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

• URL: http://arxiv.org/abs/2604.13103v1
• Date: Fri, 10 Apr 2026 13:49:49 GMT
• Title: Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review
• Abstract summary: Transformer-based large language models (LLMs) and multi-agent systems (MAS) are increasingly embedded across the software development lifecycle (SDLC)<n>We present a rapid review of recent work on fairness in MAS, emphasizing LLM-enabled settings and relevance to software engineering.
• Score: 3.0969191504482243
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report [3.5548623483904436]
  Gen AI powered by large language models (LLMs) has transformed the software development process.<n>Recent advances have shifted toward multi-agent systems (MAS) that orchestrate multiple-based agents.<n>This paper provides a comprehensive overview of the existing tools and frameworks for implementing MAS in software engineering.
  arXiv  Detail & Related papers  (2026-08-12T11:53:44Z)
• A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions [0.0]
  Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering.<n>This study consolidates secondary evidence on LLM-based CGTs, synthesizing the publication landscape, effects, scenarios, integration challenges, and future research directions.
  arXiv  Detail & Related papers  (2026-05-25T07:49:23Z)
• LLMs taking shortcuts in test generation: A study with SAP HANA and LevelDB [0.22940141855172033]
  Large Language Models (LLMs) have achieved impressive results on public benchmarks, often leading to claims of advanced reasoning.<n>This paper investigates behavior in automated test generation for software memorization, contrasting performance on an open-source system.<n>Results show that LLMs excel on familiar, open-source benchmarks but struggle with unseen, complex, often prioritizing compilability over effectiveness.
  arXiv  Detail & Related papers  (2026-04-15T21:30:02Z)
• TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability [4.517933493143603]
  This paper introduces TraceLLM, a framework for enhancing requirements traceability through prompt engineering and demonstration selection.<n>We assess prompt generalization and robustness using eight state-of-the-art LLMs on four benchmark datasets.
  arXiv  Detail & Related papers  (2026-02-01T14:29:13Z)
• Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering [19.584762693453893]
  BEHELM is a holistic benchmarking infrastructure that unifies software-scenario specification with multi-metric evaluation.<n>Our goal is to reduce the overhead currently required to construct benchmarks while enabling a fair, realistic, and future-proof assessment of LLMs in software engineering.
  arXiv  Detail & Related papers  (2026-01-28T21:55:10Z)
• A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigms [20.241519889633285]
  Large Language Models (LLMs) are increasingly deployed as reasoning systems, where reasoning paradigms play a critical role.<n>We conduct a comprehensive and unified evaluation of reasoning paradigms, spanning direct single-model generation, CoT-augmented single-model reasoning, and representative MAS.<n>We introduce MIMeBench, a new open-ended benchmark that targets two foundational yet underexplored semantic capabilities.
  arXiv  Detail & Related papers  (2026-01-19T17:23:45Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System [56.40989626804489]
  This survey provides the first holistic analysis of Large Language Models-powered software engineering.<n>We review over 150 recent papers and propose a taxonomy along two key dimensions: (1) Solutions, categorized into prompt-based, fine-tuning-based, and agent-based paradigms, and (2) Benchmarks, including tasks such as code generation, translation, and repair.
  arXiv  Detail & Related papers  (2025-10-10T06:56:50Z)
• MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers [86.00932417210477]
  We introduce MCP-Universe, the first comprehensive benchmark specifically designed to evaluate LLMs in realistic and hard tasks through interaction with real-world MCP servers.<n>Our benchmark encompasses 6 core domains spanning 11 different MCP servers: Location Navigation, Repository Management, Financial Analysis, 3D Design, Browser Automation, and Web Searching.<n>We find that even SOTA models such as GPT-5 (43.72%), Grok-4 (33.33%) and Claude-4.0-Sonnet (29.44%) exhibit significant performance limitations.
  arXiv  Detail & Related papers  (2025-08-20T13:28:58Z)
• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics [82.0813150432867]
  We introduce OpenUnlearning, a standardized framework for benchmarking large language models (LLMs) unlearning methods and metrics.<n>OpenUnlearning integrates 13 unlearning algorithms and 16 diverse evaluations across 3 leading benchmarks.<n>We also benchmark diverse unlearning methods and provide a comparative analysis against an extensive evaluation suite.
  arXiv  Detail & Related papers  (2025-06-14T20:16:37Z)
• MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered [2.8692611791027893]
  We present MALIBU, a novel benchmark developed to assess the degree to which multi-agent systems implicitly reinforce social biases and stereotypes.<n>Our study quantifies biases in LLM-generated outputs, revealing that bias mitigation may favor marginalized personas over true neutrality.
  arXiv  Detail & Related papers  (2025-04-10T19:16:40Z)
• The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? [54.18519360412294]
  Large Language Models (LLMs) must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility.<n>This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance.<n>We analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model.
  arXiv  Detail & Related papers  (2025-01-20T06:35:01Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.