Multiagent Systems Papers

Where FactsGo Missing: A LayerwiseTaxonomy and Per-Layer Attribution of Information Omissionin Air-Gapped LLM Agent Pipelines Santhiya Rajan arxiv.org/abs/2607.22448 [𝚌𝚜.𝙼𝙰]

Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives Marcantonio Bracale Syrnicov, Federico Pierucci, Matteo Prandi, Marcello Galisai, Piercosma Bisconti, Francesco Giarrusso, … arxiv.org/abs/2607.22188 [𝚌𝚜.𝙼𝙰]

When Language Models Meet NeuroGraphs: Exploring Enhanced Agentic LLM Framework Towards Brain Network Analysis Jiaxing Li, Rui Dong, Muyao Tang, Youyong Kong arxiv.org/abs/2607.22082 [𝚌𝚜.𝙼𝙰]

Reliability-Contagion Feasibility in LLM Multi-Agent Networks Ruiwu Niu, Xincheng Shu, Ying Zhao arxiv.org/abs/2607.21912 [𝚌𝚜.𝙼𝙰]

FedAgentKE: Federated Semantic Knowledge Evolution for Heterogeneous Agents Weihao Li, Jun Bai, Ziyang Song arxiv.org/abs/2607.21361 [𝚌𝚜.𝙼𝙰]

pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development Chen Zhu, Xiaolu Wang, Weilong Zhang arxiv.org/abs/2607.21268 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚎𝚌𝚘𝚗.𝙶𝙽]

Harnessing Disagreement: Detecting Correlated Agreement Blindness in Multi-Agent Triage Shay Seiya McDonnell, Avantika Singh, Quoc-Viet Pham, Vratislav Havlik, Gregory M. P. O'Hare arxiv.org/abs/2607.19899 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶] 💬Accepted at PAAMS 2026

Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning Taisuke Takayama, Naoto Yoshida, Tadahiro Taniguchi arxiv.org/abs/2607.19809 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶]

Not Birds of a Feather: Personality-Based Partner Selection in LLM Agents Tao Wang, Hsiang-Ling Chiu, Chihang Wei, Yang Xiu, Zhonghao Hou arxiv.org/abs/2607.19785 [𝚌𝚜.𝙼𝙰]

Same Game, Different Story: A Minimal Conservative Strategic Robustness Benchmark for Large Language Model Agents Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi, Amin Gholami Davodi, Hamidreza Hasani Balyani, Arshia Gharagozlou arxiv.org/abs/2607.19670 [𝚌𝚜.𝙼𝙰]

CHMAS: A Coupled Hierarchical Framework for Multi-Agent Reinforcement Learning Dongming Wang, Jie Xu, Yanyu Zhang, Wei Ren arxiv.org/abs/2607.19555 [𝚌𝚜.𝙼𝙰]

Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents Yamato Takahagi, Gentoku Nakasone, Yoshinari Motokawa, Toshiharu Sugawara arxiv.org/abs/2607.18719 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸]

Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces Dongming Wang, Pengcheng Dai, Wenwu Yu, Wei Ren arxiv.org/abs/2607.18554 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶]

Decentralized Multi-agent Reinforcement Learning for Resilient Critical Infrastructures Minghui Ding, … arxiv.org/abs/2607.18359 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶] 💬Accepted at the 2026 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS 2026)

Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization Zijian Zhao, Sen Li arxiv.org/abs/2607.17924 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶]

PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks Wen Qiu, Zhiqiang He, Wei Zhao, Hiroshi Masui arxiv.org/abs/2607.17922 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙽𝙸]

Value-Aware Prediction for Robust Multi-Agent Coordination Under Communication Loss Kemal Devrim Kafadar, Eren Özaltun, … arxiv.org/abs/2607.17914 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙻𝙶 𝚌𝚜.𝚁𝙾] 💬Accepted to 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

A Digital Twin-Based Method for Evaluating Local Collective Tariffs in Distribution-Level Energy Systems Kristoffer Christensen, Bo Nørregaard Jørgensen, Zheng Grace Ma arxiv.org/abs/2607.17640 [𝚌𝚜.𝙼𝙰 𝚎𝚌𝚘𝚗.𝙶𝙽 𝚎𝚎𝚜𝚜.𝚂𝚈]

The Optimization Trilemma: Efficiency, Comfort and Fairness in Decentralized Multi-agent Coordination Jovan Nikolic, Maciej Krzysztof Zuziak, Evangelos Pournaras arxiv.org/abs/2607.17311 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙳𝙲 𝚎𝚎𝚜𝚜.𝚂𝚈]

Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer Jingjie Ning, Xiaochuan Li, Shanshan Zhong, Ji Zeng, Guolin Ke arxiv.org/abs/2607.17100 [𝚌𝚜.𝙼𝙰 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝚂𝙴]