Cover Image

Group size effects and collective misalignment in LLM multi-agent systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Flint, Ariel, Aiello, Luca Maria, Pastor-Satorras, Romualdo, Baronchelli, Andrea
Format:	Preprint
Published:	2025
Subjects:	Multiagent Systems Artificial Intelligence Computers and Society Physics and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Emergent social conventions and collective bias in LLM populations
by: Ashery, Ariel Flint, et al.
Published: (2024)

Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
by: Ye, Jinyi, et al.
Published: (2026)

TerraLingua: Emergence and Analysis of Open-endedness in LLM Ecologies
by: Paolo, Giuseppe, et al.
Published: (2026)

FlockVote: LLM-Empowered Agent-Based Modeling for Simulating U.S. Presidential Elections
by: Zhou, Lingfeng, et al.
Published: (2025)

Leveraging LLM-based agents for social science research: insights from citation network simulations
by: Ji, Jiarui, et al.
Published: (2025)

Mathematics of multi-agent learning systems at the interface of game theory and artificial intelligence
by: Wang, Long, et al.
Published: (2024)

Failure of contextual invariance in large language models
by: Kumar, Sagar, et al.
Published: (2026)

Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
by: Lin, Hsien-Tsung, et al.
Published: (2025)

Network Effects and Agreement Drift in LLM Debates
by: Cau, Erica, et al.
Published: (2026)

Reply to "Emergent LLM behaviors are observationally equivalent to data leakage"
by: Ashery, Ariel Flint, et al.
Published: (2025)

Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
by: Hu, Yueqing, et al.
Published: (2026)

Multi-agent reinforcement learning using echo-state network and its application to pedestrian dynamics
by: Komatsu, Hisato
Published: (2023)

Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems
by: Idowu, Jamiu, et al.
Published: (2026)

The potential role of AI agents in transforming nuclear medicine research and cancer management in India
by: Vashistha, Rajat, et al.
Published: (2025)

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
by: Zhu, Kunlun, et al.
Published: (2025)

Generative AI collective behavior needs an interactionist paradigm
by: Ferrarotti, Laura, et al.
Published: (2026)

Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai
by: Coppolillo, Erica, et al.
Published: (2026)

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

Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations
by: Fidone, Giacomo, et al.
Published: (2025)

Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approach
by: Elhaimeur, Iizalaarab, et al.
Published: (2025)

Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
by: Takata, Ryosuke, et al.
Published: (2025)

TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Education
by: Zamojska, Monika, et al.
Published: (2025)

From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation
by: Li, Qiumeng, et al.
Published: (2025)

Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System
by: Lou, Shangyu
Published: (2025)

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

Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline
by: Dietrich, Juergen
Published: (2026)

Investigating social alignment via mirroring in a system of interacting language models
by: McGuinness, Harvey, et al.
Published: (2024)

CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
by: Ye, Wanghao, et al.
Published: (2025)

Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Bandits
by: Pokhriyal, Subham, et al.
Published: (2024)

Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis
by: Heus, Evan, et al.
Published: (2025)

Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems
by: Abram, Marcin
Published: (2026)

MaaSSim -- agent-based two-sided mobility platform simulator
by: Kucharski, Rafał, et al.
Published: (2020)

Soft-Label Governance for Distributional Safety in Multi-Agent Systems
by: Aiersilan, Aizierjiang, et al.
Published: (2026)

Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies
by: Ruan, Anbang
Published: (2026)

AI Agents as Policymakers in Simulated Epidemics
by: Aoki, Goshi, et al.
Published: (2026)

Validating Generative Agent-Based Models for Logistics and Supply Chain Management Research
by: Castillo, Vincent E.
Published: (2025)

Governing What the EU AI Act Excludes: Accountability for Autonomous AI Agents in Smart City Critical Infrastructure
by: Butt, Talal Ashraf, et al.
Published: (2026)

Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
by: Hu, Botao Amber, et al.
Published: (2026)

Data-driven and distributed governance of building facilities management using decentralized autonomous organization, digital twin, and large language models
by: Ly, Reachsak, et al.
Published: (2026)

Governed Reasoning for Institutional AI
by: Seck, Mamadou
Published: (2026)