Cover Image

Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Tianxiao, Ma, Yixing, Wen, Haiquan, Huang, Zhenglin, Zhou, Qianyu, Fu, Zeyu, Cheng, Guangliang
Format:	Preprint
Published:	2026
Subjects:	Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment
by: Hu, Jinwei, et al.
Published: (2025)

Position: Towards a Responsible LLM-empowered Multi-Agent Systems
by: Hu, Jinwei, et al.
Published: (2025)

When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges
by: Liang, Sichu, et al.
Published: (2026)

Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System
by: Du, Haikuo, et al.
Published: (2025)

How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
by: He, Zeyu, et al.
Published: (2026)

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

Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
by: Cho, Young-Min, et al.
Published: (2025)

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
by: Zhang, Ruijia, et al.
Published: (2025)

Relaxing Constraints in Anonymous Multi Agent Path Finding for Large Agents
by: Dergachev, Stepan, et al.
Published: (2026)

GameChat: Multi-LLM Dialogue for Safe, Agile, and Socially Optimal Multi-Agent Navigation in Constrained Environments
by: Mahadevan, Vagul, et al.
Published: (2025)

Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems
by: Guan, Zhaoyang, et al.
Published: (2026)

Pancake: Hierarchical Memory System for Multi-Agent LLM Serving
by: Hu, Zhengding, et al.
Published: (2026)

The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems
by: Kulshreshtha, Devang, et al.
Published: (2025)

Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration
by: Song, Xinyuan, et al.
Published: (2025)

MDG: Masked Denoising Generation for Multi-Agent Behavior Modeling in Traffic Environments
by: Huang, Zhiyu, et al.
Published: (2025)

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
by: Ye, Yulei, et al.
Published: (2026)

AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization
by: Yang, Zijiu, et al.
Published: (2026)

Behavior Modeling for Training-free Building of Private Domain Multi Agent System
by: Cho, Won Ik, et al.
Published: (2025)

Situational Awareness for Safe and Robust Multi-Agent Interactions Under Uncertainty
by: Alcorn, Benjamin, et al.
Published: (2025)

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

Fault Tolerant Multi-Agent Learning with Adversarial Budget Constraints
by: Mguni, David, et al.
Published: (2025)

Insider Attacks in Multi-Agent LLM Consensus Systems
by: Sun, Xiaolin, et al.
Published: (2026)

LLM Multi-Agent Systems: Challenges and Open Problems
by: Han, Shanshan, et al.
Published: (2024)

Conjunctive Prompt Attacks in Multi-Agent LLM Systems
by: Arif, Nokimul Hasan, et al.
Published: (2026)

MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs
by: Wang, Qian, et al.
Published: (2024)

Multi-Agent Systems Should be Treated as Principal-Agent Problems
by: Rauba, Paulius, et al.
Published: (2026)

Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
by: Cuadros, Diego F., et al.
Published: (2026)

Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System
by: Kostka, Adam, et al.
Published: (2025)

Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form
by: Wang, Xuefeng, et al.
Published: (2026)

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
by: Pan, Shuai, et al.
Published: (2026)

AgentScope: A Flexible yet Robust Multi-Agent Platform
by: Gao, Dawei, et al.
Published: (2024)

DePAint: A Decentralized Safe Multi-Agent Reinforcement Learning Algorithm considering Peak and Average Constraints
by: Hassan, Raheeb, et al.
Published: (2023)

Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems
by: Zamojska, Monika, et al.
Published: (2025)

Differentiable Environment-Trajectory Co-Optimization for Safe Multi-Agent Navigation
by: Gao, Zhan, et al.
Published: (2026)

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
by: Zhang, Guibin, et al.
Published: (2024)

CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems
by: Ma, Ziyang, et al.
Published: (2026)

ALAS: Transactional and Dynamic Multi-Agent LLM Planning
by: Geng, Longling, et al.
Published: (2025)

LLM Harmony: Multi-Agent Communication for Problem Solving
by: Rasal, Sumedh
Published: (2024)

TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
by: Kavathekar, Ishan, et al.
Published: (2025)

Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework
by: Binkyte, Ruta
Published: (2025)