# Privacy-Enhancing Paradigms within Federated Multi-Agent Systems

arXiv: https://arxiv.org/abs/2503.08175 · HTML: https://mlsanity.com/paper/2503.08175/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects](https://mlsanity.com/paper/2401.03428/) (2024)
- [MMedAgent: Learning to Use Medical Tools with Multi-modal Agent](https://mlsanity.com/paper/2407.02483/) (2024)
- [Guardrail Baselines for Unlearning in LLMs](https://mlsanity.com/paper/2403.03329/) (2024)
- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)
- [Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models](https://mlsanity.com/paper/2305.09955/) (2023)
- [Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System](https://mlsanity.com/paper/2312.04854/) (2023)
- [Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters](https://mlsanity.com/paper/2201.12467/) (2022)
- [A Privacy-Preserving and Trustable Multi-agent Learning Framework](https://mlsanity.com/paper/2106.01242/) (2021)
- [Differential Privacy in Cooperative Multiagent Planning](https://mlsanity.com/paper/2301.08811/) (2023)
- [Dynamics-Based Algorithm-Level Privacy Preservation for Push-Sum Average Consensus](https://mlsanity.com/paper/2304.08018/) (2023)

## Built on by (most cited first, 7 of 7)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2504.00587/) (2025)
- [PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training](https://mlsanity.com/paper/2602.13840/) (2026)
- [Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks](https://mlsanity.com/paper/2603.21654/) (2026)
- [SRPG: Semantically Reconstructed Privacy Guard for Zero-Trust Privacy in Educational Multi-Agent Systems](https://mlsanity.com/paper/2512.03694/) (2025)
- [Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations](https://mlsanity.com/paper/2606.15335/) (2026)
- [PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?](https://mlsanity.com/paper/2610.19458/) (2026)

## Abstract (arXiv)

LLM-based Multi-Agent Systems (MAS) have proven highly effective in solving complex problems by integrating multiple agents, each performing different roles. However, in sensitive domains, they face emerging privacy protection challenges. In this paper, we introduce the concept of Federated MAS, highlighting the fundamental differences between Federated MAS and traditional FL. We then identify key challenges in developing Federated MAS, including: 1) heterogeneous privacy protocols among agents, 2) structural differences in multi-party conversations, and 3) dynamic conversational network structures. To address these challenges, we propose Embedded Privacy-Enhancing Agents (EPEAgent), an innovative solution that integrates seamlessly into the Retrieval-Augmented Generation (RAG) phase and the context retrieval stage. This solution minimizes data flows, ensuring that only task-relevant, agent-specific information is shared. Additionally, we design and generate a comprehensive dataset to evaluate the proposed paradigm. Extensive experiments demonstrate that EPEAgent effectively enhances privacy protection while maintaining strong system performance. The code will be availiable at https://github.com/ZitongShi/EPEAgent