Cover Image

Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	De Nobili, Cristiano
Format:	Preprint
Published:	2026
Subjects:	Statistical Mechanics Computation and Language Multiagent Systems Physics and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Collective Behavior of AI Agents: the Case of Moltbook
by: De Marzo, Giordano, et al.
Published: (2026)

Conformity Generates Collective Misalignment in AI Agents Societies
by: De Marzo, Giordano, et al.
Published: (2026)

Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
by: Kumar, Shivani, et al.
Published: (2026)

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

Coordination Requires Simplification: Thermodynamic Bounds on Multi-Objective Compromise in Natural and Artificial Intelligence
by: Anand, Atma
Published: (2025)

Tricritical behavior in epidemic dynamics with vaccination
by: Pires, Marcelo A., et al.
Published: (2023)

Embodied LLM Agents Learn to Cooperate in Organized Teams
by: Guo, Xudong, et al.
Published: (2024)

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

Game susceptibility, Correlation and Payoff capacity as a measure of Cooperative behavior in the thermodynamic limit of some Social dilemmas
by: Benjamin, Colin, et al.
Published: (2024)

LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
by: Frisch, Ivar, et al.
Published: (2024)

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

AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
by: Xia, Tong, et al.
Published: (2025)

Selection pressure/Noise driven cooperative behaviour in the thermodynamic limit of repeated games
by: Tah, Rajdeep, et al.
Published: (2024)

How Exploration Breaks Cooperation in Shared-Policy Multi-Agent Reinforcement Learning
by: Weng, Yi-Ning, et al.
Published: (2026)

APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
by: Zheng, Quan, et al.
Published: (2026)

Food4All: A Multi-Agent Framework for Real-time Free Food Discovery with Integrated Nutritional Metadata
by: Yuan, Zhengqing, et al.
Published: (2025)

CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening
by: Wang, Yiyang, et al.
Published: (2026)

The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems
by: Wu, Zengqing, et al.
Published: (2025)

Preserving Cultural Identity with Context-Aware Translation Through Multi-Agent AI Systems
by: Anik, Mahfuz Ahmed, et al.
Published: (2025)

Geospatial distributions reflect rates of evolution of features of language
by: Kauhanen, Henri, et al.
Published: (2018)

You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
by: Hsing, Nicole, et al.
Published: (2026)

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
by: Cruz, Carlos Jose Xavier
Published: (2024)

LLM-Based Social Simulations Require a Boundary
by: Wu, Zengqing, et al.
Published: (2025)

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
by: Nguyen, Thi-Nhung, et al.
Published: (2025)

The High Cost of Incivility: Quantifying Interaction Inefficiency via Multi-Agent Monte Carlo Simulations
by: Mangold, Benedikt
Published: (2025)

Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
by: Wu, Zengqing, et al.
Published: (2024)

Law in Silico: Simulating Legal Society with LLM-Based Agents
by: Wang, Yiding, et al.
Published: (2025)

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
by: Yang, Yingxuan, et al.
Published: (2025)

Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
by: Gabison, Garry A., et al.
Published: (2025)

How to measure the optimality of word or gesture order with respect to the principle of swap distance minimization
by: Ferrer-i-Cancho, Ramon
Published: (2026)

Generating consensus and dissent on massive discussion platforms with an $O(N)$ semantic-vector model
by: Ferrer, A., et al.
Published: (2026)

Multimodal Multi-Agent Empowered Legal Judgment Prediction
by: Kang, Zhaolu, et al.
Published: (2026)

Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content
by: Mushtaq, Abdullah, et al.
Published: (2025)

AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence
by: Ghafarollahi, Alireza, et al.
Published: (2024)

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

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
by: Zhang, Shaokun, et al.
Published: (2025)

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
by: Pan, Shuai, et al.
Published: (2026)

ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
by: Liu, Jinnuo, et al.
Published: (2026)

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

How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent Simulation
by: Liao, Junjie, et al.
Published: (2026)