Cover Image

Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bisconti, Piercosma, Galisai, Marcello, Pierucci, Federico, Bracale, Marcantonio, Prandi, Matteo
Format:	Preprint
Published:	2025
Subjects:	Multiagent Systems Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agentic Microphysics: A Manifesto for Generative AI Safety
by: Pierucci, Federico, et al.
Published: (2026)

Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
by: Syrnikov, Marcantonio Bracale, et al.
Published: (2026)

Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
by: Prandi, Matteo, et al.
Published: (2025)

Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
by: Bisconti, Piercosma, et al.
Published: (2025)

From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
by: Bisconti, Piercosma, et al.
Published: (2025)

Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety
by: Galisai, Marcello, et al.
Published: (2026)

Standards for trustworthy AI in the European Union: technical rationale, structural challenges, and an implementation path
by: Bisconti, Piercosma, et al.
Published: (2026)

Institutional AI: A Governance Framework for Distributional AGI Safety
by: Pierucci, Federico, et al.
Published: (2026)

MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems
by: Chen, Kai, et al.
Published: (2025)

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
by: Luo, Yinyi, et al.
Published: (2026)

TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
by: Kavathekar, Ishan, et al.
Published: (2025)

Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework
by: Binkyte, Ruta
Published: (2025)

AI Agents Under EU Law
by: Nannini, Luca, et al.
Published: (2026)

Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems
by: Reid, Alistair, et al.
Published: (2025)

A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
by: Cho, Ha Na
Published: (2026)

Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities
by: Takata, Ryosuke, et al.
Published: (2024)

Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
by: Özdemir, Nurullah Eymen, et al.
Published: (2026)

LLM-enabled Social Agents
by: Gürcan, Önder, et al.
Published: (2026)

OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
by: Bi, Zhenyu, et al.
Published: (2025)

Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems
by: Fukui, Hiroki
Published: (2026)

LLM Constitutional Multi-Agent Governance
by: de Curtò, J., et al.
Published: (2026)

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
by: Ye, Yulei, et al.
Published: (2026)

Cultural Evolution of Cooperation among LLM Agents
by: Vallinder, Aron, et al.
Published: (2024)

SODE: Analyzing Social Dynamics in LLM Agents
by: Jung, Inseo, et al.
Published: (2026)

Scaling Behavior of Single LLM-Driven Multi-Agent Systems
by: Li, Jialing, et al.
Published: (2026)

SAGE: Multi-Agent Self-Evolution for LLM Reasoning
by: Peng, Yulin, et al.
Published: (2026)

Insider Attacks in Multi-Agent LLM Consensus Systems
by: Sun, Xiaolin, et al.
Published: (2026)

LLM Multi-Agent Systems: Challenges and Open Problems
by: Han, Shanshan, et al.
Published: (2024)

WESE: Weak Exploration to Strong Exploitation for LLM Agents
by: Huang, Xu, et al.
Published: (2024)

Voluntary Collusion with Secret Tools in Competing LLM Agents
by: Zeng, Xijie, et al.
Published: (2026)

Conjunctive Prompt Attacks in Multi-Agent LLM Systems
by: Arif, Nokimul Hasan, et al.
Published: (2026)

Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration
by: Song, Xinyuan, et al.
Published: (2025)

Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
by: Ren, Shuo, et al.
Published: (2025)

The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
by: Reza, Zarreen
Published: (2025)

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System
by: Liu, Zhiwei, et al.
Published: (2024)

Scheming Ability in LLM-to-LLM Strategic Interactions
by: Pham, Thao
Published: (2025)

Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents
by: Zhang, Enhao, et al.
Published: (2025)

Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges
by: Taillandier, Patrick, et al.
Published: (2025)

Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems
by: Zamojska, Monika, et al.
Published: (2025)

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
by: Wang, Chenyu, et al.
Published: (2026)