Decision Making in Multiagent Systems: A Survey
The DOI matches its Crossref record; 263 of the 275 references it cites were found in a registry or an index.
Abstract
Intelligent transport systems, efficient electric grids, and sensor networks for data collection and analysis are some examples of the multiagent systems (MAS) that cooperate to achieve common goals. Decision making is an integral part of intelligent agents and MAS that will allow such systems to accomplish increasingly complex tasks. In this survey, we investigate state-of-the-art work within the past five years on cooperative MAS decision making models, including Markov decision processes, game theory, swarm intelligence, and graph theoretic models. We survey algorithms that result in optimal and suboptimal policies such as reinforcement learning, dynamic programming, evolutionary computing, and neural networks. We also discuss the application of these models to robotics, wireless sensor networks, cognitive radio networks, intelligent transport systems, and smart electric grids. In addition, we define key terms in the area and discuss remaining challenges that include incorporating big data advancements to decision making, developing autonomous, scalable and computationally efficient algorithms, tackling more complex tasks, and developing standardized evaluation metrics. While recent surveys have been published on this topic, we present a broader discussion of related models and applications.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The objective is to maximize the system's overall reward, while agents work together to accomplish a common task [54].”
From Leveraging 3GPP Features and Optimization Techniques for 5G NR-V2X Resource Allocation: A Survey (2025) · cites this paper as [54]
Citations
Cites
Kennedy, J., & Eberhart, R. (2002) · Proceedings of ICNN'95 - International Conference on Neural Networks · doi:10.1109/icnn.1995.488968 · Cited by 58,192
Artificial intelligence: a modern approach
(1995) · Choice Reviews Online · doi:10.5860/choice.33-1577 · Cited by 21,974
Particle swarm optimization: An overview
Poli, R., Kennedy, J., & Blackwell, T. (2007) · Swarm Intelligence · doi:10.1007/s11721-007-0002-0 · Cited by 21,101
Artificial intelligence: A modern approach
Nilsson, N. J. (1996) · Artificial Intelligence · doi:10.1016/0004-3702(96)00007-0 · Cited by 10,583
Consensus and Cooperation in Networked Multi-Agent Systems
Olfati-Saber, R., Fax, J. A., & Murray, R. M. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2006.887293 · Cited by 10,522 · cited 1×
“Graphical models for consensus [157], formation [158], [159], and rendezvous [158] have also been investigated.”
BackgroundEquilibrium points in n -person games
Nash, J. F. (1950) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.36.1.48 · Cited by 7,560 · cited 1×
“For example, stochastic games with a finite number of players, actions and states always have a Nash equilibrium, defined as the strategy profile which maximizes each player’s utility knowing the strategy of others in the game [111].”
BackgroundAsynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 1×
“approximate methods are adopted and include model-free RL approaches like Q-learning [54] and SARSA [55], evolutionary computing [56], [57], RNN [58]–[63], and deep RL [64], [65].”
MethodSwarm Intelligence: From Natural to Artificial Systems
Bonabeau, E., Dorigo, M., & Theraulaz, G. (1999) · Oxford University Press eBooks · doi:10.1093/oso/9780195131581.001.0001 · Cited by 6,435
Watkins, C. (1989) · OpenGrey (Institut de l'Information Scientifique et Technique) · doi:10.17863/cam.132164 · Cited by 5,297
SMITH, J. M., & PRICE, G. R. (1973) · Nature · doi:10.1038/246015a0 · Cited by 5,089 · cited 1×
“Evolutionary stable strategy is a refinement of the Nash equilibrium which requires a strategy to be stable to any perturbations that may occur to the games as they evolve [112] and was extended to stochastic games [113].”
Background
Research works printed but not linked: 11
- 2015, First Workshop on Cognitive Architectures
- altman, 1999, Constrained Markov Decision Processes, 7
- amato, 2013, Scalable Bayesian reinforcement learning for multiagent POMDPs, Multidisciplinary Conf on Reinforcement Learning and Decision Making, 188
- sandhu, 2004, Wireless sensor networks for commercial lighting control: Decision making with multi-agent systems, Proc of the AAAI-04 Workshop on Sensor Networks, 10, 131
- strikos, 2007, A Full Approach for Intrusion Detection in Wireless Sensor Networks
- melo, 2012, Decentralized multiagent planning for balance control in smart grids, Proc 1st Int Workshop Inf Technol Energy Appl, 923, 21
- 2016, An Internet of Things That Will Number Ten Billions
- 2015, Gartner Says 6 4 Billion Connected “Things” Will Be in Use in 2016 Up 30 Percent From 2015
- lauri, 2013, Managing power flows in microgrids using multi-agent reinforcement learning, Proc Agent Technol Energy Syst, 1
- emery, 2005, Game Theoretic Control for Robot Teams
- teodorovi?, 2005, Bee colony optimization—A cooperative learning approach to complex transportation problems, Proc 16th Mini Eur Conf 10th Meeting Adv OR AI Methods Transport (EWGT), 51
Cited by
Items 201–219 of 219
Security Consensus of Multi-agent Systems under Cyber-attack: An Iterative Learning Control Strategy
Luo, Z., Yang, H., & Jiang, J. (2024) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs63458.2024.10704508
“Hence, the study of MASs has gradually attracted attention and has been widely applied in many fields, such as circuit network [2], supply chain systems [3], [4], decision making [5], etc.”
BackgroundPan, Y., Ma, B., Zhang, H., & Zeng, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5051570
Systems Thinking: How Systems Work
Mämmelä, A. (2025) · Springer eBooks · doi:10.1007/978-3-031-85012-7_5
CPIG: Leveraging Consistency Policy With Intention Guidance for Multiagent Exploration
Fu, Y., Zhu, Y., Li, H., Zhao, Z., Chai, J., & Zhao, D. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3578001 · Cited by 3
Safety Containment Control for Parabolic PDEs
Li, G. (2025) · IET Control Theory and Applications · doi:10.1049/cth2.70038
Goal-conditioned Trajectory Generation for Planning with Flow Matching in Offline RL
Diao, H., Zhang, J., Zhang, P., & Peng, B. (2025) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus66297.2025.11294744
“In some planning tasks, a commander specifies a desired goal, and the unmanned system needs to autonomously plan and make decisions to achieve that goal, such as cooperative tasks in UAVs and autonomous driving navigation tasks in USVs [1] [4].”
Chen, C., Wu, X., Zhuang, W., Wang, J., Bao, J., & Li, X. (2026) · Journal of Engineering Design · doi:10.1080/09544828.2025.2609041 · Cited by 3
Liu, L., & Xu, Z. (2026) · Journal of Simulation · doi:10.1080/17477778.2026.2628940
“The RL agent operates within a Markov Decision Process (MDP) framework, where the state space comprises the fused multimodal data and GNN-generated network embed-dings (Rizk et al., 2018).”
Utility Theory based Cognitive Modeling in the Application of Robotics: A SurveyPreprint
Yang, Q. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6435083
Linear Lens: A human-centered, non-interventional mechanistic approach to explainable AI
Danish, M. U., Aziz, M., Rehman, U., & Grolinger, K. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100897
Simulating Autonomous Agent in Connected Virtual Environments
Gramoli, L. (2023) · theses.fr (ABES) · doi:10.70675/30509701z9a29z4beezbb15zeb1797051d75
BOSA: Bayesian Online Strategy Adaptation for Unexpected Events in Multi-Agent Teams
Wu, H., Ghadami, A., Bayrak, A. E., Smereka, J. M., & Epureanu, B. I. (2026) · IEEE Systems Man and Cybernetics Letters · doi:10.1109/lsmc.2026.3688371
“For the experiment in Section IV-B, the novelty is degrading team capabilities from [4 , 3 , 2] to [3 , 2 , 1], and two corresponding strategies π max , π degrad are collected during offline preparation.”
InfluentialDeveloping a Transaction System on Intelligent Multi-Agent with Applicability in E-Commerce
Alecsoiu, O.-R., Dumitrescu, C. M., Tăbîrcă, A. I., Radu, F., Vasile, E., & Radu, V. (2026) · Computational Economics · doi:10.1007/s10614-026-11371-2
Bahrampour, S., Rasouli, M. R., & Fathian, M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06165-y
“MAS has been extensively researched for various applications, including supply chain management and distributed energy systems, where coordination is essential both on-chain and off-chain data [ 36].”
Lê, T. S., Le, H. S., Tuyen, N. T. V., & Tuyen, N. T. V. (2026) · Advanced Robotics · doi:10.1080/01691864.2026.2707053
Dynamic compensation for flood and sediment regulation in the Yellow River using a digital twin
Feng, Y., Cheng, C., & Ma, J. (2026) · Journal of Hydrology Regional Studies · doi:10.1016/j.ejrh.2026.103903
Asgari, A., Panichella, A., Derakhshanfar, P., & Olsthoorn, M. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113108
Using an Ontology-based Multi-agent System for Decentralized Control of a Swarm of UAVs
Gladun, A. Y., & Khala, K. O. (2024) · International Scientific and Practical Conference "Information Technologies and Security" (ITS) · doi:10.55056/ceur-ws.org/vol-3887/paper18 · Cited by 3
Dual Observer-Based Fuzzy Containment of Nonlinear Mass Under DoS Attacks
Wei, L. (2026) · International Conference on Control, Robotics and Intelligent System (CCRIS) · doi:10.1109/ccris71163.2026.11721672
Metadata
- Authors
- Rizk, Y., Awad, M., & Tunstel, E. W.
- Affiliations
- American University of Beirut (LB)
- Venue
- IEEE Transactions on Cognitive and Developmental Systems
- Published
- 2018-09
- Volume
- 10
- Issue
- 3
- Pages
- 514-529
- ISSN
- 2379-8920 (ISSN-L)
- 2379-8939
- OpenAlex
- W2803208334
- Cited by
- 219
- References
- 275
- Citations by year
- 2026: 18 · 2025: 29 · 2024: 34 · 2023: 39 · 2022: 35 · 2021: 29 · 2020: 21 · 2019: 13 · 2018: 1
- FWCI
- 8.96
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Cognitive and Developmental Systems (publishedVersion)
- Funders
- National Council of Scientific Research in Lebanon
- American University of Beirut
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- multi-agent systems, cooperative decision-making, Markov decision process, game theory, swarm intelligence, graph model, reinforcement learning, dynamic programming, evolutionary computation, artificial neural networks, robotics, wireless sensor networks, cognitive radio networks, intelligent transportation systems, big data, evaluation metrics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.