Multi-agent system

Template:Short description Template:Use mdy dates Template:Multi-agent system

Simple reflex agent

Learning agent

A multi-agent system (MAS or "self-organized system") is a computerized system composed of multiple interacting intelligent agents.<ref>Yoav Shoham, Kevin Leyton-Brown. Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press, 2009. http://www.masfoundations.org/</ref><ref name="uav">H. Pan; M. Zahmatkesh; F. Rekabi-Bana; F. Arvin; J. Hu "T-STAR: Time-Optimal Swarm Trajectory Planning for Quadrotor Unmanned Aerial Vehicles" IEEE Transactions on Intelligent Transportation Systems, 2025.</ref> Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a monolithic system to solve.<ref name="tcas">Hu, J.; Turgut, A.; Lennox, B.; Arvin, F., "Robust Formation Coordination of Robot Swarms with Nonlinear Dynamics and Unknown Disturbances: Design and Experiments" IEEE Transactions on Circuits and Systems II: Express Briefs, 2021.</ref> Intelligence may include methodic, functional, procedural approaches, algorithmic search or reinforcement learning.<ref>Stefano V. Albrecht, Filippos Christianos, Lukas Schäfer. Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press, 2024. https://www.marl-book.com/</ref> With advancements in large language models (LLMs), LLM-based multi-agent systems have emerged as a new area of research, enabling more sophisticated interactions and coordination among agents.<ref name=li2023>Template:Cite journal</ref>

Despite considerable overlap, a multi-agent system is not always the same as an agent-based model (ABM). The goal of an ABM is to search for explanatory insight into the collective behavior of agents (which do not necessarily need to be "intelligent") obeying simple rules, typically in natural systems, rather than in solving specific practical or engineering problems. The terminology of ABM tends to be used more often in the science, and MAS in engineering and technology.<ref name="Niazi-Hussain">Template:Cite journal</ref> Applications where multi-agent systems research may deliver an appropriate approach include online trading,<ref>Template:Cite journal</ref> disaster response,<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref><ref>Template:Cite book</ref> target surveillance<ref>Template:Cite journal</ref> and social structure modelling.<ref>Template:Cite journal</ref>

ConceptEdit

Multi-agent systems consist of agents and their environment. Typically multi-agent systems research refers to software agents. However, the agents in a multi-agent system could equally well be robots, humans or human teams. A multi-agent system may contain combined human-agent teams.

Agents can be divided into types spanning simple to complex. Categories include:

Passive agents<ref name=yoann2010>Template:Citation</ref> or "agent without goals" (such as obstacle, apple or key in any simple simulation)
Active agents<ref name=yoann2010/> with simple goals (like birds in flocking, or wolf–sheep in prey-predator model)
Cognitive agents (complex calculations)

Agent environments can be divided into:

Virtual
Discrete
Continuous

Agent environments can also be organized according to properties such as accessibility (whether it is possible to gather complete information about the environment), determinism (whether an action causes a definite effect), dynamics (how many entities influence the environment in the moment), discreteness (whether the number of possible actions in the environment is finite), episodicity (whether agent actions in certain time periods influence other periods),<ref>Template:Russell Norvig 2003</ref> and dimensionality (whether spatial characteristics are important factors of the environment and the agent considers space in its decision making).<ref name="Salamon2011">Template:Cite book</ref> Agent actions are typically mediated via an appropriate middleware. This middleware offers a first-class design abstraction for multi-agent systems, providing means to govern resource access and agent coordination.<ref>Template:Cite journal</ref>

CharacteristicsEdit

The agents in a multi-agent system have several important characteristics:<ref>Template:Cite book</ref>

Autonomy: agents at least partially independent, self-aware, autonomous
Local views: no agent has a full global view, or the system is too complex for an agent to exploit such knowledge
Decentralization: no agent is designated as controlling (or the system is effectively reduced to a monolithic system)<ref>Template:Cite journal</ref>

Self-organisation and self-directionEdit

Multi-agent systems can manifest self-organisation as well as self-direction and other control paradigms and related complex behaviors even when the individual strategies of all their agents are simple.Template:Citation needed When agents can share knowledge using any agreed language, within the constraints of the system's communication protocol, the approach may lead to a common improvement. Example languages are Knowledge Query Manipulation Language (KQML) or Agent Communication Language (ACL).

System paradigmsEdit

Many MAS are implemented in computer simulations, stepping the system through discrete "time steps". The MAS components communicate typically using a weighted request matrix, e.g.

 Speed-VERY_IMPORTANT: min=45 mph, 
 Path length-MEDIUM_IMPORTANCE: max=60 expectedMax=40, 
 Max-Weight-UNIMPORTANT 
 Contract Priority-REGULAR

and a weighted response matrix, e.g.

 Speed-min:50 but only if weather sunny, 
 Path length:25 for sunny / 46 for rainy
 Contract Priority-REGULAR
 note – ambulance will override this priority and you'll have to wait

A challenge-response-contract scheme is common in MAS systems, where

First a "Who can?" question is distributed.
Only the relevant components respond: "I can, at this price".
Finally, a contract is set up, usually in several short communication steps between sides,

also considering other components, evolving "contracts" and the restriction sets of the component algorithms.

Another paradigm commonly used with MAS is the "pheromone", where components leave information for other nearby components. These pheromones may evaporate/concentrate with time, that is their values may decrease (or increase).

PropertiesEdit

MAS tend to find the best solution for their problems without intervention. There is high similarity here to physical phenomena, such as energy minimizing, where physical objects tend to reach the lowest energy possible within the physically constrained world. For example: many of the cars entering a metropolis in the morning will be available for leaving that same metropolis in the evening.

The systems also tend to prevent propagation of faults, self-recover and be fault tolerant, mainly due to the redundancy of components.

ResearchEdit

The study of multi-agent systems is "concerned with the development and analysis of sophisticated AI problem-solving and control architectures for both single-agent and multiple-agent systems."<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref> Research topics include:

agent-oriented software engineering
beliefs, desires, and intentions (BDI)
cooperation and coordination
distributed constraint optimization (DCOPs)
organization
communication
negotiation
distributed problem solving
multi-agent learning<ref>Template:Citation</ref>
agent mining
scientific communities (e.g., on biological flocking, language evolution, and economics)<ref>Template:Cite journal</ref><ref>Template:Cite journal

</ref>

dependability and fault-tolerance
robotics,<ref>Template:Citation</ref> multi-robot systems (MRS), robotic clusters
multi-agent systems also present possible applications in microrobotics,<ref>Template:Cite journal</ref> where the physical interaction between the agents are exploited to perform complex tasks such as manipulation and assembly of passive components.
language model-based multi-agent systems<ref name=li2023></ref>

FrameworksEdit

Frameworks have emerged that implement common standards (such as the FIPA and OMG MASIF standards).<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref> These frameworks e.g. JADE, save time and aid in the standardization of MAS development.<ref name=DF_1>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref>

Currently though, no standard is actively maintained from FIPA or OMG. Efforts for further development of software agents in industrial context are carried out in IEEE IES technical committee on Industrial Agents.<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref>

With advancements in large language models (LLMs) such as ChatGPT, LLM-based multi-agent frameworks, such as CAMEL,<ref name="camel2023">{{#invoke:citation/CS1|citation |CitationClass=web }}</ref><ref name="li2023" /> have emerged as a new paradigm for developing multi-agent applications.

ApplicationsEdit

MAS have not only been applied in academic research, but also in industry.<ref>Template:Cite book</ref> MAS are applied in the real world to graphical applications such as computer games. Agent systems have been used in films.<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref> It is widely advocated for use in networking and mobile technologies, to achieve automatic and dynamic load balancing, high scalability and self-healing networks. They are being used for coordinated defence systems.

Other applications<ref>Template:Cite journal</ref> include transportation,<ref name="surtrac2012b">Xiao-Feng Xie, S. Smith, G. Barlow. Schedule-driven coordination for real-time traffic network control. International Conference on Automated Planning and Scheduling (ICAPS), São Paulo, Brazil, 2012: 323–331.</ref> logistics,<ref name="compare">Template:Cite journal</ref> graphics, manufacturing, power system,<ref name="GEP_1">Template:Cite book</ref> smartgrids,<ref name=DMA_1>Template:Cite journal</ref> and the GIS.

Also, Multi-agent Systems Artificial Intelligence (MAAI) are used for simulating societies, the purpose thereof being helpful in the fields of climate, energy, epidemiology, conflict management, child abuse, ....<ref name="newscientist.com">{{#invoke:citation/CS1|citation |CitationClass=web }}</ref>

Some organisations working on using multi-agent system models include Center for Modelling Social Systems,<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref> Centre for Research in Social Simulation,<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref> Centre for Policy Modelling, Society for Modelling and Simulation International.<ref name="newscientist.com" />

Vehicular traffic with controlled autonomous vehicles can be modelling as a multi-agent system involving crowd dynamics.<ref name="Gong">Template:Cite journal</ref>

Hallerbach et al. discussed the application of agent-based approaches for the development and validation of automated driving systems via a digital twin of the vehicle-under-test and microscopic traffic simulation based on independent agents.<ref>Template:Cite journal</ref> Waymo has created a multi-agent simulation environment Carcraft to test algorithms for self-driving cars.<ref>Template:Cite news</ref><ref>Template:Cite journal</ref> It simulates traffic interactions between human drivers, pedestrians and automated vehicles. People's behavior is imitated by artificial agents based on data of real human behavior.

ReferencesEdit

Template:Reflist