Multi-Agent System

All of us have heard about the Mixture-of-Experts (MoE) architecture for LLMs. MoE divides models into separate sub-networks (or “experts”), each specializing in a subset of the input data, to jointly perform a task. A mixture of Expert architectures enables large-scale models, even those comprising many billions of parameters, to greatly reduce computation costs during pre-training and achieve faster performance during inference time. Broadly speaking, it achieves this efficiency through selectively activating only the specific experts needed for a given task, rather than activating the entire neural network for every task.

What if we adopt the principles of MoE on the agent level? Agents, like LLMs, become hard to scale as we add multiple responsibilities to them. This simple yet ground-breaking insight led us to develop the world’s first Multi-Agent System (MAS) which is also deployed in production. But we dive deeper, let’s start with the basics of Single-Agent Architecture and how it can be extended to MAS.

Agent – The fundamental building block

An agent, in the context of Large Language Models (LLMs), is a system that uses an LLM as the fundamental computational component to construct a plan with appropriate reasoning to tackle any challenge using the tools and resources at its disposal. It is similar to a human, who, given a problem, will devise a strategy and solve the problem utilizing the tools required to tackle the problem. The LLM acts similarly to the human brain in the Agent. For any given task, one will not solve it as such. The ideal way is to break it down into one or more smaller tasks that can be done sequentially or independently to solve the task. An agent will also do the same thing. The LLM will plan out the way it intends to solve the task. To accomplish any of the intermediate steps, the plan usually calls for the use of one or more tools available to the agent. Apart from the LLM and the tools the agent will also have other components for its proper intended functioning.

Broadly, there are three main components of an agent:

• A prompt
• Memory for the Agent
• The Tools

The prompt will define the way the system is going to behave and work. It will define the set of goals the agent must achieve, while also having the constraints it must follow to achieve these goals. Think of the prompt as the blueprint for our multi-agent system. It’s like the master plan that outlines what each agent needs to achieve and how they should go about doing it. Without this guidance, agents would lack direction and might wander aimlessly. So, the prompt essentially serves as the compass that keeps our system on course, ensuring that all agents are working towards common objectives within a defined framework. This prompt is also the major bottleneck in increasing the complexity of a single agent. To build complex systems, we divide the responsibilities between multiple agents so that the prompt of every agent remains simple.

Memory is the backbone of our LLM agents. It acts like their personal archive of knowledge and experiences. Similar to how humans draw from past experiences to make decisions, LLM agents utilize their memory to understand context, learn from past interactions, and make informed choices. Memory can simply be just passing the conversation history back to the LLM, or it can even be passing the extracted semantic information from the conversation and giving it to the LLM.

Tools are the Swiss Army knives of our agents, providing them with specialized capabilities to tackle various tasks effectively. These tools can be APIs, executable functions, or other services that help agents finish their tasks.

Now that we have understood the basic components of an Agent, let’s see how these components work together in a single-agent system.

Single-Agent System

A single-agent system consists of one particular AI agent that is equipped with multiple tools at its disposal to achieve any given problem. These systems are designed to handle tasks autonomously, leveraging the combined capabilities of the tools along with the reasoning capability of the LLM. The agent will devise a step-by-step plan that is to be followed to achieve the user goal. Once the plan is formulated, the agent will use the required tools to complete each of the available steps. Once each steps are completed, the outputs that were achieved at each stage can be clubbed together to get the final output.

There are different ways a particular user goal can be achieved. The plan that the LLMs will come up with depends on the availability of tools, its overall goal, and the constraints that it has to follow. The prompt, that controls the behavior of the agent should be therefore crafted in such a way that it works in the way we want it to work, and will be utilizing the resources efficiently to achieve the goals.

Architecture:

Why are Single-Agent Systems still relevant?

There are a few advantages to going with a Single-Agent system architecture. Firstly, simplicity, with just one agent handling all tasks, the system becomes easier to design, implement, and manage. The overhead of organizing communication between multiple agents will not be there.

Single-agent systems often boast greater coherence and consistency in decision-making. With a single agent in control, there’s no possibility of conflicting goals or actions among multiple agents. This can result in more predictable and stable behavior, making it easier to understand and debug the system.

Single-agent systems are typically more suitable for tasks that don’t require complex coordination. In fields and areas where centralized decision-making is required, a single-agent system will be quite efficient and will perform well in achieving the user goal.

Limitations of Single-Agent System

Single agents are often designed with a narrow focus, which can limit their ability to handle tasks outside their immediate domain. This limitation can pose challenges in environments where tasks are diverse or rapidly changing. Their narrow focus can hinder their ability to handle tasks beyond their immediate domain.

Scaling a single agent for more extensive or varied tasks often requires substantial redesign. When faced with the need to handle a broader range of tasks or increased complexity, simply adding more capabilities to a single agent may not be sufficient. Furthermore, scaling a single agent may introduce performance bottlenecks or efficiency issues.

Single-agent systems are also limited by memory constraints and processing capabilities. Since all tasks and responsibilities are concentrated within a single agent, it must contend with the finite resources available to it, including memory and processing power.

The shift towards Multi-Agent System Architecture

The exploration of Single-Agent Systems has highlighted significant limitations, particularly in handling complex, dynamic tasks and scalability issues. This sets the stage for the introduction of Multi-Agent Systems (MAS), which offer a robust framework capable of overcoming these challenges. In MAS, architecture, there are multiple independent agents who all work together to solve complex tasks.

In MAS, individual agents have their own responsibilities, characterized by their prompts and tools. Unlike single-agent systems, where one agent is responsible for all tasks, MAS allows for specialization and collaboration among several agents. This approach not only enhances efficiency but also improves the system’s ability to handle more complex and varied tasks.

Adding more agents to the system can extend its capabilities without the need for significant redesign. When faced with increasing demands or expanding task domains, incorporating additional agents offers a scalable solution that can accommodate growth seamlessly. Unlike single-agent systems, where scaling often requires substantial modifications to the existing architecture, multi-agent systems can adapt more readily to changing requirements by simply adding new agents with specialized capabilities. The redundancy inherent in multi-agent systems provides built-in fault tolerance and resilience. If one or more agents malfunction, the system can still perform the right intended work as the rest of the agents would come to a mutual agreement.

Architecture:

Concept and Structure of Multi-Agent Systems

Multi-Agent system consist of multiple intelligent agents, each capable of performing tasks autonomously but designed to work collaboratively toward a common goal. The structure of MAS allows for distributed problem-solving and decision-making, which significantly enhances the system’s overall efficiency and effectiveness. Each agent in a MAS can specialize in different tasks or aspects of a problem, bringing a diverse set of skills and perspectives to the table. Unlike single-agent systems, control in MAS is distributed among multiple agents, which reduces bottlenecks and single points of failure. Agents in a MAS can communicate and coordinate with each other, sharing information and decisions to optimize outcomes. The system is inherently modular, allowing for the addition, removal, or modification of agents without disrupting the entire system.

Agent to Agent Communication Protocol (AACP)

In a Multi-Agent system, the Agent-to-Agent Communication Protocol (AACP) is designed to facilitate structured and efficient communication among agents, pivotal for achieving consensus and addressing complex problems collaboratively. This protocol is instrumental in enhancing the overall system performance by leveraging the diverse insights and capabilities of individual agents, each characterized by a unique persona responding to system prompts.

The AACP adopts a dual-faceted communication architecture:

1. Hierarchical Communication Flow: This structure allows for the dissemination of information across different levels of the system hierarchy, enabling superior agents to coordinate and direct the actions of subordinate agents efficiently.
2. Lateral Communication: Agents situated at the same hierarchical level possess the capability to engage in direct communication. This feature is essential for collaborative problem-solving and task execution, facilitating rapid information exchange and coordination among peers.

The reconfigurability of the communication flow, tailored to the specific requirements of the task at hand, underscores the flexibility and adaptiveness of the AACP.

Analysis of single and multi-agent systems

When comparing single-agent and multi-agent systems, several key differences emerge:

• Scalability: MAS are inherently more scalable than single-agent systems due to their distributed nature. They can handle more complex tasks by dividing the workload among multiple agents.
• Robustness and Reliability: Multi-agent systems are generally more robust and reliable. The failure of one agent does not cripple the system, and others can take over or redistribute the tasks.
• Flexibility and Adaptability: MAS can adapt to changes in the environment or task requirements more effectively. They can reconfigure themselves, with agents taking on new roles as needed.

Two Design Choices for MAS

In this section, we will highlight two possible design patterns for MAS. But before we delve into the differences between these two patterns, let’s highlight their commonalities. The core premise of MAS is that the observation from the environment will be passed to multiple experts and different experts will recommend different actions. Then there will be an aggregation layer where these recommendations will analyzed and some of them will be approved. Now the two flavors discussed below differ on just one parameter – do we consult all the experts or do we selectively invoke relevant experts only?

Routing-Based Multi-Agent System

In a routing-based MAS, the orchestration acts as a routing layer. Depending on the message sent by the user, it will decide the agents it needs to invoke. The invoked agents will interact among themselves regarding the message and will decide on what is the best action to take and communicate it effectively to the user. By routing, the orchestrator will be solely responsible for identifying the right agents and communicating the same to the user. The main drawback of this is that the routing layer will tend to become the single point of failure. If the router decides not to invoke an agent that is required, or if it invokes some other agent that is not needed, there might be discrepancies in the communication to the user.

Broadcast-Based Multi-Agent System

The Broadcast-Based MAS architecture represents a generalized evolution of the Routing-Based MAS, effectively eliminating the Routing Layer that acts as a potential single point of failure. In instances where the Routing Layer mismanages the user query, the system’s integrity may be compromised. To enhance robustness and circumvent this vulnerability, the Routing Layer is omitted, permitting the free dissemination of information to all corresponding agents in unison. This way all the agents will get the input, and they will decide whether or not to give their output for the aggregation. This way it will ensure that there is no communication mishap between any of the agents.

Why do we believe the Multi-Agent System is a fundamental breakthrough?

The collaborative nature of multi-agent systems brings several benefits, especially in complex and dynamic environments

• Enhanced Problem-Solving Capabilities: By leveraging the diverse capabilities of various agents, MAS can tackle complex problems more effectively than single-agent systems.
• Increased Efficiency: Collaboration among agents often leads to more efficient use of resources, as tasks are allocated based on the specialization of each agent.
• Resilience to Uncertainty and Change: Multi-agent systems are better equipped to handle uncertainty and changes in the environment, as they can quickly reorganize and adapt.

Besides, the above-mentioned benefits, Multi-Agents systems have a strong resemblance to systems that have stood the test of time. For example, the hierarchal organizational structure that powers some of the largest organizations in the world is a lot similar to multi-agent systems. Even the human body is a composition of multiple organ systems. These resemblances instill our confidence in that MAS is going to be an enduring concept in the evolution journey of agents.