Multiagent Systems Papers

Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents Zhuofu Chen, Rui Pan, Yinwei Dai, Ravi Netravali arxiv.org/abs/2605.08580 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Too Many Specialists: Emergent Inefficiencies and Bottlenecks for Multi-agent Ad-hoc Collaboration Benjamin Panny, Shashank Mehrotra, Zahra Zahedi, Teruhisa Misu, Kumar Akash arxiv.org/abs/2605.08540 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙷𝙲]

SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics Yicheng Zhu, Yang Chen, Tao Li, Zilin Bian arxiv.org/abs/2605.08528 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝚁𝙾]

Insider Attacks in Multi-Agent LLM Consensus Systems Xiaolin Sun, Zixuan Liu, Yibin Hu, Zizhan Zheng arxiv.org/abs/2605.08268 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Designing Intelligent Enterprise Agents: A Capability-Aligned Multi-Agent Architecture John deVadoss arxiv.org/abs/2605.08258 [𝚌𝚜.𝙼𝙰]

Emergence of Social Reality of Emotion through a Social Allostasis Model with Dynamic Interpretants Kentaro Nomura, Yushi Tsubamoto, Takato Horii arxiv.org/abs/2605.07761 [𝚌𝚜.𝙼𝙰]

Synchronizing Minds through Collective Predictive Coding: A Computational Model of Parent-Infant Homeostatic Co-Regulation Yushi Tsubamoto, Takato Horii arxiv.org/abs/2605.07524 [𝚌𝚜.𝙼𝙰]

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing Jianming Chen, Yawen Wang, Junjie Wang, Zhe Liu, Qing Wang, Fanjiang Xu arxiv.org/abs/2605.07414 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁]

Rethinking Priority Scheduling for Sequential Multi-Agent Decision Making in Stackelberg Games Xiangyu Liu, Liang Zhang, Bo Jin, Ziqi Wei arxiv.org/abs/2605.07240 [𝚌𝚜.𝙼𝙰]

Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning Yuyang Zhang, Haldun Balim, Na Li arxiv.org/abs/2605.07101 [𝚌𝚜.𝙼𝙰 𝚜𝚝𝚊𝚝.𝙼𝙻]

Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems Lynnette Hui Xian Ng, Iain J. Cruickshank, Adrian Xuan Wei Lim, Kathleen M. Carley arxiv.org/abs/2605.07069 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙲𝚈]

The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search David Farr, Iain Cruickshank, Kate Starbird, Jevin West arxiv.org/abs/2605.06988 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙸𝚃 𝚌𝚜.𝚁𝙾]

Generalising Travel Time Prediction To Varying Route Choices In Urban Networks Łukasz Gorczyca, Kacper Drozd, Michał Bujak, Rafał Kucharski arxiv.org/abs/2605.06918 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶]

Coordination Matters: Evaluation of Cooperative Multi-Agent Reinforcement Learning Maria Ana Cardei, Matthew Landers, Afsaneh Doryab arxiv.org/abs/2605.06557 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization Zijiu Yang, Zixiang Zhang, Shunpu Tang, Qianqian Yang, Zhiguo Shi arxiv.org/abs/2605.06443 [𝚌𝚜.𝙼𝙰]

Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs Elizabeth Mieczkowski, Alexander Ku, Tiwalayo Eisape, Dilip Arumugam, John Matters, Katherine M. Collins, Ilia Sucholutsky, Thomas L. Griffiths arxiv.org/abs/2605.06320 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻]

Power-Efficiency and Scalability Analysis of Magnetically-Actuated Satellite Swarms via Convex Optimization Yuta Takahashi, Seang Shim, Hiraku Sakamoto, … arxiv.org/abs/2605.06286 [𝚌𝚜.𝙼𝙰] 💬Submitted to IEEE Transactions on Aerospace and Electronic Systems (Correspondence)

Multiagent Stochastic Shortest Path Problem Martin Jonáš, Antonín Kučera, Vojtěch Kůr, Jan Mačák, Vojtěch Řehák arxiv.org/abs/2605.06056 [𝚌𝚜.𝙼𝙰] 💬A full version of the paper that was presented at IJCAI 2026

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes Jingjie Ning, Xiaochuan Li, Ji Zeng, Hao Kang, Chenyan Xiong arxiv.org/abs/2605.05724 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems Huchen Yang, Xinghao Dong, Dan Negrut, Jin-Long Wu arxiv.org/abs/2605.05703 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]