Copertina

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yutong, Xiong, Siyuan, Liu, Xuebo, Zhou, Wenkang, Ding, Liang, Zhang, Miao, Zhang, Min
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
di: Wang, Zhexuan, et al.
Pubblicazione: (2025)

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
di: Tian, Chunhao, et al.
Pubblicazione: (2025)

MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
di: Wang, Zhexuan, et al.
Pubblicazione: (2026)

DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
di: Wang, Yutong, et al.
Pubblicazione: (2024)

Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
di: Zhu, Guobin, et al.
Pubblicazione: (2025)

FlowTS: Time Series Generation via Rectified Flow
di: Hu, Yang, et al.
Pubblicazione: (2024)

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
di: Deng, Hexuan, et al.
Pubblicazione: (2024)

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
di: Lu, Yunhong, et al.
Pubblicazione: (2026)

Strategic Learning for Disturbance Rejection in Multi‐Agent Systems: Nash and Minmax in Graphical Games
di: Xinyang Wang, et al.
Pubblicazione: (2025)

Dynamic Role Assignment for Multi-Agent Debate
di: Zhang, Miao, et al.
Pubblicazione: (2026)

Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection
di: Wang, Yutong, et al.
Pubblicazione: (2026)

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
di: Zhu, Guobin, et al.
Pubblicazione: (2025)

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation
di: Ye, Wen, et al.
Pubblicazione: (2025)

MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
di: Wang, Kun, et al.
Pubblicazione: (2025)

SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
di: Ding, Yifeng, et al.
Pubblicazione: (2026)

Optimized Flow Control based on Automatic Differentiation in Compressible Turbulent Channel Flows
di: Wang, Wenkang, et al.
Pubblicazione: (2024)

Adaptive Dropout for Pruning Conformers
di: Kubo, Yotaro, et al.
Pubblicazione: (2024)

Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
di: Lu, Qingyu, et al.
Pubblicazione: (2025)

Prune4Web: DOM Tree Pruning Programming for Web Agent
di: Zhang, Jiayuan, et al.
Pubblicazione: (2025)

Preserving Core Structures of Social Networks via Information Guided Multi-Step Graph Pruning
di: Hu, Yutong, et al.
Pubblicazione: (2025)

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
di: Wu, Yutong, et al.
Pubblicazione: (2025)

AgentAsk: Multi-Agent Systems Need to Ask
di: Lin, Bohan, et al.
Pubblicazione: (2025)

FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
di: Jung, Dongwon, et al.
Pubblicazione: (2025)

M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation
di: Shao, Weizi, et al.
Pubblicazione: (2025)

LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents
di: Zhang, Ke, et al.
Pubblicazione: (2025)

Multi-Agent Consensus Seeking via Large Language Models
di: Chen, Huaben, et al.
Pubblicazione: (2023)

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
di: Yang, Yingxuan, et al.
Pubblicazione: (2025)

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
di: Li, Fanxiao, et al.
Pubblicazione: (2026)

Finite-time Non-overshooting Leader-following Consensus Control for Multi-Agent Systems
di: Li, Min, et al.
Pubblicazione: (2024)

A Lyapunov-based MPC for Distributed Multi Agent Systems with Time Delays and Packet Dropouts using Hidden Markov Models
di: Solyman, Loaie, et al.
Pubblicazione: (2025)

TasTe: Teaching Large Language Models to Translate through Self-Reflection
di: Wang, Yutong, et al.
Pubblicazione: (2024)

SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems
di: Zhang, Dong, et al.
Pubblicazione: (2024)

Divergence-Suppressing Couplings for Rectified Flow
di: Min, Yimeng, et al.
Pubblicazione: (2026)

Quantized Iterative Learning Control for Consensus of Nonlinear Impulsive Multi‐Agent Systems With Inter‐Channel Encoding‐Decoding Mechanisms and Packet Dropouts
di: Hongjin Zhang, et al.
Pubblicazione: (2025)

The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models
di: Zhang, Junyao, et al.
Pubblicazione: (2026)

Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout
di: Fiscko, Carmel, et al.
Pubblicazione: (2023)

Optimizing Generative AI Networking: A Dual Perspective with Multi-Agent Systems and Mixture of Experts
di: Zhang, Ruichen, et al.
Pubblicazione: (2024)

Efficient Rectified Flow for Image Fusion
di: Wang, Zirui, et al.
Pubblicazione: (2025)

WSI-Agents: A Collaborative Multi-Agent System for Multi-Modal Whole Slide Image Analysis
di: Lyu, Xinheng, et al.
Pubblicazione: (2025)

Reinforced Collaboration in Multi-Agent Flow Networks
di: Wang, Zheng, et al.
Pubblicazione: (2026)