From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

[2608.15127] From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Operating Systems arXiv:2608.15127 (cs) [Submitted on 15 Aug 2026] Title: From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems Authors: Chaokun Chang , Yukun Zhou , Kaihua Fu , Dakai An , Tianyu Feng , Hanfeng Lu , Sheng Yao , Pu Guo , Yinghao Yu , Yizhou Shan , Bo Li , Binhang Yuan , Wei Wang View a PDF of the paper titled From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems, by Chaokun Chang and 12 other authors View PDF HTML (experimental) Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state. However, the system behavior of these workloads---where latency, cost, and bottlenecks arise---remains poorly characterized, leaving serving systems to rely on assumptions built for conventional inference. We present AgentSysBench, a benchmark suite and measurement toolkit with ten representative agentic applications and unified systems-level instrumentation. Across controlled deployments and production traces, we identify six properties that distinguish agentic workloads from conventional LLM serving: (1) execution is heavyweight and stateful, with non-LLM components dominating latency in 5 of 10 applications and sandbox working-set memory peaking at 28 GB per session; (2) applications compose components with heterogeneous resource affinity---GPU-bound inference, memory-bound retrieval, CPU-bound sandboxes---whose task latencies diverge by up to 32x; (3) bottlenecks shift across requests, models, and deployments; (4) production sessions hold state idle for minutes to hours between active steps; (5) a control-plane tax---auxiliary LLM calls and context overhead from tool schemas and observations---crowds out productive compute and context; and (6) production traces from three applications reveal heavy cross-request redundancy in search queries and web fetches, exposing a large caching opportunity. Four design explorations demonstrate that these findings are actionable: task-aware serving reduces latency by 29--40%, communication-aware placement by up to 4.5x, state offloading reduces memory usage by 4.6x, and tool-result caching removes 35.2% of redundant search calls and saves 19.3% of aggregate search latency. Subjects: Operating Systems (cs.OS) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA) Cite as: arXiv:2608.15127 [cs.OS] (or arXiv:2608.15127v1 [cs.OS] for this version) https://doi.org/10.48550/arXiv.2608.15127 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chaokun Chang [ view email ] [v1] Sat, 15 Aug 2026 09:02:16 UTC (1,339 KB) Full-text links: Access Paper: View a PDF of the paper titled From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems, by Chaokun Chang and 12 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.OS < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.DC cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems#611077
• From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems#459631
• The Cost of Coordination: Why Multi-Agent LLMs Explore More But Discover Less#368869
• SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center#927025
• HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling#200468