Copertina

Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Yingxuan, Qu, Chengrui, Wen, Muning, Shi, Laixi, Wen, Ying, Zhang, Weinan, Wierman, Adam, Gu, Shangding
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
di: Gu, Shangding, et al.
Pubblicazione: (2025)

LLM-based Multi-Agent Systems: Techniques and Business Perspectives
di: Yang, Yingxuan, et al.
Pubblicazione: (2024)

Agent Exchange: Shaping the Future of AI Agent Economics
di: Yang, Yingxuan, et al.
Pubblicazione: (2025)

Reinforcing Language Agents via Policy Optimization with Action Decomposition
di: Wen, Muning, et al.
Pubblicazione: (2024)

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
di: Zhou, Ruiwen, et al.
Pubblicazione: (2024)

Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization
di: Qu, Chengrui, et al.
Pubblicazione: (2026)

MARFT: Multi-Agent Reinforcement Fine-Tuning
di: Liao, Junwei, et al.
Pubblicazione: (2025)

Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
di: Wen, Muning, et al.
Pubblicazione: (2024)

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
di: Liu, Xianyang, et al.
Pubblicazione: (2026)

Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web
di: Nie, Xiaohang, et al.
Pubblicazione: (2026)

A Survey of AI Agent Protocols
di: Yang, Yingxuan, et al.
Pubblicazione: (2025)

SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer
di: As, Yarden, et al.
Pubblicazione: (2025)

Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization
di: Gu, Shangding
Pubblicazione: (2026)

PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning
di: Hu, Kun, et al.
Pubblicazione: (2025)

Position: Agentic AI System Is a Foreseeable Pathway to AGI
di: Liao, Junwei, et al.
Pubblicazione: (2026)

KL-regularization Itself is Differentially Private in Bandits and RLHF
di: Zhang, Yizhou, et al.
Pubblicazione: (2025)

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
di: Liao, Junwei, et al.
Pubblicazione: (2026)

Agentic Web: Weaving the Next Web with AI Agents
di: Yang, Yingxuan, et al.
Pubblicazione: (2025)

MonoScale: Scaling Multi-Agent System with Monotonic Improvement
di: Shao, Shuai, et al.
Pubblicazione: (2026)

PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
di: Chai, Huacan, et al.
Pubblicazione: (2025)

Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data
di: Qu, Chengrui, et al.
Pubblicazione: (2024)

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
di: Al-Tawaha, Ahmad, et al.
Pubblicazione: (2026)

Autonomous Goal Detection and Cessation in Reinforcement Learning: A Case Study on Source Term Estimation
di: Shi, Yiwei, et al.
Pubblicazione: (2024)

Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
di: Shi, Laixi, et al.
Pubblicazione: (2024)

Understanding and Optimizing Agentic Workflows via Shapley value
di: Yang, Yingxuan, et al.
Pubblicazione: (2025)

Training Generalizable Collaborative Agents via Strategic Risk Aversion
di: Qu, Chengrui, et al.
Pubblicazione: (2026)

Scaling Behavior of Single LLM-Driven Multi-Agent Systems
di: Li, Jialing, et al.
Pubblicazione: (2026)

Which LLM Multi-Agent Protocol to Choose?
di: Du, Hongyi, et al.
Pubblicazione: (2025)

Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
di: Gu, Shangding, et al.
Pubblicazione: (2024)

Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
di: Feng, Xidong, et al.
Pubblicazione: (2023)

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

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
di: Shi, Laixi, et al.
Pubblicazione: (2024)

Conceptual Belief-Informed Reinforcement Learning
di: Gu, Xingrui, et al.
Pubblicazione: (2024)

AgentSME for Simulating Diverse Communication Modes in Smart Education
di: Yang, Wen-Xi, et al.
Pubblicazione: (2025)

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
di: Jain, Jitesh, et al.
Pubblicazione: (2025)

Evaluating Theory of Mind and Internal Beliefs in LLM-Based Multi-Agent Systems
di: Kostka, Adam, et al.
Pubblicazione: (2026)

MIRIX: Multi-Agent Memory System for LLM-Based Agents
di: Wang, Yu, et al.
Pubblicazione: (2025)

Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
di: Yuen, Sizhe, et al.
Pubblicazione: (2025)

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
di: Wu, Shanglin, et al.
Pubblicazione: (2026)

P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training
di: Yang, Yingxuan, et al.
Pubblicazione: (2024)