# FAIRTOPIA: Envisioning Multi-Agent Guardianship for Disrupting Unfair AI Pipelines

arXiv: https://arxiv.org/abs/2506.09107 · HTML: https://mlsanity.com/paper/2506.09107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 30 of 31)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization](https://mlsanity.com/paper/2402.17574/) (2024)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?](https://mlsanity.com/paper/2502.15657/) (2025)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [A Comprehensive Survey on Automatic Knowledge Graph Construction](https://mlsanity.com/paper/2302.05019/) (2023)
- [Making Large Language Models Perform Better in Knowledge Graph Completion](https://mlsanity.com/paper/2310.06671/) (2023)
- [Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces](https://mlsanity.com/paper/2211.03536/) (2022)
- [FairRAG: Fair Human Generation via Fair Retrieval Augmentation](https://mlsanity.com/paper/2403.19964/) (2024)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms](https://mlsanity.com/paper/2407.01294/) (2024)
- [Symphony: Composing Interactive Interfaces for Machine Learning](https://mlsanity.com/paper/2202.08946/) (2022)
- [The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice](https://mlsanity.com/paper/2302.06347/) (2023)
- [From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs](https://mlsanity.com/paper/2407.04434/) (2024)
- [Fair Enough: Searching for Sufficient Measures of Fairness](https://mlsanity.com/paper/2110.13029/) (2021)
- [GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding](https://mlsanity.com/paper/2402.06764/) (2024)
- [A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge](https://mlsanity.com/paper/2402.17081/) (2024)
- [Comprehensible Artificial Intelligence on Knowledge Graphs: A survey](https://mlsanity.com/paper/2404.03499/) (2024)
- [AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems](https://mlsanity.com/paper/2402.06287/) (2024)
- [Responsible Artificial Intelligence -- from Principles to Practice](https://mlsanity.com/paper/2205.10785/) (2022)
- [The State of Algorithmic Fairness in Mobile Human-Computer Interaction](https://mlsanity.com/paper/2307.12075/) (2023)
- [Uncovering Bias in Personal Informatics](https://mlsanity.com/paper/2303.15592/) (2023)

## Abstract (arXiv)

AI models have become active decision makers, often acting without human supervision. The rapid advancement of AI technology has already caused harmful incidents that have hurt individuals and societies and AI unfairness in heavily criticized. It is urgent to disrupt AI pipelines which largely neglect human principles and focus on computational biases exploration at the data (pre), model(in), and deployment (post) processing stages. We claim that by exploiting the advances of agents technology, we will introduce cautious, prompt, and ongoing fairness watch schemes, under realistic, systematic, and human-centric fairness expectations. We envision agents as fairness guardians, since agents learn from their environment, adapt to new information, and solve complex problems by interacting with external tools and other systems. To set the proper fairness guardrails in the overall AI pipeline, we introduce a fairness-by-design approach which embeds multi-role agents in an end-to-end (human to AI) synergetic scheme. Our position is that we may design adaptive and realistic AI fairness frameworks, and we introduce a generalized algorithm which can be customized to the requirements and goals of each AI decision making scenario. Our proposed, so called FAIRTOPIA framework, is structured over a three-layered architecture, which encapsulates the AI pipeline inside an agentic guardian and a knowledge-based, self-refining layered scheme. Based on our proposition, we enact fairness watch in all of the AI pipeline stages, under robust multi-agent workflows, which will inspire new fairness research hypothesis, heuristics, and methods grounded in human-centric, systematic, interdisciplinary, socio-technical principles.