{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T17:58:41Z","timestamp":1769795921638,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/comcomap68359.2025.11353145","type":"proceedings-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:19:25Z","timestamp":1769721565000},"page":"334-339","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive GPU Resource Allocation for Multi-Agent Collaborative Reasoning in Serverless Environments"],"prefix":"10.1109","author":[{"given":"Guilin","family":"Zhang","sequence":"first","affiliation":[{"name":"George Washington University,Department of Engineering Management and Systems Engineering,USA"}]},{"given":"Wulan","family":"Guo","sequence":"additional","affiliation":[{"name":"George Washington University,Department of Engineering Management and Systems Engineering,USA"}]},{"given":"Ziqi","family":"Tan","sequence":"additional","affiliation":[{"name":"George Washington University,Department of Engineering Management and Systems Engineering,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on llm-based multi-agent system: Recent advances and new frontiers in application","author":"Guo","year":"2024"},{"key":"ref2","article-title":"Large language model based multi-agents: A survey of progress and challenges","author":"Guo","year":"2024"},{"key":"ref3","article-title":"Multi-agent collaboration mechanisms: A survey of llms","author":"Wang","year":"2025"},{"key":"ref4","article-title":"Self-resource allocation in multi-agent llm systems","author":"Liu","year":"2025"},{"key":"ref5","article-title":"Multi-agent reinforcement learning for resources allocation optimization: A survey","author":"Wang","year":"2025"},{"key":"ref6","article-title":"Efficient and scalable agentic ai with heterogeneous systems","author":"Chen","year":"2025"},{"key":"ref7","article-title":"Serverlessllm: Low-latency serverless inference for large language models","author":"Fu","year":"2024"},{"key":"ref8","article-title":"Has-gpu: Efficient hybrid auto-scaling with fine-grained gpu allocation for slo-aware serverless inferences","volume-title":"European Conference on Computer Systems","author":"Yang"},{"key":"ref9","article-title":"Torpor: Gpu-enabled serverless computing for low-latency, resource-efficient inference","author":"Romero","year":"2023"},{"key":"ref10","article-title":"Faastube: Optimizing gpu-oriented data transfer for serverless computing","author":"Liu","year":"2024"},{"key":"ref11","article-title":"Dilu: Enabling gpu resourcing-on-demand for serverless deep learning","author":"Wang","year":"2025"},{"key":"ref12","article-title":"Esg: Pipeline-conscious efficient scheduling of dnn workflows on serverless platforms with shareable gpus","author":"Zhang","year":"2024"},{"key":"ref13","article-title":"Towards fast setup and high throughput of gpu serverless computing","author":"Yang","year":"2024"},{"key":"ref14","article-title":"Agent.xpu: Efficient scheduling of agentic llm workloads on heterogeneous soc","author":"Chen","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"},{"key":"ref16","article-title":"Gpu cluster scheduling for network-sensitive deep learning","author":"Wang","year":"2024"},{"key":"ref17","article-title":"Resource allocation and workload scheduling for large-scale distributed deep learning: A survey","author":"Chen","year":"2024"},{"key":"ref18","article-title":"Scheduling deep learning jobs in multi-tenant gpu clusters via wise resource sharing","author":"Zhang","year":"2024"},{"key":"ref19","article-title":"Towards efficient and practical gpu multitasking in the era of llm","author":"Li","year":"2025"},{"key":"ref20","article-title":"Hierarchical resource partitioning on modern gpus: A reinforcement learning approach","author":"Kim","year":"2024"},{"key":"ref21","article-title":"Power- and fragmentation-aware online scheduling for gpu datacenters","author":"Li","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23977\/acss.2025.090109"},{"key":"ref23","article-title":"Adaptive, efficient and fair resource allocation in cloud datacenters leveraging weighted a3c deep reinforcement learning","author":"Li","year":"2025"},{"key":"ref24","article-title":"Secure resource allocation via constrained deep reinforcement learning","author":"Wang","year":"2025"},{"key":"ref25","article-title":"Adaptive two-stage cloud resource scaling via hierarchical multi-indicator forecasting and bayesian decision-making","author":"Zhang","year":"2024"},{"key":"ref26","article-title":"Ai-driven resource allocation framework for microservices in hybrid cloud platforms","author":"Gao","year":"2024"},{"key":"ref27","article-title":"Drpc: Distributed reinforcement learning approach for scalable resource provisioning in container-based clusters","author":"Liu","year":"2024"},{"key":"ref28","first-page":"1979","article-title":"A meta reinforcement learning approach for predictive autoscaling in the cloud","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Chen"},{"key":"ref29","article-title":"Nvidia dynamo: A low-latency distributed inference framework for scaling reasoning ai models","year":"2025","journal-title":"NVIDIA Technical Blog"},{"key":"ref30","article-title":"Temporal-aware gpu resource allocation for distributed llm inference via reinforcement learning","author":"Li","year":"2025"},{"key":"ref31","article-title":"Cloud native system for llm inference serving","author":"Wang","year":"2025"},{"key":"ref32","article-title":"Aibrix: Towards scalable, costeffective large language model inference infrastructure","author":"Zhang","year":"2025"},{"key":"ref33","article-title":"Polyserve: Efficient multi-slo serving at scale","author":"Yang","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FMEC65595.2025.11119384"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC66453.2025.11304654"}],"event":{"name":"2025 Computing, Communications and IoT Applications (ComComAp)","location":"Madrid, Spain","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,17]]}},"container-title":["2025 Computing, Communications and IoT Applications (ComComAp)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11353105\/11353106\/11353145.pdf?arnumber=11353145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T07:04:19Z","timestamp":1769756659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/comcomap68359.2025.11353145","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}