When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ren, Qibing, Xie, Sitao, Wei, Longxuan, Yin, Zhenfei, Yan, Junchi, Ma, Lizhuang, Shao, Jing
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
by: Ren, Qibing, et al.
Published: (2025)

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
by: Ren, Qibing, et al.
Published: (2024)

TodoEvolve: Learning to Architect Agent Planning Systems
by: Liu, Jiaxi, et al.
Published: (2026)

LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
by: Ren, Qibing, et al.
Published: (2024)

When the Pacemaker Goes Rogue: Pacemaker‐Induced Tachycardia, Syncope, and Car Crash
by: Hanna Grogg, et al.
Published: (2026)

MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
by: Ye, Rui, et al.
Published: (2025)

StepShield: When, Not Whether to Intervene on Rogue Agents
by: Felicia, Gloria, et al.
Published: (2026)

INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
by: Zhou, Yijin, et al.
Published: (2026)

Preventing Rogue Agents Improves Multi-Agent Collaboration
by: Barbi, Ohav, et al.
Published: (2025)

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
by: Nakamura, Mason, et al.
Published: (2026)

When Fat Goes Astray: Your Liver and Pancreas Get Into Trouble
by: Yuying Chen, et al.
Published: (2026)

When Criticism Goes to War
by: Milutinovic, Zoran
Published: (2025)

When Popular Goes Public
by: Tennant, Roy
Published: (2005)

When Abundance Goes Wrong
by: Lee Skallerup Bessette
Published: (2024)

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
by: Rose, Aaron, et al.
Published: (2026)

Targeted Therapy for Idiopathic Inflammatory Myopathy
by: Ruijie Wang, et al.
Published: (2025)

One RL to See Them All: Visual Triple Unified Reinforcement Learning
by: Ma, Yan, et al.
Published: (2025)

When Tibetan Meditation Goes Global
by: Arizaga, Mara Lisa
Published: (2022)

When Information Abundance Goes Wrong
by: Lee Skallerup Bessette
Published: (2024)

Breaking the Secret: Economic Interventions for Combating Collusion in Embodied Multi-Agent Systems
by: Liu, Qi, et al.
Published: (2026)

Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare
by: Bashir, Adeela, et al.
Published: (2025)

Multi-Agent Systems for Robotic Autonomy with LLMs
by: Chen, Junhong, et al.
Published: (2025)

When Handwriting Goes Social: Creativity, Anonymity, and Communication in Graphonymous Online Spaces
by: Purohit, Aditya Kumar, et al.
Published: (2026)

When Autonomy Breaks: The Hidden Existential Risk of AI
by: Krook, Joshua
Published: (2025)

X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
by: Ye, Rui, et al.
Published: (2025)

On the Fragility of AI Agent Collusion
by: Keppo, Jussi, et al.
Published: (2026)

GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
by: Tao, Yiling, et al.
Published: (2026)

MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception
by: Qin, Yiran, et al.
Published: (2023)

Audit the Whisper: Detecting Steganographic Collusion in Multi-Agent LLMs
by: Tailor, Om
Published: (2025)

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
by: Motwani, Sumeet Ramesh, et al.
Published: (2024)

AURA: An Agent Autonomy Risk Assessment Framework
by: Chiris, Lorenzo Satta, et al.
Published: (2025)

Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions
by: Lin, Ryan Y., et al.
Published: (2024)

Multi-Agent Reinforcement Learning for Market Making: Competition without Collusion
by: Wang, Ziyi, et al.
Published: (2025)

Collusive Outcomes Without Collusion
by: Cho, Inkoo, et al.
Published: (2024)

Emergent Social Intelligence Risks in Generative Multi-Agent Systems
by: Huang, Yue, et al.
Published: (2026)

ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy
by: Yang, Zonghan, et al.
Published: (2024)

Multimarket Contact, Merger, and Airline Collusion
by: Yan, Ziyu
Published: (2024)

Rogue wave, interaction solutions to the KMM system
by: Jin, Xin-Wei, et al.
Published: (2020)

Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
by: Zhou, Ruiwen, et al.
Published: (2026)

Evaluating LLM Agent Collusion in Double Auctions
by: Agrawal, Kushal, et al.
Published: (2025)