Image de couverture de livre

When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Su, Junwei, Wu, Chuan
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When Do Neural Nets Outperform Boosted Trees on Tabular Data?
par: McElfresh, Duncan, et autres
Publié: (2023)

What Limits Agentic Systems Efficiency?
par: Bian, Song, et autres
Publié: (2025)

Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks
par: Su, Junwei, et autres
Publié: (2024)

When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
par: Schäfer, Lukas, et autres
Publié: (2026)

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
par: Liu, Xianyang, et autres
Publié: (2026)

Hybrid Agentic AI and Multi-Agent Systems in Smart Manufacturing
par: Farahani, Mojtaba A., et autres
Publié: (2025)

Learning to Construct Practical Agentic Systems
par: Kumar, Aditya, et autres
Publié: (2026)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
par: Wang, Bin, et autres
Publié: (2026)

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
par: Yao, Bohan, et autres
Publié: (2025)

ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization
par: Su, Hongyuan, et autres
Publié: (2026)

Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
par: Aryal, Manish, et autres
Publié: (2026)

AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems
par: Kadekodi, Rohan, et autres
Publié: (2025)

When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
par: Wang, Zehao, et autres
Publié: (2026)

GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
par: Xu, Haofeng, et autres
Publié: (2026)

Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation
par: Ma, Xiaowen, et autres
Publié: (2025)

Efficiency Robustness of Dynamic Deep Learning Systems
par: Rathnasuriya, Ravishka, et autres
Publié: (2025)

Learning under Quantization for High-Dimensional Linear Regression
par: Zhang, Dechen, et autres
Publié: (2025)

Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
par: Feng, Lang, et autres
Publié: (2026)

AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learning
par: Jiang, Qile, et autres
Publié: (2025)

SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data
par: Liu, Dianyu, et autres
Publié: (2026)

Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
par: Kim, Jihwan, et autres
Publié: (2026)

Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representation
par: Walczak, Jakub
Publié: (2025)

Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System
par: Zhao, Yang, et autres
Publié: (2024)

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems
par: Liu, Rui, et autres
Publié: (2025)

When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
par: Amir, Michael, et autres
Publié: (2025)

Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
par: Yang, Huchen, et autres
Publié: (2026)

Model Comparisons: XNet Outperforms KAN
par: Li, Xin, et autres
Publié: (2024)

Disaster Management in the Era of Agentic AI Systems: A Vision for Collective Human-Machine Intelligence for Augmented Resilience
par: Li, Bo, et autres
Publié: (2025)

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
par: Kim, Donghwan, et autres
Publié: (2026)

Emergent Bias and Fairness in Multi-Agent Decision Systems
par: Madigan, Maeve, et autres
Publié: (2025)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
par: Zeng, Yifan, et autres
Publié: (2026)

Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
par: Yang, Yingxuan, et autres
Publié: (2026)

RMA: an Agentic System for Research-Level Mathematical Problems
par: Zhao, Zelin, et autres
Publié: (2026)

Recursive Multi-Agent Systems
par: Yang, Xiyuan, et autres
Publié: (2026)

Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning
par: Tang, Wenlong
Publié: (2025)

Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systems
par: Abadi, Alireza Saleh, et autres
Publié: (2025)

Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know
par: Manchingal, Shireen Kudukkil
Publié: (2025)

On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
par: Liu, Tong, et autres
Publié: (2026)

Multi-Agent Debate: A Unified Agentic Framework for Tabular Anomaly Detection
par: Wang, Pinqiao, et autres
Publié: (2026)

Agent-Oriented Planning in Multi-Agent Systems
par: Li, Ao, et autres
Publié: (2024)