mlsanityData to 14 Oct 2026

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

arXiv 2507.04105 ↗First posted 5 Jul 2025cs.AI cs.MAcited by 9

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

14 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systems3 Feb
  2. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?28 Feb
  3. 2023Multi-Agent Consensus Seeking via Large Language Models31 Oct

Other references · 11

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  3. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 113
  4. 2024Safeguarding Large Language Models: A Surveycited by 78
  5. 2024Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitionscited by 26
  6. 2024Advancing the Robustness of Large Language Models through Self-Denoised Smoothingcited by 16
  7. 2022Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planningcited by 13
  8. 2024Trust-Oriented Adaptive Guardrails for Large Language Modelscited by 8
  9. 2024Generative AI Agents in Autonomous Machines: A Safety Perspectivecited by 7
  10. 2025TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Modelscited by 3
  11. 2019Reasoning about Cognitive Trust in Stochastic Multiagent Systemscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025A Survey on Agentic Security: Applications, Threats and Defensescited by 20
  2. 2025Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environmentscited by 9
  3. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  4. 2025Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Modelscited by 3
  5. 2026Responsible Agentic AI Requires Explicit Provenancecited by 3
  6. 2025Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Modelscited by 2
  7. 2026SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplacescited by 2
  8. 2026Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Modelscited by 1
  9. 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systemscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
  2. 2025Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
  3. 2026SGTO-MAS: Secure Gorilla Troops Optimization for Multi-Agent LLM Systems
  4. 2025Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering
  5. 2026When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
  6. 2026PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems
  7. 2025An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring
  8. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions