Image de couverture de livre

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Donghwan, Singh, Prakhar, Min, Younghoon, Kim, Jongryool, Park, Jongse, Maeng, Kiwan
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
par: Kim, Donghwan, et autres
Publié: (2025)

CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation
par: Liu, Jinyu, et autres
Publié: (2025)

MARC: Multimodal and Multi-Task Agentic Retrieval-Augmented Generation for Cold-Start Recommender System
par: Cho, Seung Hwan, et autres
Publié: (2025)

LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale
par: Cho, Jaehong, et autres
Publié: (2024)

LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure
par: Cho, Jaehong, et autres
Publié: (2025)

Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation
par: Kim, Donghwan, et autres
Publié: (2026)

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
par: Kim, Donghwan, et autres
Publié: (2026)

Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?
par: Kim, Donghwan, et autres
Publié: (2026)

Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
par: Kim, Donghwan, et autres
Publié: (2024)

Access Controlled Website Interaction for Agentic AI with Delegated Critical Tasks
par: Kim, Sunyoung, et autres
Publié: (2026)

Adaptive Policy Backbone via Shared Network
par: Park, Bumgeun, et autres
Publié: (2025)

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
par: Cho, Jaehong, et autres
Publié: (2026)

LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks
par: Zeng, Yucheng, et autres
Publié: (2026)

HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks
par: Kim, Donghwan, et autres
Publié: (2023)

System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI
par: Kim, Sejin, et autres
Publié: (2024)

TriCEGAR: A Trace-Driven Abstraction Mechanism for Agentic AI
par: Koohestani, Roham, et autres
Publié: (2026)

Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety
par: Kim, Yubin, et autres
Publié: (2025)

Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
par: Kim, Taehun, et autres
Publié: (2026)

Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks
par: Kim, Jeongmo, et autres
Publié: (2025)

Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes
par: Lee, Donghwan, et autres
Publié: (2023)

AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
par: Kim, Hojoon, et autres
Publié: (2026)

SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use
par: Jeon, Changhyun, et autres
Publié: (2025)

Autotelic Reinforcement Learning: Exploring Intrinsic Motivations for Skill Acquisition in Open-Ended Environments
par: Srivastava, Prakhar, et autres
Publié: (2025)

Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs
par: Oh, Gyutaek, et autres
Publié: (2025)

A Policy-Driven Runtime Layer for Agentic LLM Serving
par: Zhang, Rui, et autres
Publié: (2026)

MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation
par: Park, Jiin, et autres
Publié: (2025)

ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search
par: Kim, Myungchul, et autres
Publié: (2026)

PMAx: An Agentic Framework for AI-Driven Process Mining
par: Antonov, Anton, et autres
Publié: (2026)

Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
par: Park, Jongchan, et autres
Publié: (2025)

QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety
par: Lee, Taegyeong, et autres
Publié: (2025)

From Features to Actions: Explainability in Traditional and Agentic AI Systems
par: Chaduvula, Sindhuja, et autres
Publié: (2026)

SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
par: Park, Keondo, et autres
Publié: (2026)

Sign-Separated Finite-Time Error Analysis of Q-Learning
par: Lee, Donghwan
Publié: (2026)

MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training
par: Kim, Yongwan, et autres
Publié: (2026)

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment
par: Bajaj, Tanav Singh, et autres
Publié: (2026)

Bias or Optimality? Disentangling Bayesian Inference and Learning Biases in Human Decision-Making
par: Godara, Prakhar
Publié: (2025)

ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
par: Li, Haoyun, et autres
Publié: (2026)

Agentic AI-Driven Technical Troubleshooting for Enterprise Systems: A Novel Weighted Retrieval-Augmented Generation Paradigm
par: Khanda, Rajat
Publié: (2024)

TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-Scale
par: Yoon, Dongha, et autres
Publié: (2025)

AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care
par: Yadav, Preyash, et autres
Publié: (2026)