Imagen de Portada

When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liang, Sichu, Wang, Zhenglin, Chu, Jiajia, Xia, Pengfei, Zang, Hui, Zhou, Deyu
Formato:	Preprint
Publicado:	2026
Materias:	Multiagent Systems Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems
por: Ma, Ziyang, et al.
Publicado: (2026)

When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
por: Li, Xiaoxiao
Publicado: (2026)

DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
por: Liu, Yuhan, et al.
Publicado: (2024)

QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs
por: Honavar, Pratik, et al.
Publicado: (2026)

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
por: Zhang, Lingxi, et al.
Publicado: (2026)

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

Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression
por: Kriuk, Boris, et al.
Publicado: (2025)

A Plan Reuse Mechanism for LLM-Driven Agent
por: Li, Guopeng, et al.
Publicado: (2025)

Hierarchical Multi-Agent Reinforcement Learning-based Coordinated Spatial Reuse for Next Generation WLANs
por: Yu, Jiaming, et al.
Publicado: (2025)

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

Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework
por: Binkyte, Ruta
Publicado: (2025)

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
por: Ye, Hancheng, et al.
Publicado: (2025)

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

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

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

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

Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
por: Hu, Shuyue, et al.
Publicado: (2025)

CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
por: Venkatesh, Kavana, et al.
Publicado: (2026)

A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers
por: Yang, Kaiqi, et al.
Publicado: (2025)

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

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

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
por: Pan, Zaifeng, et al.
Publicado: (2025)

GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
por: Chen, Hongjiang, et al.
Publicado: (2026)

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
por: Rainone, Corrado, et al.
Publicado: (2026)

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

Can Agents Judge Systematic Reviews Like Humans? Evaluating SLRs with LLM-based Multi-Agent System
por: Mushtaq, Abdullah, et al.
Publicado: (2025)

LLM-empowered Agents Simulation Framework for Scenario Generation in Service Ecosystem Governance
por: Zhou, Deyu, et al.
Publicado: (2025)

When Does Multi-Agent Collaboration Help? An Entropy Perspective
por: Zhao, Yuxuan, et al.
Publicado: (2026)

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

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

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

Caching-Augmented Lifelong Multi-Agent Path Finding
por: Tang, Yimin, et al.
Publicado: (2024)

Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning
por: Zhang, Junkai, et al.
Publicado: (2024)

Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
por: Xia, Chengxuan, et al.
Publicado: (2025)

Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
por: Li, Yilong, et al.
Publicado: (2025)

Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
por: Jian, HuaDong, et al.
Publicado: (2026)

From Agent Simulation to Social Simulator: A Comprehensive Review (Part 1)
por: Xue, Xiao, et al.
Publicado: (2025)

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

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

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