MAT-Agent: Adaptive Multi-Agent Training Optimization

2025-10-10 · Jusheng Zhang, Kaitong Cai, Yijia Fan, Ningyuan Liu, Keze Wang arxiv

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We propose MAT-Agent, a novel multi-agent framework that reimagines training as a collaborative, real-time optimization process. By deploying autonomous agents to dynamically tune data augmentation, optimizers, learning rates, and loss functions, MAT-Agent leverages non-stationary multi-armed bandit algorithms to balance exploration and exploitation, guided by a composite reward harmonizing accuracy, rare-class performance, and training stability. Enhanced with dual-rate exponential moving average smoothing and mixed-precision training, it ensures robustness and efficiency. Extensive experiments across Pascal VOC, COCO, and VG-256 demonstrate MAT-Agent's superiority: it achieves an mAP of 97.4 (vs. 96.2 for PAT-T), OF1 of 92.3, and CF1 of 91.4 on Pascal VOC; an mAP of 92.8 (vs. 92.0 for HSQ-CvN), OF1 of 88.2, and CF1 of 87.1 on COCO; and an mAP of 60.9, OF1 of 70.8, and CF1 of 61.1 on VG-256. With accelerated convergence and robust cross-domain generalization, MAT-Agent offers a scalable, intelligent solution for optimizing complex visual models, paving the way for adaptive deep learning advancements.

📄 PDF Abstract BibTeX arXiv:2510.17845

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Label Image Classification Domain Generalization Data Augmentation

ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference Evolution

2026-02-02 · Ujin Jeon, Jiyong Kwon, Madison Ann Sullivan, Caleb Eunho Lee 외 arxiv

Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, yet they predominantly rely on frozen agents or static fine-tuning pipelines. To address this limitation, our primary contri…

Adaptive Robust Estimator for Multi-Agent Reinforcement Learning

2026-03-23 · Zhongyi Li, Wan Tian, Jingyu Chen, Kangyao Huang 외 arxiv

Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revisio…

Multi-agent Reinforcement Learning Mathematical Reasoning

Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning

2026-07-12 · Sudipto Ghosh, Tanmoy Chakraborty arxiv

Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent comm…

ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination

2025-10-10 · Charidimos Papadakis, Angeliki Dimitriou, Giorgos Filandrianos, Maria Lymperaiou 외 arxiv

Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market n…

MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research

2026-02-03 · Yifan Shi, Jiayi Wang, Minyi Wu, Ye Fan 외 arxiv

Operations Research (OR) relies on expert-driven modeling--a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization model…