3 papers
cs.AI2026
Agent-X: Full Pipeline Acceleration of On-device AI Agents
Jinha Chung, Byeongjun Shin, Jiin Kim +1
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 fra…
cs.AI2026
SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding
Jehyeon Bang, Eunyeong Cho, Ranggi Hwang +2
The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating p…
cs.LG2026
The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective
Jiin Kim, Byeongjun Shin, Jinha Chung +1
Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with exte…