# Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing

arXiv: https://arxiv.org/abs/2507.04105 · HTML: https://mlsanity.com/paper/2507.04105/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 5 Jul 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Multi-Agent Consensus Seeking via Large Language Models](https://mlsanity.com/paper/2310.20151/) (2023)
- [Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions](https://mlsanity.com/paper/2410.00031/) (2024)
- [Advancing the Robustness of Large Language Models through Self-Denoised Smoothing](https://mlsanity.com/paper/2404.12274/) (2024)
- [Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning](https://mlsanity.com/paper/2206.02670/) (2022)
- [Trust-Oriented Adaptive Guardrails for Large Language Models](https://mlsanity.com/paper/2408.08959/) (2024)
- [Position: Towards a Responsible LLM-empowered Multi-Agent Systems](https://mlsanity.com/paper/2502.01714/) (2025)
- [Generative AI Agents in Autonomous Machines: A Safety Perspective](https://mlsanity.com/paper/2410.15489/) (2024)
- [TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models](https://mlsanity.com/paper/2503.10872/) (2025)
- [Reasoning about Cognitive Trust in Stochastic Multiagent Systems](https://mlsanity.com/paper/1905.06627/) (2019)

## Built on by (most cited first, 9 of 9)

- [A Survey on Agentic Security: Applications, Threats and Defenses](https://mlsanity.com/paper/2510.06445/) (2025)
- [Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments](https://mlsanity.com/paper/2508.11425/) (2025)
- [Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment](https://mlsanity.com/paper/2510.14008/) (2025)
- [Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models](https://mlsanity.com/paper/2508.01554/) (2025)
- [Responsible Agentic AI Requires Explicit Provenance](https://mlsanity.com/paper/2605.17169/) (2026)
- [Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models](https://mlsanity.com/paper/2512.21964/) (2025)
- [SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces](https://mlsanity.com/paper/2607.02345/) (2026)
- [Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models](https://mlsanity.com/paper/2605.01605/) (2026)
- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)

## Abstract (arXiv)

This paper presents a defense framework for enhancing the safety of large language model (LLM) empowered multi-agent systems (MAS) in safety-critical domains such as aerospace. We apply randomized smoothing, a statistical robustness certification technique, to the MAS consensus context, enabling probabilistic guarantees on agent decisions under adversarial influence. Unlike traditional verification methods, our approach operates in black-box settings and employs a two-stage adaptive sampling mechanism to balance robustness and computational efficiency. Simulation results demonstrate that our method effectively prevents the propagation of adversarial behaviors and hallucinations while maintaining consensus performance. This work provides a practical and scalable path toward safe deployment of LLM-based MAS in real-world, high-stakes environments.