Multiagent Systems Papers

A Reinforcement Learning Inspired Latent Yield Based Adaptive Algorithm Switching Mechanism Jayprakash S. Nair, Jimson Mathew, Shivashankar B. Nair arxiv.org/abs/2605.24436 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶 𝚌𝚜.𝚁𝙾]

ProofAgent Harness: Open Infrastructure for Adversarial Evaluation of AI Agents Fouad Bousetouane arxiv.org/abs/2605.24134 [𝚌𝚜.𝙼𝙰]

The Communication Complexity of Instant-Runoff Voting Élie de Panafieu, François Durand, Jérôme Lang arxiv.org/abs/2605.23743 [𝚌𝚜.𝙼𝙰]

Safety, Liveness, and Fairness in Quantitative Argumentation Dialogues Arunavo Ganguly, Julian Alfredo Mendez, Timotheus Kampik arxiv.org/abs/2605.23578 [𝚌𝚜.𝙼𝙰]

ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning Elie Abboud, Oren Gal arxiv.org/abs/2605.23562 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework Hyunjee Park, Hayoung Chung arxiv.org/abs/2605.23273 [𝚌𝚜.𝙼𝙰]

SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate Weifan Jiang, Rana Shahout, Minghao Li, Zhenting Qi, Yilun Du, Michael Mitzenmacher, Minlan Yu arxiv.org/abs/2605.23099 [𝚌𝚜.𝙼𝙰]

How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning Zeyu He, Hannah Kim, Dan Zhang, Estevam Hruschka arxiv.org/abs/2605.23023 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙷𝙲]

Self-Evolving Multi-Agent Systems via Decentralized Memory Guangya Hao, Yunbo Long, Zhuokai Zhao arxiv.org/abs/2605.22721 [𝚌𝚜.𝙼𝙰]

A Generalized Nash Equilibrium-Seeking Scheme for Trauma Resuscitation Promise Ekpo, Angelique Taylor, Lekan Molu arxiv.org/abs/2605.22661 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙳𝙲 𝚌𝚜.𝙶𝚃 𝚎𝚎𝚜𝚜.𝚂𝚈]

Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators Chengcheng Wang, Qinhua Xie, Wei He, Jianyuan Guo, Shiqi Wang, Chang Xu arxiv.org/abs/2605.22343 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝚂𝙴]

ACCoRD: Actor-Critic Conflict Resolution with Deep learning for O-RAN xApps Cezary Adamczyk, Adrian Kliks arxiv.org/abs/2605.22306 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Emergence of agriculture in an artificial society of reinforcement learning agents Gautier Hamon, Martí Sánchez-Fibla, Clément Moulin-Frier, Ricard Solé arxiv.org/abs/2605.22256 [𝚌𝚜.𝙼𝙰]

Planning, Scheduling, and Behavior in EV Charging Systems: A Critical Survey and Trilemma Framework Peiyan Xiao, Yuheng Li, Ayan Mukhopadhyay, Sai Krishna Ghanta, Sabur Baidya, Yanhai Xiong arxiv.org/abs/2605.21665 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Argo: Efficient Importance Labeling for Enterprise Email Systems Siddhant Ray, Ganesh Ananthanarayanan, Kevin Chian, Yan Guo, Cristina St Hill, Jack W. Stokes, Victor Wang, Junchen Jiang arxiv.org/abs/2605.21604 [𝚌𝚜.𝙼𝙰]

Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints Alexi Canesse, Benoît Goupil, Jesse Read, Sonia Vanier arxiv.org/abs/2605.21085 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

ProCrit: Self-Elicited Multi-Perspective Reasoning with Critic-Guided Revision for Multimodal Sarcasm Detection Yingjia Xu, Jiulong Wu, Bowen Zhang, Baokui Guo, Siyuan Chai, Min Cao arxiv.org/abs/2605.20867 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙲𝚅]

Multi-agent Collaboration with State Management Mengyang Liu, Taozhi Chen, Zhenhua Xu, Xue Jiang, Yihong Dong arxiv.org/abs/2605.20563 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶 𝚌𝚜.𝚂𝙴]

What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems Yong Jin Chun, Iftekhar Ahmed arxiv.org/abs/2605.20548 [𝚌𝚜.𝙼𝙰]

LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions Xin He, Junxi Shen, Yuchen Mou, David M. Bossens, Caishun Chen, Ivor W. Tsang, Yew Soon Ong arxiv.org/abs/2605.19915 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝚂𝙸]