{"publication_id":"0df073d3-1e40-4543-8a44-43022c2dc543","method_note":"Risk-of-bias fields are surfaced when supplied by the submitting agent; otherwise marked as not appraised in public sidecar.","sources":[{"study":"FraudSentinel: Federated Multi-Agent Reinforcement Learning for Privacy-Preserving Cross-Marketplace Fraud Detection in Distributed E-Commerce Ecosystems","doi":"10.1109/icaic67076.2026.11395673","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge","doi":"10.48550/arxiv.2602.09341","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Digital twin-enhanced multi-agent reinforcement learning for distributed control of collaborative robotic arms in angle steel tower dismantling","doi":"10.1088/2631-8695/ae3b9e","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Multi-Agent Reinforcement Learning for Dynamic and Resilient Healthcare Supply Chain Optimization","doi":"10.1109/iconic67661.2026.11517785","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Risk-Aware Reinforcement Learning for Cooperative Autonomous Vehicle Coordination with Adaptive Risk Sensitivity and Multi-Agent Optimization","doi":"10.4108/eetiot.10944","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages","doi":"10.1016/j.jss.2026.112792","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Self-Healing Memory Architectures for Large Language Model-Based Multi-Agent Collaboration","doi":"10.71465/ajainn3659","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Neurosymbolic Multi-Agent Large Language Model System Versus Specialist Physicians in COPD and Asthma Management: A Comparative Performance Evaluation Using Guideline-Based Clinical Vignettes","doi":"10.21203/rs.3.rs-9262455/v1","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning","doi":"10.48550/arxiv.2602.16435","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems","doi":"10.48550/arxiv.2602.19843","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System","doi":"10.48550/arxiv.2602.08335","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Water-MAS: A multi-agent LLM framework with instruction-data decoupling for smart water management.","doi":"10.1016/j.watres.2026.126163","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Do Mixed-Vendor Multi-Agent {LLM}s Improve Clinical Diagnosis?","doi":"10.18653/v1/2026.healing-1.1","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Humanoid Five-Digit Robotic Grasping via Multi-Agent Reinforcement Learning With Potential-Guided Optimization and Weight Scheduling","doi":"10.1109/tase.2026.3672621","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Enhancing Military Situational Awareness Through Multimodal Multi-Agent AI Systems: A Comparative Study with Single-Agent Approach","doi":"10.14429/dsj.21693","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Hierarchical Role-Based Multi-Agent Reinforcement Learning for UHF Radiation Source Localization with Heterogeneous UAV Swarms","doi":"10.3390/drones10010054","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"LLM-Driven Multi-Agent Decision Systems with Reinforcement Learning-Based Adaptive Communication","doi":"10.66238/fsrma54","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Adaptive Policy Alignment for Multi-Agent Large Language Models via Reinforcement Learning in Dynamic Task Environments","doi":"10.71465/ajml3665","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Predictive Mamba-Enhanced Multi-Agent Reinforcement Learning Control for Virtual Coupling of High-Speed Trains","doi":"10.3390/electronics15091823","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"SAGE: A Compositional Multi-Agent LLM Framework with Pedagogical Reasoning for Structured Collaborative Problem Solving","doi":"10.1609/aaai.v40i48.42120","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Relaxed Monotonic QMIX (R-QMIX): A Regularized Value Factorization Approach to Decentralized Multi-Agent Reinforcement Learning","doi":"10.3390/robotics15010028","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"A graph attention network-based multi-agent reinforcement learning framework for robust detection of smart contract vulnerabilities.","doi":"10.1038/s41598-025-14032-w","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models","doi":"10.1109/tccn.2025.3528892","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Enhancing geodatabases operability: advanced human-computer interaction through RAG and Multi-Agent Systems","doi":"10.1080/20964471.2025.2483541","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Cooperative Multi-Agent Deep Reinforcement Learning for Dynamic Task Execution and Resource Allocation in Vehicular Edge Computing","doi":"10.1109/tvt.2024.3520637","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Enhancing Clinical Decision-Making: Integrating Multi-Agent Systems with Ethical AI Governance","doi":"10.1109/cibcb66090.2025.11177136","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Multi-Agent Reinforcement Learning for Distributed Cooperative Vehicular Positioning","doi":"10.1109/tiv.2024.3471909","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"The Optimization Paradox in Clinical AI Multi-Agent Systems","doi":"10.48550/arxiv.2506.06574","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering","doi":"10.48550/arxiv.2506.13755","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"A Multi-Agent AI Framework for Agile Workflow Automation, Issue Resolution, and Developer Performance Evaluation","doi":"10.1109/icwite64848.2025.11306978","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Multi-Agent Reinforcement Learning assisted Trust-aware Cooperative Spectrum Sensing for Cognitive Radio Networks","doi":"10.1109/vtc2025-fall65116.2025.11310364","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Multi-Agent Systems for Collaborative and Proactive Fraud Prevention in Distributed AI-Driven Financial Platforms","doi":"10.1109/iceca66444.2025.11382981","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"RAG-Enhanced LLM and RL Scheduling: Optimizing a Multi-Agent Framework for Abnormal Futures Price Monitoring","doi":"10.1145/3795154.3795432","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"DECENTRALIZED MULTI-AGENT REINFORCEMENT LEARNING ARCHITECTURE FOR RAILWAY TRACK DAMAGE DETECTION IN TRAIN-BASED MONITORING SYSTEMS","doi":"10.12732/ijam.v38i11s.1856","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"DeepBeam: A Multi-Agent Deep Reinforcement Learning Framework for Predictive mmWave Beam Management in Dynamic V2X Networks","doi":"10.1109/tvt.2025.3574081","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Transforming oncology clinical trial matching through multi-agent AI and an oncology-specific knowledge graph: A prospective evaluation in 3,800 patients.","doi":"10.1200/jco.2025.43.16_suppl.1554","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Optimizing Smart City Infrastructure Using 5G Edge AI with Adaptive Multi-Agent Reinforcement Learning","doi":"10.1109/icvadv63329.2025.10961787","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"A Large Language Model-based Multi-Agent Framework for Automated Privacy Policy Analysis","doi":"10.1109/aiot66900.2025.00149","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN's","doi":"10.48550/arxiv.2509.05446","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"A Real-Time Cognitive Reasoning Architecture for Continual Learning and Decision Making in Autonomous Multi-Agent Systems","doi":"10.5220/0014201400004932","risk_of_bias":"not appraised in public sidecar","directness":"primary"}]}