paper-with-me

홈 › Papers

Agent-X: Full Pipeline Acceleration of On-device AI Agents

2026-05-11 · Jinha Chung, Byeongjun Shin, Jiin Kim, Minsoo Rhu arxiv

LLM-based agents deliver state-of-the-art performance across tasks but incur high end-to-end latency on edge devices. We introduce Agent-X, a software-only, accuracy-preserving framework that accelerates both the prefill and decode stages of on-device agent workloads. Agent-X's two key components rewrite prompts to leverage prefix caching tailored to agent-specific input-token patterns and enable LLM-free speculative decoding for fast token generation with minimal overhead. On representative agentic workloads, Agent-X achieves a 1.61x end-to-end speedup in real systems with no accuracy loss and can be seamlessly integrated into existing on-device AI agents. To the best of our knowledge, ours is the first to systematically characterize and eliminate latency bottlenecks in on-device agents.

📄 PDF Abstract BibTeX arXiv:2605.10380

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents

2026-04-13 · Fei Tang, Zhiqiong Lu, Boxuan Zhang, Weiming Lu 외 arxiv

GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes, reaching a long tail of applications that CLI-based agents…

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

2024-02-23 · JianGuo Zhang, Tian Lan, Rithesh Murthy, Zhiwei Liu 외

Autonomous agents powered by large language models (LLMs) have garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presents inherent challenges due to the hetero…

SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation

2024-10-19 · Jingxuan Chen, Derek Yuen, Bin Xie, Yuhao Yang 외

Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is esse…

AI AgentBenchmarkingLanguage ModellingLarge Language Model+1

MobiAgent: A Systematic Framework for Customizable Mobile Agents

2025-08-30 · Cheng Zhang, Erhu Feng, Xi Zhao, Yisheng Zhao 외 arxiv

With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant…

LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning

2026-05-08 · Yubin Wu, Zicheng Cai, Liping Ning, Hua Wang 외 arxiv

Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device agents are constrained by limited model capacity, and further perfo…

Reinforcement LearningKnowledge Distillation