Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chaudhry, Gohar Irfan, Choukse, Esha, Qiu, Haoran, Goiri, Íñigo, Fonseca, Rodrigo, Belay, Adam, Bianchini, Ricardo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909767899807744
author Chaudhry, Gohar Irfan
Choukse, Esha
Qiu, Haoran
Goiri, Íñigo
Fonseca, Rodrigo
Belay, Adam
Bianchini, Ricardo
author_facet Chaudhry, Gohar Irfan
Choukse, Esha
Qiu, Haoran
Goiri, Íñigo
Fonseca, Rodrigo
Belay, Adam
Bianchini, Ricardo
contents Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key problem is that they expose workflows as opaque sequences of model and tool calls that tightly couple agent logic with model and hardware choices. Often, these workflow components are fragmented across different entities, preventing systems from reasoning about trade-offs across accuracy, latency, energy, and cost. This leads to resource waste and degraded service-level objectives (SLOs). We present Murakkab, a resource-efficient serving system for agentic workflows. Murakkab introduces a declarative abstraction that decouples workflow specification from execution configuration. A profile-guided optimizer and adaptive runtime jointly manage the full stack: orchestrating workflow components, mapping them to models and hardware, and dynamically reconfiguring execution to satisfy user-defined SLOs. By exposing the internal structure of agentic workflows, Murakkab enables cross-layer optimization that existing frameworks and cloud schedulers cannot achieve. Our evaluation on diverse workflows shows that Murakkab reduces GPU usage by up to 2.8$\times$, energy consumption by 3.7$\times$, and cost by 4.3$\times$ while maintaining SLOs.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
Chaudhry, Gohar Irfan
Choukse, Esha
Qiu, Haoran
Goiri, Íñigo
Fonseca, Rodrigo
Belay, Adam
Bianchini, Ricardo
Multiagent Systems
Artificial Intelligence
Software Engineering
Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key problem is that they expose workflows as opaque sequences of model and tool calls that tightly couple agent logic with model and hardware choices. Often, these workflow components are fragmented across different entities, preventing systems from reasoning about trade-offs across accuracy, latency, energy, and cost. This leads to resource waste and degraded service-level objectives (SLOs). We present Murakkab, a resource-efficient serving system for agentic workflows. Murakkab introduces a declarative abstraction that decouples workflow specification from execution configuration. A profile-guided optimizer and adaptive runtime jointly manage the full stack: orchestrating workflow components, mapping them to models and hardware, and dynamically reconfiguring execution to satisfy user-defined SLOs. By exposing the internal structure of agentic workflows, Murakkab enables cross-layer optimization that existing frameworks and cloud schedulers cannot achieve. Our evaluation on diverse workflows shows that Murakkab reduces GPU usage by up to 2.8$\times$, energy consumption by 3.7$\times$, and cost by 4.3$\times$ while maintaining SLOs.
title Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
topic Multiagent Systems
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2508.18298