Cover Image

The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Jiin, Shin, Byeongjun, Chung, Jinha, Rhu, Minsoo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Hardware Architecture
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers
by: Yeo, Gwangoo, et al.
Published: (2024)

PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models
by: Cho, Eunyeong, et al.
Published: (2026)

PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models
by: Lee, Yunjae, et al.
Published: (2024)

Agent-X: Full Pipeline Acceleration of On-device AI Agents
by: Chung, Jinha, et al.
Published: (2026)

Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology
by: Hyun, Bongjoon, et al.
Published: (2023)

vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training
by: Bang, Jehyeon, et al.
Published: (2023)

PIM-malloc: A Fast and Scalable Dynamic Memory Allocator for Processing-In-Memory (PIM) Architectures
by: Lee, Dongjae, et al.
Published: (2025)

PIM-MMU: A Memory Management Unit for Accelerating Data Transfers in Commercial PIM Systems
by: Lee, Dongjae, et al.
Published: (2024)

SwarmIO: Towards 100 Million IOPS SSD Emulation for Next-generation GPU-centric Storage Systems
by: Kim, Hyeseong, et al.
Published: (2026)

LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit
by: Liu, Chang, et al.
Published: (2025)

AI Accelerators for Large Language Model Inference: Architecture Analysis and Scaling Strategies
by: Sharma, Amit
Published: (2025)

EEsizer: LLM-Based AI Agent for Sizing of Analog and Mixed Signal Circuit
by: Liu, Chang, et al.
Published: (2025)

Mamba-X: An End-to-End Vision Mamba Accelerator for Edge Computing Devices
by: Yoon, Dongho, et al.
Published: (2025)

The AetherFloat Family: Block-Scale-Free Quad-Radix Floating-Point Architectures for AI Accelerators
by: Morisaki, Keita
Published: (2026)

Accelerating Diffusion Models for Generative AI Applications with Silicon Photonics
by: Suresh, Tharini, et al.
Published: (2026)

M100: An Orchestrated Dataflow Architecture Powering General AI Computing
by: Xie, Yan, et al.
Published: (2026)

Token-Picker: Accelerating Attention in Text Generation with Minimized Memory Transfer via Probability Estimation
by: Park, Junyoung, et al.
Published: (2024)

AiEDA: An Open-Source AI-Aided Design Library for Design-to-Vector
by: Qiu, Yihang, et al.
Published: (2025)

From LLM to Silicon: RL-Driven ASIC Architecture Exploration for On-Device AI Inference
by: Ganti, Ravindra, et al.
Published: (2026)

A Survey of Circuit Foundation Model: Foundation AI Models for VLSI Circuit Design and EDA
by: Fang, Wenji, et al.
Published: (2025)

FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI
by: Cho, Eun-Su, et al.
Published: (2025)

Breaking the HBM Bit Cost Barrier: Domain-Specific ECC for AI Inference Infrastructure
by: Xie, Rui, et al.
Published: (2025)

MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI
by: Jiang, Zijun, et al.
Published: (2025)

Hardware-Aware Data and Instruction Mapping for AI Tasks: Balancing Parallelism, I/O and Memory Tradeoffs
by: Chowdhury, Md Rownak Hossain, et al.
Published: (2025)

QuArch: A Question-Answering Dataset for AI Agents in Computer Architecture
by: Prakash, Shvetank, et al.
Published: (2025)

GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models
by: Fu, Yonggan, et al.
Published: (2023)

Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics
by: Xu, Bin, et al.
Published: (2025)

Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators
by: Alexandridis, Kosmas, et al.
Published: (2025)

DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models
by: Shao, Kunming, et al.
Published: (2026)

GCN-ABFT: Low-Cost Online Error Checking for Graph Convolutional Networks
by: Peltekis, Christodoulos, et al.
Published: (2024)

A Cost-Efficient FPGA Implementation of Tiny Transformer Model using Neural ODE
by: Okubo, Ikumi, et al.
Published: (2024)

Position Paper: From Edge AI to Adaptive Edge AI
by: Pittorino, Fabrizio, et al.
Published: (2026)

VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers
by: Wang, Run, et al.
Published: (2025)

Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy
by: Xie, Peichen, et al.
Published: (2025)

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
by: Bambhaniya, Abhimanyu, et al.
Published: (2024)

Autoformalizing Memory Specifications with Agents
by: Ernst, Jan Ole, et al.
Published: (2026)

TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog
by: Abdollahi, Armin, et al.
Published: (2026)

Periodic Online Testing for Sparse Systolic Tensor Arrays
by: Peltekis, Christodoulos, et al.
Published: (2025)

On Robustness and Generalization of ML-Based Congestion Predictors to Valid and Imperceptible Perturbations
by: Holtz, Chester, et al.
Published: (2024)

Memory-Efficient FPGA Implementation of Stochastic Simulated Annealing
by: Shin, Duckgyu, et al.
Published: (2026)