Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation

• URL: http://arxiv.org/abs/2604.18005v2
• Date: Tue, 21 Apr 2026 04:12:30 GMT
• Title: Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
• Abstract summary: We study diversity in MAS-based ideation across three bottom-up levels: model intelligence, agent cognition, and system dynamics.<n>We characterize these outcomes as collective failures emerging from structural coupling.<n>Our analysis shows that this collapse arises primarily from the interaction structure rather than inherent model insufficiency.
• Score: 38.13720312846963
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the solution space remains unclear. We present a systematic empirical study of diversity in MAS-based ideation across three bottom-up levels: model intelligence, agent cognition, and system dynamics. At the model level, we identify a compute efficiency paradox, where stronger, highly aligned models yield diminishing marginal diversity despite higher per-sample quality. At the cognition level, authority-driven dynamics suppress semantic diversity compared to junior-dominated groups. At the system level, group-size scaling yields diminishing returns and dense communication topologies accelerate premature convergence. We characterize these outcomes as collective failures emerging from structural coupling, a process where interaction inadvertently contracts agent exploration and triggers diversity collapse. Our analysis shows that this collapse arises primarily from the interaction structure rather than inherent model insufficiency, highlighting the importance of preserving independence and disagreement when designing MAS for creative tasks. Our code is available at https://github.com/Xtra-Computing/MAS_Diversity.

Related papers

• The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents [51.56484100374058]
  We show that the high document density required to serve majority interests can geometrically overcrowd the retrieval neighborhood of a semantically similar minority.<n>We introduce a formal framework to analyze how such goal collisions in dense retrieval induce fundamental performance limits.<n>We prove that such objectives drive the system to self-organize into a state that exclusively serves majority interests.
  arXiv  Detail & Related papers  (2026-06-01T20:40:30Z)
• Scaling Behavior of Single LLM-Driven Multi-Agent Systems [5.2324118961669575]
  Multi-Agent Systems (MAS) promise to tackle complex tasks through collaborative intelligence.<n>This paper systematically investigates how the performance of a homogeneous MAS evolves as the number of agents increases.
  arXiv  Detail & Related papers  (2026-05-30T09:57:49Z)
• Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems [65.90791804095561]
  Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination amplifies a less explored risk.<n>Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined.<n>This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement.
  arXiv  Detail & Related papers  (2026-05-14T14:36:13Z)
• When Agents Evolve, Institutions Follow [52.359340707289114]
  We argue that multi-agent systems built on large language models face the same challenge.<n>Their central problem is not only individual intelligence, but collective organization.<n>We translate seven historical political institutions, spanning four canonical governance patterns, into executable multi-agent architectures.
  arXiv  Detail & Related papers  (2026-04-30T10:30:58Z)
• Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems [5.867974734829712]
  We present the first large-scale empirical study of coordination dynamics in multi-agent systems.<n>We analyze over 1.5 Million interactions across tasks, topologies, and scales.<n>We uncover three coupled laws: coordination follows heavy-tailed cascades, concentrates via preferential attachment into intellectual elites, and produces increasingly frequent extreme events as system size grows.
  arXiv  Detail & Related papers  (2026-04-03T03:08:07Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval [35.96356869281219]
  We describe a counterintuitive phenomenon in the strong-weak system: a strong-weak collaboration may under-perform weak-weak combinations.<n>We propose an Entropy-Based Adaptive Guidance Framework that dynamically aligns the guidance with the cognitive state of each agent.<n>Our approach consistently enhances the effectiveness and stability of heterogeneous collaboration.
  arXiv  Detail & Related papers  (2026-02-14T07:10:04Z)
• Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science [70.3658845234978]
  Large Language Models (LLMs) have greatly extended the capabilities of Multi-Agent Systems (MAS)<n>Despite this rapid progress, the field still relies heavily on empirical trial-and-error.<n>This bottleneck stems from the ambiguity of attribution.<n>We propose a factor attribution paradigm to systematically identify collaboration-driving factors.
  arXiv  Detail & Related papers  (2026-02-05T04:19:52Z)
• On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity [39.49884797762817]
  This work aims to answer a fundamental question: How does diversity of values shape the collective behavior of AI communities?<n>Using naturalistic value elicitation grounded in the prevalent Schwartz's Theory of Basic Human Values, we constructed simulations where communities with varying numbers of agents engaged in open-ended interactions and constitution formation.<n>The results show that value diversity enhances value stability, fosters emergent behaviors, and brings more creative principles developed by the agents themselves without external guidance.
  arXiv  Detail & Related papers  (2025-12-11T14:13:53Z)
• Multi-Agent Collaboration via Evolving Orchestration [55.574417128944226]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)
• The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems [1.137572571250676]
  We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments.<n>We formalize a consensus-diversity tradeoff, showing conditions where implicit methods outperform explicit ones.<n>We highlight emergent coordination via in-context learning, underscoring the value of preserving diversity for resilient decision-making.
  arXiv  Detail & Related papers  (2025-02-23T13:12:53Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• Scaling Large Language Model-based Multi-Agent Collaboration [72.8998796426346]
  Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning.<n>This study explores whether the continuous addition of collaborative agents can yield similar benefits.
  arXiv  Detail & Related papers  (2024-06-11T11:02:04Z)

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.