arXiv cs.MA Multiagent Systems

Qiyue Xia, J. Michael Herrmann: Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning https://arxiv.org/abs/2610.35736 https://arxiv.org/pdf/2610.35736 https://arxiv.org/html/2610.35736

Brell Sanwouo, Nada Zine, Paul Temple, Cl\'ement Quinton, Romain Rouvoy: GEAR: Feature-Based Configuration and Code Generation for Agentic Systems https://arxiv.org/abs/2610.35592 https://arxiv.org/pdf/2610.35592 https://arxiv.org/html/2610.35592

Junyao Zhang, Jinglai Li, Junqi Tang: Simulation-Efficient Double-Flow Neural Posterior Estimation for Agent-Based Models https://arxiv.org/abs/2610.35442 https://arxiv.org/pdf/2610.35442 https://arxiv.org/html/2610.35442

Micha{\l} Wawer, Jaros{\l}aw A. Chudziak: Knowing When to Escalate: Disagreement Patterns for Uncertainty-Aware Content Moderation https://arxiv.org/abs/2610.35335 https://arxiv.org/pdf/2610.35335 https://arxiv.org/html/2610.35335

Yuhang Dong, Min Xia, Jinghong Li, Yue Dai, Xinyue Wang, Shi Liang: Guarded Agent-in-the-Loop Residual Adaptation for Evolving Wind Power Regimes https://arxiv.org/abs/2610.34968 https://arxiv.org/pdf/2610.34968 https://arxiv.org/html/2610.34968

Jingjie Ning, Xueqi Li, Yi Lu, Yibo Kong: AgentProofBench: Benchmarking Reusable Verifiers for Web Agents https://arxiv.org/abs/2610.34634 https://arxiv.org/pdf/2610.34634 https://arxiv.org/html/2610.34634

Ruhao Liu, Qi Li, Shizun Wang, Xinchao Wang: DynaFlow: Learning Free-Form Multi-Agent Orchestration https://arxiv.org/abs/2610.34467 https://arxiv.org/pdf/2610.34467 https://arxiv.org/html/2610.34467

Wu, Ma, Xu, Zhang, Bai, Wang, Li, Lv, Yuan, Wang, Wang, Zhang, Chua: EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems https://arxiv.org/abs/2610.34450 https://arxiv.org/pdf/2610.34450 https://arxiv.org/html/2610.34450

Chih-Wei Huang, Hsin-Chieh Lee, Yun-Chen Yu, Ibrahim Althamary, Rongxing Lu, Phone Lin: BE-CTDE: Blockchain-Enabled Multi-Agent Reinforcement Learning with Anomaly Detection and Token Economics https://arxiv.org/abs/2610.34121 https://arxiv.org/pdf/2610.34121 https://arxiv.org/html/2610.34121

Ren, Zang, Wang, Deb, Yang, Forder, Carroll, Gevero, Liu, Du, Tambe, Guo: Coral Discovery: The Division of Cognitive Labor in Autonomous Research https://arxiv.org/abs/2610.33281 https://arxiv.org/pdf/2610.33281 https://arxiv.org/html/2610.33281

Hu, Li, Wei, Cao, Hong, Dai, Bai, Liang, Liao, An, Lou, Wang, Lyu, Yang, Liu, Si: VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team https://arxiv.org/abs/2610.33106 https://arxiv.org/pdf/2610.33106 https://arxiv.org/html/2610.33106

Zhonghang Li, Zongwei Li, Chao Huang: AutoSwarm: Automating Agent Swarms https://arxiv.org/abs/2610.33048 https://arxiv.org/pdf/2610.33048 https://arxiv.org/html/2610.33048

Hanwen Li, Jinhao Duan, Xiaoshuang Shi, Yue Zhang, Tianlong Chen, Kaidi Xu, Chenxi Yuan: UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems https://arxiv.org/abs/2610.33013 https://arxiv.org/pdf/2610.33013 https://arxiv.org/html/2610.33013

Eric Onyame, Runtao Zhou, Kowshik Thopalli, Bhavya Kailkhura, Chirag Agarwal: When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems https://arxiv.org/abs/2610.33011 https://arxiv.org/pdf/2610.33011 https://arxiv.org/html/2610.33011

Lynnette Hui Xian Ng, Kathleen M. Carley: LLM-Augmented Agent-Based Simulation of Cyber Social Agents https://arxiv.org/abs/2610.32988 https://arxiv.org/pdf/2610.32988 https://arxiv.org/html/2610.32988

[2026-10-27 Tue (UTC), 15 new articles found for csMA Multiagent Systems]

Abdelkader Dib, Milos Balac: Agent-Based Transport Model Calibration via Online Stochastic Batch Optimization https://arxiv.org/abs/2610.32698 https://arxiv.org/pdf/2610.32698 https://arxiv.org/html/2610.32698

Amirmohammad Khakpour (Marco), Nachuan Li (Marco), Pedram Beigi (Marco), Yu (Marco), Nie: Empirically Calibrated Differential Games for Simulating Driver Interactions https://arxiv.org/abs/2610.32276 https://arxiv.org/pdf/2610.32276 https://arxiv.org/html/2610.32276

Jusheng Zhang, Xuekun Wu, Wenhao Wang, Mark Wang, Ming-Hsuan Yang: Markets of Minds: A 51-Billion-State Economy of Intelligence https://arxiv.org/abs/2610.32190 https://arxiv.org/pdf/2610.32190 https://arxiv.org/html/2610.32190

Xueyi Zhang, Hongru Du, Ensheng Dong: Toward an Agentic AI Approach to Public Health Data Collection https://arxiv.org/abs/2610.31746 https://arxiv.org/pdf/2610.31746 https://arxiv.org/html/2610.31746

Cai, Xian, Ma, Wang, Song, Li, Liu: Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems https://arxiv.org/abs/2610.31743 https://arxiv.org/pdf/2610.31743 https://arxiv.org/html/2610.31743

[2026-10-26 Mon (UTC), 5 new articles found for csMA Multiagent Systems]

Yiqi Wang, Yifei Wang, Jiaqi Zhang, Zhangkai Wu, Yiqun Duan, Taotao Cai, Mingkai Zheng: When Is a Memory Safe Enough to Act On? Action-Conditioned Verification for Long-Lived Agents https://arxiv.org/abs/2610.31446 https://arxiv.org/pdf/2610.31446 https://arxiv.org/html/2610.31446

Yitong Bai (Columbia University), Chengyi Zhang (Swansea University), Ziyang Wang (Aston University): Consistent but Biased: Chair Personas Trade Noise for Bias in Multi-Agent Clinical Decisions https://arxiv.org/abs/2610.31325 https://arxiv.org/pdf/2610.31325 https://arxiv.org/html/2610.31325

Germ\'an Pardo-Gonz\'alez, Shaghayegh Vosough, Katerina Papadaki, Claudio Roncoli: Learning to Incentivise: Using Reinforcement Learning for Sustainable Urban Mobility https://arxiv.org/abs/2610.30469 https://arxiv.org/pdf/2610.30469 https://arxiv.org/html/2610.30469

[2026-10-23 Fri (UTC), 3 new articles found for csMA Multiagent Systems]

Hanmin Li, Yury Demidovich, Peter Richt\'arik: Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization https://arxiv.org/abs/2610.30074 https://arxiv.org/pdf/2610.30074 https://arxiv.org/html/2610.30074

Jinyi Ye, Lei Cao, Ding Chen, Emilio Ferrara: The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits https://arxiv.org/abs/2610.28981 https://arxiv.org/pdf/2610.28981 https://arxiv.org/html/2610.28981

Daniele Montagnani, Andrea Coletta, Antonietta Mira, Aldo Glielmo: JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds https://arxiv.org/abs/2610.28907 https://arxiv.org/pdf/2610.28907 https://arxiv.org/html/2610.28907

[2026-10-22 Thu (UTC), 3 new articles found for csMA Multiagent Systems]

Ivan Ilin, Peter Richt\'arik: Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration https://arxiv.org/abs/2610.28286 https://arxiv.org/pdf/2610.28286 https://arxiv.org/html/2610.28286

Li, Wan, Wang, He, Xu, Chen, Zhong, Binjie, Guo, Jun, Guo, Lin, Zhou, Liu, Luo: S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents https://arxiv.org/abs/2610.27746 https://arxiv.org/pdf/2610.27746 https://arxiv.org/html/2610.27746

Sharika J. Hegde (Marco), Amirmohammad Khakpour (Marco), Pedram Beigi (Marco), Yu (Marco), Nie, Hani S. Mahmassani: Complete Street Design informed by Multi-Agent Simulation https://arxiv.org/abs/2610.27509 https://arxiv.org/pdf/2610.27509 https://arxiv.org/html/2610.27509

[2026-10-21 Wed (UTC), 3 new articles found for csMA Multiagent Systems]

Zihuang Cai, Changjian Chen, Zhuo Tang, Chang Tang, Kenli Li: Discovery-Probability Graph Planning for Embodied Agents in Tasks with Hidden Cooperation Requirements https://arxiv.org/abs/2610.26359 https://arxiv.org/pdf/2610.26359 https://arxiv.org/html/2610.26359

Junhui Chen, Yu Zhang, Lantian Li, Dong Wang: Behavioral Probes for Information Flow in LLM Swarms https://arxiv.org/abs/2610.25966 https://arxiv.org/pdf/2610.25966 https://arxiv.org/html/2610.25966

Haibin Li, Wenya Yu, Xuefeng Jiang, Jia Li, Xiao Han, Shuai Su, Wei Wei: Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration https://arxiv.org/abs/2610.25851 https://arxiv.org/pdf/2610.25851 https://arxiv.org/html/2610.25851

Dima Galat, Marian-Andrei Rizoiu: How Far Can an Agent Push? Trust-Safety Margins in Live Language-Based Economic Games https://arxiv.org/abs/2610.25508 https://arxiv.org/pdf/2610.25508 https://arxiv.org/html/2610.25508

Congjing Zhang, Siyuan Xu, Yunfei Bai, Ke Ren, Xiaoning Qian, Shuai Huang: AgentSoV: Virtual Sensing for LLM Multi-Agent Systems via Stream of Variation https://arxiv.org/abs/2610.24845 https://arxiv.org/pdf/2610.24845 https://arxiv.org/html/2610.24845

Jin Gao: Measuring Consensus in AI Agent Networks https://arxiv.org/abs/2610.24833 https://arxiv.org/pdf/2610.24833 https://arxiv.org/html/2610.24833

Chaoran Li, Zeyuan Zhao, Shao Zhang: CARVS: A Congestion-Aware Algorithm for Online Multi-Agent Pickup-and-Delivery in Human-Collaborative Warehouses https://arxiv.org/abs/2610.24549 https://arxiv.org/pdf/2610.24549 https://arxiv.org/html/2610.24549

Wang, Zhao, Yu, Zhou, Chi, Liu, Zhang, Chu, Koh, Ushaw, Davison: ROAR: Benchmarking LMM Agents under Real-Time Constraints in Multiplayer Action-Shooter Games https://arxiv.org/abs/2610.24282 https://arxiv.org/pdf/2610.24282 https://arxiv.org/html/2610.24282

Patrick Zhao, Yuxuan Li, Hirokazu Shirado: Model Capacity Frontier: A Development Framework for LLM-Supported Social Simulation https://arxiv.org/abs/2610.24168 https://arxiv.org/pdf/2610.24168 https://arxiv.org/html/2610.24168

Jianing Shi, Zaibin Zhang, Shijun Lei, Zhenfei Yin: The Weight of Teamwork: Does Communication Structure Help LLM Scientists Search for Scientific Laws? https://arxiv.org/abs/2610.24131 https://arxiv.org/pdf/2610.24131 https://arxiv.org/html/2610.24131

Charlie Pilgrim, Christopher Krupenye, Dora Biro, Richard P. Mann: LLM Evolution in a Simple Simulated Market https://arxiv.org/abs/2610.24033 https://arxiv.org/pdf/2610.24033 https://arxiv.org/html/2610.24033

Dixi Yao, Tahseen Rabbani, Tian Li: Federation over Harness https://arxiv.org/abs/2610.24007 https://arxiv.org/pdf/2610.24007 https://arxiv.org/html/2610.24007

[2026-10-20 Tue (UTC), 12 new articles found for csMA Multiagent Systems]

Shoucheng Song, Chang Yao, Hao Wu, Youfang Lin, Sheng Han, Kai Lv: Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication https://arxiv.org/abs/2610.23092 https://arxiv.org/pdf/2610.23092 https://arxiv.org/html/2610.23092

Zhenhan Guan, Xiaolong Liu, Hengwei Ye, Zheng Tian: Thought Blocks: Non-Autoregressive Latent Communication for Multi-Agent Systems via Trajectory-to-State Compilation https://arxiv.org/abs/2610.23056 https://arxiv.org/pdf/2610.23056 https://arxiv.org/html/2610.23056

Caticha, Sant'Ana, Alves, Costa, Mercucci, Neirotti, Citton, Vicente: Emergent Discrimination and Polarization in Multi-Agent Systems https://arxiv.org/abs/2610.22701 https://arxiv.org/pdf/2610.22701 https://arxiv.org/html/2610.22701