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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Nuo, Tong, Yicheng, Yang, Yuzhe, He, Yufei, Zhang, Xueyi, Zou, Qingyun, Wang, Qian, He, Bingsheng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Multiagent Systems Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs
di: Wang, Qian, et al.
Pubblicazione: (2024)

Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning
di: Wang, Qian, et al.
Pubblicazione: (2024)

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

TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
di: Liu, Jiale, et al.
Pubblicazione: (2026)

Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale
di: Omari, Bassel Al, et al.
Pubblicazione: (2025)

Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration
di: Chen, Nuo, et al.
Pubblicazione: (2025)

Multi-LLM Systems Exhibit Robust Semantic Collapse
di: Kong, Weiyi, et al.
Pubblicazione: (2026)

Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
di: Hu, Zhengding, et al.
Pubblicazione: (2026)

Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations
di: Chen, Jinkun, et al.
Pubblicazione: (2025)

Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding
di: Zheng, Muyang, et al.
Pubblicazione: (2026)

Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
di: Chen, Mengzhuo, et al.
Pubblicazione: (2026)

Emergence of Collective Open-Ended Exploration from Decentralized Meta-Reinforcement Learning
di: Bornemann, Richard, et al.
Pubblicazione: (2023)

LLM Multi-Agent Systems: Challenges and Open Problems
di: Han, Shanshan, et al.
Pubblicazione: (2024)

Conjunctive Prompt Attacks in Multi-Agent LLM Systems
di: Arif, Nokimul Hasan, et al.
Pubblicazione: (2026)

How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
di: He, Zeyu, et al.
Pubblicazione: (2026)

Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
di: Zhang, Yuzhe, et al.
Pubblicazione: (2026)

Evaluating Collective Behaviour of Hundreds of LLM Agents
di: Willis, Richard, et al.
Pubblicazione: (2026)

The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systems
di: Gupta, Prateek, et al.
Pubblicazione: (2025)

Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus
di: Patel, Dipkumar
Pubblicazione: (2026)

Data-Driven Cooperative Output Regulation of Continuous-Time Multi-Agent Systems with Unknown Network Topology
di: Ren, Peng, et al.
Pubblicazione: (2024)

Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
di: Venkatesh, Kavana, et al.
Pubblicazione: (2026)

AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems
di: Mulian, Hadar, et al.
Pubblicazione: (2026)

Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
di: Yang, Jiaxi, et al.
Pubblicazione: (2025)

Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems
di: Guan, Zhaoyang, et al.
Pubblicazione: (2026)

Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
di: Li, Yuxuan, et al.
Pubblicazione: (2025)

Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems
di: Zhang, Zhuohui, et al.
Pubblicazione: (2024)

AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization
di: Yang, Zijiu, et al.
Pubblicazione: (2026)

SAGE: Multi-Agent Self-Evolution for LLM Reasoning
di: Peng, Yulin, et al.
Pubblicazione: (2026)

Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration
di: He, Zhixuan, et al.
Pubblicazione: (2025)

Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems
di: Li, Tianxiao, et al.
Pubblicazione: (2026)

KAOS: Large Model Multi-Agent Operating System
di: Zhuo, Zhao, et al.
Pubblicazione: (2024)

Inverse Attention Agents for Multi-Agent Systems
di: Long, Qian, et al.
Pubblicazione: (2024)

Norm Violation Detection in Multi-Agent Systems using Large Language Models: A Pilot Study
di: He, Shawn, et al.
Pubblicazione: (2024)

Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs
di: Mao, Yuren, et al.
Pubblicazione: (2025)

LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions
di: He, Xin, et al.
Pubblicazione: (2026)

Reaching New Heights in Multi-Agent Collective Construction
di: Rameš, Martin, et al.
Pubblicazione: (2024)

PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems
di: Deng, Yingfan, et al.
Pubblicazione: (2025)

Reputation as a Solution to Cooperation Collapse in LLM-based MASs
di: Ren, Siyue, et al.
Pubblicazione: (2025)

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
di: Ye, Yulei, et al.
Pubblicazione: (2026)

Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
di: Cuadros, Diego F., et al.
Pubblicazione: (2026)