Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC

• URL: http://arxiv.org/abs/2506.24045v1
• Date: Mon, 30 Jun 2025 16:50:48 GMT
• Title: Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC
• Authors: Xinming Wei, Jiahao Zhang, Haoran Li, Jiayu Chen, Rui Qu, Maoliang Li, Xiang Chen, Guojie Luo,
• Abstract summary: This paper introduces Agent.xpu, an efficient serving system for agentic LLM workloads on memory-unified heterogeneous SOCs.<n>With dedicated offline profiling, Agent.xpu first constructs a heterogeneous execution graph, which fuses and chunks model kernels for affinity-guided, elastic accelerator mapping.<n>At runtime, its online scheduler enables fine-grained, kernel-level preemption to guarantee the responsiveness of reactive tasks.
• Score: 11.82567747365518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The proliferation of agentic Large Language Models (LLMs) on personal devices introduces a new class of workloads characterized by a dichotomy of objectives. Reactive tasks, initiated by users, demand immediate, low-latency responses, while proactive tasks operate invisibly and prioritize throughput. Existing on-device LLM engines, designed for isolated inferences, fail to efficiently manage these concurrent and conflicting requests on consumer-grade heterogeneous SoCs with CPU, integrated GPU, and NPU. This paper introduces Agent.xpu, an efficient serving system for agentic LLM workloads on memory-unified heterogeneous SoCs. With dedicated offline profiling, Agent.xpu first constructs a heterogeneous execution graph, which fuses and chunks model kernels for affinity-guided, elastic accelerator mapping with predictive kernel annotation. At runtime, its online scheduler enables fine-grained, kernel-level preemption to guarantee the responsiveness of reactive tasks. To maximize SoC utilization, it adopts slack-aware kernel backfill to opportunistically append proactive tasks, and mitigates NPU-iGPU contention via bandwidth-aware dispatch. Evaluation on an Intel Core Ultra SoC shows that Agent.xpu achieves 4.6$\times$ lower latency for reactive tasks and sustains 1.6$\times$-6.8$\times$ higher throughput for proactive tasks compared to state-of-the-art inference engines.

Related papers

• Agentic Test-Time Scaling for WebAgents [65.5178428849495]
  We present Confidence-Aware Test-Time Scaling (CATTS), which uses vote-derived uncertainty to allocate compute only when decisions are genuinely contentious.<n>CATTS improves performance on WebArena-Lite and GoBrowse by up to 9.1% over React while using up to 2.3x fewer tokens than uniform scaling.
  arXiv  Detail & Related papers  (2026-02-12T18:58:30Z)
• PackInfer: Compute- and I/O-Efficient Attention for Batched LLM Inference [11.149400020066333]
  We present PackInfer, a kernel-level attention framework that enables compute- and I/O-aware execution for batched inference.<n>We show that PackInfer reduces latency 13.0-20.1%, and improves throughput by 20% compared to the state-of-the-art FlashAttention.
  arXiv  Detail & Related papers  (2026-02-03T01:46:34Z)
• ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks [62.031889234230725]
  6G networks rely on complex cross-layer optimization.<n> manually translating high-level intents into mathematical formulations remains a bottleneck.<n>We present ComAgent, a multi-LLM agentic AI framework.
  arXiv  Detail & Related papers  (2026-01-27T13:43:59Z)
• HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network [50.33808558714122]
  Large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy.<n>We propose HALO, a novel framework that can boost the distributed LLM inference in lossy edge network.<n> Experimental results from a Raspberry Pi cluster demonstrate that HALO achieves a 3.41x end-to-end speedup for LLaMA-series LLMs under unreliable network conditions.
  arXiv  Detail & Related papers  (2026-01-16T07:37:23Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• A CPU-Centric Perspective on Agentic AI [8.417523196411574]
  Agentic AI frameworks add a decision-making orchestrator embedded with external tools, including web search, Python interpreter, contextual database, and others.<n>This paper aims to characterize and understand the system bottlenecks introduced by agentic AI workloads from a CPU-centric perspective.
  arXiv  Detail & Related papers  (2025-11-01T23:46:44Z)
• Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems [11.42175340352007]
  We introduce SupervisorAgent, a lightweight and modular framework for runtime, adaptive supervision.<n>SupervisorAgent intervenes at critical junctures to proactively correct errors, guide inefficient behaviors, and purify observations.<n>On the challenging GAIA benchmark, SupervisorAgent reduces the token consumption of the Smolagent framework by an average of 29.45% without compromising its success rate.
  arXiv  Detail & Related papers  (2025-10-30T15:12:59Z)
• Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving [4.309392302169281]
  Engine-level prefill-decode (PD) disaggregation avoids interference but incurs higher hardware and coordination overhead.<n>PD achieves up to 2.2x higher throughput, 20x lower TTFT, and 2.5x lower TBT than vLLM; outperforms SG by up to 2x; and matches or exceeds disaggregated vLLM.
  arXiv  Detail & Related papers  (2025-07-09T07:27:18Z)
• Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing [38.187358106473894]
  Intra-DP is a high-performance collaborative inference system optimized for deep neural networks (DNNs) on mobile devices.<n>It reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.<n>The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-07-08T09:50:57Z)
• AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents [60.881609323604685]
  Agent Synth is a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets.<n>Our pipeline achieves a low average cost of $0.60 per trajectory, orders of magnitude cheaper than human annotations.
  arXiv  Detail & Related papers  (2025-06-17T05:46:52Z)
• Real-Time Execution of Action Chunking Flow Policies [49.1574468325115]
  This paper presents a novel inference-time algorithm that enables asynchronous execution of action interacting systems.<n>It is applicable to any diffusion- or VLA-based systems executing out of the box with no re-training.<n>Results show that RTC is fast, performant, and uniquely robust to inference manipulation.
  arXiv  Detail & Related papers  (2025-06-09T01:01:59Z)
• EcoAgent: An Efficient Edge-Cloud Collaborative Multi-Agent Framework for Mobile Automation [36.08217588070538]
  Cloud-based mobile agents powered by (multimodal) large language models ((M)LLMs) offer strong reasoning abilities but suffer from high latency and cost.<n>We propose textbfEcoAgent, an textbfEdge-textbfCloud ctextbfOllaborative multi-agent framework for mobile automation.<n>EcoAgent features a closed-loop collaboration among a cloud-based Planning Agent and two edge-based agents: the Execution Agent for action execution and the Observation Agent for verifying outcomes.
  arXiv  Detail & Related papers  (2025-05-08T17:31:20Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference [9.164093249308419]
  We present POD-Attention - the first GPU kernel that efficiently computes attention for hybrid batches.<n> POD-Attention aims to maximize the utilization of both compute and memory bandwidth by carefully allocating the GPU's resources.
  arXiv  Detail & Related papers  (2024-10-23T17:06:56Z)
• Benchmarking Edge AI Platforms for High-Performance ML Inference [0.0]
  Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often involve scaling down modern hardware, the performance characteristics of neural network workloads can vary significantly. We compare the latency and throughput of various linear algebra and neural network inference tasks across CPU-only, CPU/GPU, and CPU/NPU integrated solutions.
  arXiv  Detail & Related papers  (2024-09-23T08:27:27Z)
• DASA: Delay-Adaptive Multi-Agent Stochastic Approximation [64.32538247395627]
  We consider a setting in which $N$ agents aim to speedup a common Approximation problem by acting in parallel and communicating with a central server. To mitigate the effect of delays and stragglers, we propose textttDASA, a Delay-Adaptive algorithm for multi-agent Approximation.
  arXiv  Detail & Related papers  (2024-03-25T22:49:56Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts [60.1586169973792]
  M$3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE) MoE achieves better accuracy and over 80% reduction computation but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations.
  arXiv  Detail & Related papers  (2023-05-30T02:24:03Z)
• Multi-user Co-inference with Batch Processing Capable Edge Server [26.813145949399427]
  We focus on novel scenarios that the energy-constrained mobile devices offload inference tasks to an edge server with GPU. The inference task is partitioned into sub-tasks for a finer granularity of offloading and scheduling. It is proven that optimizing the offloading policy of each user independently and aggregating all the same sub-tasks in one batch is optimal. Experiments show that IP-SSA reduces up to 94.9% user energy consumption in the offline setting.
  arXiv  Detail & Related papers  (2022-06-03T15:40:32Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)

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.