# Emergent Coordination in Multi-Agent Language Models

arXiv: https://arxiv.org/abs/2510.05174 · HTML: https://mlsanity.com/paper/2510.05174/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 81 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 25 of 25)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://mlsanity.com/paper/2405.02957/) (2024)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Towards Understanding Distilled Reasoning Models: A Representational Approach](https://mlsanity.com/paper/2503.03730/) (2025)
- [First-Person Fairness in Chatbots](https://mlsanity.com/paper/2410.19803/) (2024)
- [Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games](https://mlsanity.com/paper/2506.23276/) (2025)
- [Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States](https://mlsanity.com/paper/2505.17663/) (2025)
- [Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data](https://mlsanity.com/paper/2004.08220/) (2020)
- [Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach](https://mlsanity.com/paper/2208.11660/) (2022)
- [Diversity in Sociotechnical Machine Learning Systems](https://mlsanity.com/paper/2107.09163/) (2021)
- [Multivariate Information Theory Uncovers Synergistic Subsystems of the Human Cerebral Cortex](https://mlsanity.com/paper/2206.06477/) (2022)
- [textttLM^texttt2: A Simple Society of Language Models Solves Complex Reasoning](https://mlsanity.com/paper/2404.02255/) (2024)
- [Greater than the parts: A review of the information decomposition approach to causal emergence](https://mlsanity.com/paper/2111.06518/) (2021)
- [Integrated information as a common signature of dynamical and information-processing complexity](https://mlsanity.com/paper/2106.10211/) (2021)
- [Spontaneous emergence of groups and signaling diversity in dynamic networks](https://mlsanity.com/paper/2210.17309/) (2022)

## Built on by (most cited first, 23 of 23)

- [Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity](https://mlsanity.com/paper/2602.03794/) (2026)
- [Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs](https://mlsanity.com/paper/2601.11369/) (2026)
- [Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook](https://mlsanity.com/paper/2602.14299/) (2026)
- [AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation](https://mlsanity.com/paper/2605.28655/) (2026)
- [TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code](https://mlsanity.com/paper/2602.06875/) (2026)
- [AI Agents Under EU Law](https://mlsanity.com/paper/2604.04604/) (2026)
- [CRAFT: Grounded Multi-Agent Coordination Under Partial Information](https://mlsanity.com/paper/2603.25268/) (2026)
- [Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs](https://mlsanity.com/paper/2605.06320/) (2026)
- [Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research](https://mlsanity.com/paper/2603.28986/) (2026)
- [Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems](https://mlsanity.com/paper/2604.19540/) (2026)
- [Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows](https://mlsanity.com/paper/2604.20658/) (2026)
- [Testing Interchangeability in LLM Agent Teams](https://mlsanity.com/paper/2609.05279/) (2026)
- [Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination](https://mlsanity.com/paper/2609.32939/) (2026)
- [Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning](https://mlsanity.com/paper/2603.02070/) (2026)
- [Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI](https://mlsanity.com/paper/2603.13244/) (2026)
- [High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination](https://mlsanity.com/paper/2604.02578/) (2026)
- [CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations](https://mlsanity.com/paper/2604.14691/) (2026)
- [Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game](https://mlsanity.com/paper/2606.28456/) (2026)
- [The Contagion Tensor: A Framework for Measuring Output-Distribution Coupling in Multi-Agent LLM Systems -- and Auditing the Claims It Enables](https://mlsanity.com/paper/2606.28839/) (2026)
- [When Do Multi-Agent Systems Help? An Information Bottleneck Perspective](https://mlsanity.com/paper/2607.16133/) (2026)
- [Agentic AI Containment Architecture for Security Hardening](https://mlsanity.com/paper/2608.26108/) (2026)
- [Scaling Multi-Agent Systems with Prospect-State Propagation](https://mlsanity.com/paper/2609.08033/) (2026)
- [Persistent Partners Raise Prices Among Learning Agents](https://mlsanity.com/paper/2609.35402/) (2026)

## Abstract (arXiv)

When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framework to test -- in a purely data-driven way -- whether multi-agent systems show signs of higher-order structure. This information decomposition lets us measure whether dynamical emergence is present in multi-agent LLM systems, localize it, and distinguish spurious temporal coupling from performance-relevant cross-agent synergy. We implement a practical criterion and an emergence capacity criterion operationalized as partial information decomposition of time-delayed mutual information (TDMI). We apply our framework to experiments using a simple guessing game without direct agent communication and minimal group-level feedback with three randomized interventions. Groups in the control condition exhibit strong temporal synergy but little coordinated alignment across agents. Assigning a persona to each agent introduces stable identity-linked differentiation. Combining personas with an instruction to ``think about what other agents might do'' shows identity-linked differentiation and goal-directed complementarity across agents. Taken together, our framework establishes that multi-agent LLM systems can be steered with prompt design from mere aggregates to higher-order collectives. Our results are robust across emergence measures and entropy estimators, and not explained by coordination-free baselines or temporal dynamics alone. Without attributing human-like cognition to the agents, the patterns of interaction we observe mirror well-established principles of collective intelligence in human groups: effective performance requires both alignment on shared objectives and complementary contributions across members.