Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective

• URL: http://arxiv.org/abs/2603.16104v1
• Date: Tue, 17 Mar 2026 04:03:18 GMT
• Title: Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
• Abstract summary: Helium is a workflow-aware serving framework that models agentic workloads as query plans and treats LLM invocations as first-class operators.<n>Helium bridges classic query optimization principles with LLM serving, achieving up to 1.56x speedup over state-of-the-art agent serving systems.
• Score: 3.9457939396735573
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and intermediate results due to speculative and parallel exploration. Existing LLM serving systems, such as vLLM, focus on optimizing individual inference calls and overlook cross-call dependencies, leading to significant inefficiencies. This paper rethinks LLM and agent serving from a data systems perspective and introduces Helium, a workflow-aware serving framework that models agentic workloads as query plans and treats LLM invocations as first-class operators. Helium integrates proactive caching and cache-aware scheduling to maximize reuse across prompts, KV states, and workflows. Through these techniques, Helium bridges classic query optimization principles with LLM serving, achieving up to 1.56x speedup over state-of-the-art agent serving systems on various workloads. Our results demonstrate that end-to-end optimization across workflows is essential for scalable and efficient LLM-based agents.

Related papers

• UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems [46.48622741253505]
  We present UnityMAS-O, a general RL optimization framework for LLM-based multi-agent systems.<n>UnityMAS-O treats the complete runtime as the optimization unit, rather than a single response or policy trajectory.<n>We show that UnityMAS-O can serve as a reusable substrate for converting diverse-based multi-agent systems into trainable multi-agent RL systems.
  arXiv  Detail & Related papers  (2026-05-26T07:30:03Z)
• Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations [53.53864188270018]
  Large language models (LLMs) have advanced recommendation systems (RSs)<n>We propose MARC to explicitly control the modularity of LLMs.<n>MARC achieved a 2.82% eCPM lift in an online A/B test within a large-scale commercial search advertising scenario.
  arXiv  Detail & Related papers  (2026-04-20T12:08:58Z)
• Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System [1.4669344809969722]
  Large language models (LLMs) play a critical role in autonomous decision-making.<n>We present a scalable, hierarchical multi-agent framework for orchestrating high- throughput screening campaigns.<n>Results demonstrate that the proposed agentic framework enables efficient and scalable execution on the Aurora supercomputer.
  arXiv  Detail & Related papers  (2026-04-09T01:01:11Z)
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs [62.17306142810532]
  We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters.<n>Chime traces the best latency, reducing end-to-end latency by 1.2--2.4$times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines.
  arXiv  Detail & Related papers  (2026-03-23T17:01:42Z)
• Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows [0.8250374560598494]
  Large language models (LLMs) are increasingly used in applications forming multi-request systems.<n>They amplify latency and energy demand during inference.<n>This paper presents the first systematic characterization of performance-energy trade-offs in multi-request inference.
  arXiv  Detail & Related papers  (2026-03-12T10:10:37Z)
• LLM for Large-Scale Optimization Model Auto-Formulation: A Lightweight Few-Shot Learning Approach [10.44190976207354]
  LEAN-LLM-OPT is a workflow framework for large-scale OPTimization auto-formulation.<n>It decomposes the modeling task into structured sub-tasks and offloads mechanical data-handling operations to auxiliary tools.<n>It achieves strong performance on large-scale optimization modeling tasks and is competitive with state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-01-14T17:09:57Z)
• Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows [5.376980683850103]
  We propose Difficulty-Aware Agentic Orchestration (DAAO), which generates query-specific multi-agent guided by predicted difficulty.<n>DAAO surpasses prior multi-agent systems in both accuracy and inference efficiency.
  arXiv  Detail & Related papers  (2025-09-14T03:57:43Z)
• Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System [75.25394449773052]
  Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving.<n>Yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods.<n>We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness.
  arXiv  Detail & Related papers  (2024-10-10T17:00:06Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency [20.33467627548677]
  Large language models (LLMs) have surged in popularity and are extensively used in commercial applications. We conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving.
  arXiv  Detail & Related papers  (2024-07-23T23:37:29Z)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
  MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
  arXiv  Detail & Related papers  (2024-02-22T18:56:07Z)
• Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations [53.76682562935373]
  We introduce an efficient framework called textbfInteRecAgent, which employs LLMs as the brain and recommender models as tools. InteRecAgent achieves satisfying performance as a conversational recommender system, outperforming general-purpose LLMs.
  arXiv  Detail & Related papers  (2023-08-31T07:36:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.