Multi-LLM Systems Exhibit Robust Semantic Collapse

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kong, Weiyi, Lai, Shiyang, Piao, Jinghua, Evans, James
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Multiagent Systems
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems
di: Xu, Hongwei
Pubblicazione: (2026)

Semantic Fusion: Verifiable Alignment in Decentralized Multi-Agent Systems
di: Zaichyk, Sofiya
Pubblicazione: (2026)

Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing
di: Hu, Jinwei, et al.
Pubblicazione: (2025)

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

Graph-theoretic Agreement Framework for Multi-agent LLM Systems
di: Javed, Muhammad Umar
Pubblicazione: (2026)

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

Synthesis of Communication Policies for Multi-Agent Systems Robust to Communication Restrictions
di: Soudijani, Saleh, et al.
Pubblicazione: (2025)

OptiMA: A Transaction-Based Framework with Throughput Optimization for Very Complex Multi-Agent Systems
di: Çalıkyılmaz, Umut, et al.
Pubblicazione: (2025)

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

SRPG: Semantically Reconstructed Privacy Guard for Zero-Trust Privacy in Educational Multi-Agent Systems
di: Guo, Shuang, et al.
Pubblicazione: (2025)

SC-MAS: Constructing Cost-Efficient Multi-Agent Systems with Edge-Level Heterogeneous Collaboration
di: Zhao, Di, et al.
Pubblicazione: (2026)

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

Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System
di: Kostka, Adam, et al.
Pubblicazione: (2025)

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment
di: Hu, Jinwei, et al.
Pubblicazione: (2025)

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

Logic-Based Verification of Task Allocation for LLM-Enabled Multi-Agent Manufacturing Systems
di: Lim, Jonghan, et al.
Pubblicazione: (2026)

Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting
di: Han, Chen, et al.
Pubblicazione: (2026)

HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems
di: Xia, Yihan, et al.
Pubblicazione: (2025)

LLM-based Multi-Agent System for Simulating Strategic and Goal-Oriented Data Marketplaces
di: Sashihara, Jun, et al.
Pubblicazione: (2025)

Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
di: Chen, Nuo, et al.
Pubblicazione: (2026)

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)

IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems
di: Mao, Yihuan, et al.
Pubblicazione: (2024)

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

When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems
di: Manoranjan, Viswonathan, et al.
Pubblicazione: (2026)

LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
di: Renney, Harri, et al.
Pubblicazione: (2026)

The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
di: Tang, Luoxi, et al.
Pubblicazione: (2026)

Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
di: Li, Yubo, et al.
Pubblicazione: (2025)

Optimization under Attack: Resilience, Vulnerability, and the Path to Collapse
di: Aldawsari, Amal, et al.
Pubblicazione: (2025)

Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research
di: Haase, Jennifer, et al.
Pubblicazione: (2025)

Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation
di: Kostka, Adam, et al.
Pubblicazione: (2025)

An Agent-Centric Dynamical Systems Perspective on Multi-Agent Reinforcement Learning
di: Rudd-Jones, James, et al.
Pubblicazione: (2025)

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

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks
di: Zhou, Heng, et al.
Pubblicazione: (2025)

LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis
di: Liu, Tianming, et al.
Pubblicazione: (2025)

Camouflage Adversarial Attacks on Multiple Agent Systems
di: Lu, Ziqing, et al.
Pubblicazione: (2024)

CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
di: Venkatesh, Kavana, 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)

AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
di: Xia, Tong, et al.
Pubblicazione: (2025)

LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning
di: Wu, Xiaoguang, et al.
Pubblicazione: (2026)

MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability
di: Chen, Handi, et al.
Pubblicazione: (2026)