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

arXiv: https://arxiv.org/abs/2604.18005 · HTML: https://mlsanity.com/paper/2604.18005/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [NoveltyBench: Evaluating Language Models for Humanlike Diversity](https://mlsanity.com/paper/2504.05228/) (2025)
- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [We're Different, We're the Same: Creative Homogeneity Across LLMs](https://mlsanity.com/paper/2501.19361/) (2025)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs](https://mlsanity.com/paper/2505.16997/) (2025)
- [LLM-based Human Simulations Have Not Yet Been Reliable](https://mlsanity.com/paper/2501.08579/) (2025)
- [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025)
- [A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models](https://mlsanity.com/paper/2504.05496/) (2025)
- [What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models](https://mlsanity.com/paper/2510.04226/) (2025)
- [The wall confronting large language models](https://mlsanity.com/paper/2507.19703/) (2025)
- [Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference](https://mlsanity.com/paper/2508.04586/) (2025)
- [Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration](https://mlsanity.com/paper/2508.04575/) (2025)
- [Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration](https://mlsanity.com/paper/2510.16645/) (2025)

## Built on by (most cited first, 7 of 7)

- [Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems](https://mlsanity.com/paper/2605.07069/) (2026)
- [Diversifying Personalized Research Ideation against AI-Induced Homogenization](https://mlsanity.com/paper/2607.28087/) (2026)
- [Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct](https://mlsanity.com/paper/2608.00285/) (2026)
- [AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining](https://mlsanity.com/paper/2609.29014/) (2026)
- [Towards Better Exploration in Sequential Test-Time Scaling](https://mlsanity.com/paper/2609.39632/) (2026)
- [Federated Agent Optimization](https://mlsanity.com/paper/2610.01195/) (2026)
- [No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse](https://mlsanity.com/paper/2610.01493/) (2026)

## Abstract (arXiv)

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.