Copertina

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pan, Zaifeng, Patel, Ajjkumar, Hu, Zhengding, Shen, Yipeng, Guan, Yue, Li, Wan-Lu, Qin, Lianhui, Wang, Yida, Ding, Yufei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Distributed, Parallel, and Cluster Computing Multiagent Systems
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management
di: Pan, Zaifeng, et al.
Pubblicazione: (2026)

Empowering Scientific Workflows with Federated Agents
di: Kamatar, Alok, et al.
Pubblicazione: (2025)

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
di: Hu, Zhengding, et al.
Pubblicazione: (2026)

Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents
di: Song, Kevin, et al.
Pubblicazione: (2025)

Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving
di: Yu, Shan, et al.
Pubblicazione: (2026)

RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching
di: Zhao, Zhan, et al.
Pubblicazione: (2026)

UFO3: Weaving the Digital Agent Galaxy
di: Zhang, Chaoyun, et al.
Pubblicazione: (2025)

Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap
di: Qiang, Xinwei, et al.
Pubblicazione: (2026)

Acceleration of Gossip Algorithms through the Euler-Poisson-Darboux Equation
di: Berthier, Raphaël, et al.
Pubblicazione: (2022)

DynTaskMAS: A Dynamic Task Graph-driven Framework for Asynchronous and Parallel LLM-based Multi-Agent Systems
di: Yu, Junwei, et al.
Pubblicazione: (2025)

On the Limits of Information Spread by Memory-less Agents
di: D'Archivio, Niccolò, et al.
Pubblicazione: (2024)

Near-linear Time Dispersion of Mobile Agents
di: Sudo, Yuichi, et al.
Pubblicazione: (2023)

Distributed Butterfly Analysis using Mobile Agents
di: Chand, Prabhat Kumar, et al.
Pubblicazione: (2025)

Computing Tree Structures in Anonymous Graphs via Mobile Agents
di: Chand, Prabhat Kumar, et al.
Pubblicazione: (2025)

Distributed Set-membership Filtering Frameworks For Multi-agent Systems With Absolute and Relative Measurements
di: Ding, Yu, et al.
Pubblicazione: (2023)

Decoupling Correctness from Policy: A Deterministic Causal Structure for Multi-Agent Systems
di: Ren, Zhiyuan, et al.
Pubblicazione: (2025)

Agent-Based Triangle Counting: Unlocking Truss Decomposition, Triangle Centrality, and Local Clustering Coefficient
di: Chand, Prabhat Kumar, et al.
Pubblicazione: (2024)

When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems
di: Ranathunga, Tharindu, et al.
Pubblicazione: (2026)

APWA: A Distributed Architecture for Parallelizable Agentic Workflows
di: Rose, Evan, et al.
Pubblicazione: (2026)

Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
di: Liu, Shuo, et al.
Pubblicazione: (2026)

VineLM: Trie-Based Fine-Grained Control for Agentic Workflows
di: Pagonas, Nikos, et al.
Pubblicazione: (2026)

Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems
di: Nagaitsev, Kirill, et al.
Pubblicazione: (2025)

Marconi: Prefix Caching for the Era of Hybrid LLMs
di: Pan, Rui, et al.
Pubblicazione: (2024)

Towards Blockchain-based Multi-Agent Robotic Systems: Analysis, Classification and Applications
di: Afanasyev, Ilya, et al.
Pubblicazione: (2019)

An Accelerated Distributed Stochastic Gradient Method with Momentum
di: Huang, Kun, et al.
Pubblicazione: (2024)

Agentic Fog: A Policy-driven Framework for Distributed Intelligence in Fog Computing
di: Akbar, Saeed, et al.
Pubblicazione: (2026)

Ledger-State Stigmergy: A Formal Framework for Indirect Coordination Grounded in Distributed Ledger State
di: García, Fernando Paredes
Pubblicazione: (2026)

When Computing follows Vehicles: Decentralized Mobility-Aware Resource Allocation for Edge-to-Cloud Continuum
di: Nezami, Zeinab, et al.
Pubblicazione: (2024)

Software-Defined Agentic Serving
di: Agarwal, Saurabh, et al.
Pubblicazione: (2026)

DejaVu: A Minimalistic Mechanism for Distributed Plurality Consensus
di: d'Amore, Francesco, et al.
Pubblicazione: (2026)

Perpetual exploration in anonymous synchronous networks with a Byzantine black hole
di: Bhattacharya, Adri, et al.
Pubblicazione: (2025)

Nalar: An agent serving framework
di: Laju, Marco, et al.
Pubblicazione: (2026)

On the $h$-majority dynamics with many opinions
di: d'Amore, Francesco, et al.
Pubblicazione: (2025)

On a Voter Model with Context-Dependent Opinion Adoption
di: Becchetti, Luca, et al.
Pubblicazione: (2023)

When Coordination Is Avoidable: A Monotonicity Analysis of Organizational Tasks
di: Ju, Harang
Pubblicazione: (2026)

Cooperative Solutions to Exploration Tasks Under Speed and Budget Constraints
di: Karishma, et al.
Pubblicazione: (2022)

Asymptotic analysis of cooperative censoring policies in sensor networks
di: Fernandez-Bes, Jesus, et al.
Pubblicazione: (2025)

A Framework for Hybrid Collective Inference in Distributed Sensor Networks
di: Nash, Andrew, et al.
Pubblicazione: (2026)

Multitask Learning with Learned Task Relationships
di: Wan, Zirui, et al.
Pubblicazione: (2025)

Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches
di: Fang, Shaoke, et al.
Pubblicazione: (2026)