Lune

EMNLP Findings2025

When Allies Turn Foes: Exploring Group Characteristics of LLM-Based Multi-Agent Collaborative Systems Under Adversarial Attacks

Jiahao Zhang, Baoshuo Kan, Tao Gong, Fu Lee Wang, Tianyong Hao

Abstract

This paper investigates the group characteristics in multi-agent collaborative systems under adversarial attacks. Adversarial agents are tasked with generating counterfactual answers to a given collaborative problem, while collaborative agents normally interact with other agents to solve the given problem. To simulate real-world collaboration scenarios as closely as possible, we evaluate the collaborative system in three different collaboration scenarios and design three different communication strategies and different group structures. Furthermore, we explored several methods to mitigate adversarial attacks, all of which have been proven effective through our experiments. To quantify the robustness of collaborative systems against such attacks, a novel metric, System Defense Index (SDI), is introduced. Finally, we conducted an in-depth analysis from the perspective of group dynamics on how adversarial agents affect multi-agent collaborative systems, which reveals similarities between the agent collaboration process and human collaboration process. Our code can be found here 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Generative Agents: Interactive Simulacra of Human Behavior cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Improving Factuality and Reasoning in Language Models through Multiagent Debate cites Measuring Massive Multitask Language Understanding
  • Improving Factuality and Reasoning in Language Models through Multiagent Debate cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on23

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  3. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
  4. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  5. Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations

Related papers

  1. MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via DebateAlfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua et al.EMNLP Findings 2024 · 15 citations
  2. Can an Individual Manipulate the Collective Decisions of Multi-Agents?Fengyuan Liu, Rui Zhao, Shuo Chen, Guohao Li et al.EMNLP 2025
  3. Architecture Matters for Multi-Agent SecurityBen Hagag, William Anderson, Christian Schroeder de Witt, Sarah SchefflerICML 2026 · 1 citation
  4. Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement LearningSunwoo Lee, Jaebak Hwang, Yonghyeon Jo, Seungyul HanICML 2025
  5. Towards Interpreting and Utilizing Symmetry Property in Adversarial ExamplesShibin Mei, Chenglong Zhao, Bingbing Ni, Shengchao YuanAAAI 2023 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines