paper-with-me

홈 › Papers

AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System

2025-10-02 · Hui Yi Leong, Yuheng Li, Yuqing Wu, Wenwen Ouyang, Wei Zhu, Jiechao Gao, Wei Han arxiv

Although large language models (LLMs) have revolutionized natural language processing capabilities, their practical implementation as autonomous multi-agent systems (MAS) for industrial problem-solving encounters persistent barriers. Conventional MAS architectures are fundamentally restricted by inflexible, hand-crafted graph topologies that lack contextual responsiveness, resulting in diminished efficacy across varied academic and commercial workloads. To surmount these constraints, we introduce AMAS, a paradigm-shifting framework that redefines LLM-based MAS through a novel dynamic graph designer. This component autonomously identifies task-specific optimal graph configurations via lightweight LLM adaptation, eliminating the reliance on monolithic, universally applied structural templates. Instead, AMAS exploits the intrinsic properties of individual inputs to intelligently direct query trajectories through task-optimized agent pathways. Rigorous validation across question answering, mathematical deduction, and code generation benchmarks confirms that AMAS systematically exceeds state-of-the-art single-agent and multi-agent approaches across diverse LLM architectures. Our investigation establishes that context-sensitive structural adaptability constitutes a foundational requirement for high-performance LLM MAS deployments.

📄 PDF Abstract BibTeX arXiv:2510.01617

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringCode Generation

Similar Papers 제목 키워드 기반

BAMAS: Structuring Budget-Aware Multi-Agent Systems

2025-11-26 · Liming Yang, Junyu Luo, Xuanzhe Liu, Yiling Lou 외 arxiv

Large language model (LLM)-based multi-agent systems have emerged as a powerful paradigm for enabling autonomous agents to solve complex tasks. As these systems scale in complexity, cost becomes an important consideratio…

Reinforcement Learning

AC2C: Adaptively Controlled Two-Hop Communication for Multi-Agent Reinforcement Learning

2023-02-24 · Xuefeng Wang, Xinran Li, Jiawei Shao, Jun Zhang

Learning communication strategies in cooperative multi-agent reinforcement learning (MARL) has recently attracted intensive attention. Early studies typically assumed a fully-connected communication topology among agents…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Vocal Bursts Valence Prediction

PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis

2026-05-18 · Jinrang Jia, Zhenjia Li, Yijiang Hu, Yifeng Shi arxiv

Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagi…

3D Generation

Federated Fine-Tuning of Foundation Models via Probabilistic Masking

2023-11-29 · Vasileios Tsouvalas, Yuki Asano, Aaqib Saeed

Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is challenging due to substantial communication …

Federated Learning

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training

2023-02-20 · Chang Chen, Min Li, Zhihua Wu, dianhai yu 외

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the mo…