SDLC stages where evidence is most and least developed. We identify three persistent gaps: (1) fragmented, rarely MAS-specific evaluation practices that limit comparability, (2) limited generalization due to simplified environments and narrow attribute coverage, and (3) scarce, weakly evaluated mitigation and governance mechanisms aligned to real software workflows. These findings suggest MAS fairness research is not yet ready to support deployable, fairness-assured software systems, motivating MAS-aware benchmarks, consistent protocols, and lifecycle-spanning governance.