Score: 2

Democratizing Agentic AI with Fast Test-Time Scaling on the Edge

Published: August 29, 2025 | arXiv ID: 2509.00195v1

By: Hao Mark Chen , Zhiwen Mo , Guanxi Lu and more

BigTech Affiliations: Microsoft

Potential Business Impact:

Lets small computers think like big ones.

Business Areas:
Intelligent Systems Artificial Intelligence, Data and Analytics, Science and Engineering

Deploying agentic AI on edge devices is crucial for privacy and responsiveness, but memory constraints typically relegate these systems to smaller Large Language Models (LLMs) with inferior reasoning capabilities. Test-Time Scaling (TTS) can bridge this reasoning gap by dedicating more compute during inference, but existing methods incur prohibitive overhead on edge hardware. To overcome this, we introduce FlashTTS, a serving system that makes TTS practical for memory-constrained LLM reasoning. FlashTTS introduces three synergistic optimizations: (i) Speculative Beam Extension to mitigate system stragglers from irregular reasoning paths; (ii) Asymmetric Multi-Model Memory Allocation to dynamically balance memory between generation and verification; and (iii) Dynamic Prefix-Aware Scheduling to maximize KV-cache reuse. Built as a plug-and-play library for vLLM, FlashTTS enables edge LLMs on a single consumer GPU (24 GB) to match the accuracy and latency of large cloud models. Our evaluation demonstrates that FlashTTS achieves an average 2.2x higher goodput and reduces latency by 38%-68% compared to a vLLM baseline, paving the way for democratized, high-performance agentic AI on edge devices.

Country of Origin
πŸ‡ΊπŸ‡Έ πŸ‡¬πŸ‡§ United Kingdom, United States

Page Count
14 pages

Category
Computer Science:
Machine Learning (CS)