Multi-Agent Empowerment and Emergence of Complex Behavior in Groups

• URL: http://arxiv.org/abs/2604.21155v1
• Date: Wed, 22 Apr 2026 23:51:04 GMT
• Title: Multi-Agent Empowerment and Emergence of Complex Behavior in Groups
• Abstract summary: We study the emergence of behaviors driven by one such incentive, empowerment, specifically in the context of more than one agent.<n>This demonstrates the potential of intrinsic motivations such as empowerment to not just drive behavior for only individual agents but also higher levels of behavioral organization at scale.
• Score: 2.105755353388366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one such incentive, empowerment, specifically in the context of more than one agent. We formulate a principled extension of empowerment to the multi-agent setting, and demonstrate its efficient calculation. We observe that this intrinsic motivation gives rise to characteristic modes of group-organization in two qualitatively distinct environments: a pair of agents coupled by a tendon, and a controllable Vicsek flock. This demonstrates the potential of intrinsic motivations such as empowerment to not just drive behavior for only individual agents but also higher levels of behavioral organization at scale.

Related papers

• Causal Foundations of Collective Agency [6.242119553843324]
  Key challenge for advanced AI systems is the possibility that simpler agents might inadvertently form a collective agent with capabilities and goals distinct from those of any individual.<n>We adopt a behavioral perspective in answering this question, ascribing collective agency to a group when viewing the group's joint actions as rational and goal-directed.<n>Our framework aims to provide a foundation for theoretical and empirical work to understand, predict, and control emergent collective agents in multi-agent AI systems.
  arXiv  Detail & Related papers  (2026-04-30T21:32:10Z)
• Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective [12.899919591015912]
  Multi-agent self-organizing systems (MASOS) exhibit key characteristics including scalability, adaptability, flexibility, and robustness.<n>This paper focuses on the emergence of dependency hierarchies during task execution.<n>By calculating the gradients of each agent's actions in relation to the states of other agents, the inter-agent dependencies are quantified.
  arXiv  Detail & Related papers  (2025-08-13T06:50:03Z)
• DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning [84.22561239481901]
  We propose a new approach that enables agents to learn whether their behaviors should be consistent with that of other agents. We evaluate DCIR in multiple environments including Multi-agent Particle, Google Research Football and StarCraft II Micromanagement.
  arXiv  Detail & Related papers  (2023-12-10T06:03:57Z)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors [93.38830440346783]
  We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
  arXiv  Detail & Related papers  (2023-08-21T16:47:11Z)
• Group Cohesion in Multi-Agent Scenarios as an Emergent Behavior [0.0]
  We show that imbuing agents with intrinsic needs for group affiliation, certainty and competence will lead to the emergence of social behavior among agents. This behavior expresses itself in altruism toward in-group agents and adversarial tendencies toward out-group agents.
  arXiv  Detail & Related papers  (2022-11-03T18:37:05Z)
• Learning Latent Representations to Influence Multi-Agent Interaction [65.44092264843538]
  We propose a reinforcement learning-based framework for learning latent representations of an agent's policy. We show that our approach outperforms the alternatives and learns to influence the other agent.
  arXiv  Detail & Related papers  (2020-11-12T19:04:26Z)
• Domain-independent generation and classification of behavior traces [18.086782548507855]
  CABBOT is a learning technique that allows the agent to perform on-line classification of the type of planning agent whose behavior is observing. We present experiments in several (both financial and non-financial) domains with promising results.
  arXiv  Detail & Related papers  (2020-11-03T16:58:54Z)
• Learning to Incentivize Other Learning Agents [73.03133692589532]
  We show how to equip RL agents with the ability to give rewards directly to other agents, using a learned incentive function. Such agents significantly outperform standard RL and opponent-shaping agents in challenging general-sum Markov games. Our work points toward more opportunities and challenges along the path to ensure the common good in a multi-agent future.
  arXiv  Detail & Related papers  (2020-06-10T20:12:38Z)
• Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning [59.62721526353915]
  Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities. Our method aims to leverage these commonalities by asking the question: What is the expected utility of each agent when only considering a randomly selected sub-group of its observed entities?''
  arXiv  Detail & Related papers  (2020-06-07T18:28:41Z)
• Intrinsic Motivation for Encouraging Synergistic Behavior [55.10275467562764]
  We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks. Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own.
  arXiv  Detail & Related papers  (2020-02-12T19:34:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.