Single Agent vs Multi-Agent: When to Construct a Multi-Agent System

AI Brokers

When constructing an AI agent, the design alternative issues. A single agent could also be sufficient for simple duties, whereas extra complicated workflows might have a number of specialised brokers working collectively, with every one chargeable for a particular a part of the method, equivalent to retrieval, writing, verification, coding, testing or assessment.

This put up explains the core elements of AI agent design, the ReAct strategy, the distinction between single-agent and multi-agent architectures, and the way to decide on the suitable design relying on the duty. It additionally features a walkthrough of how a sensible Multi-Agent RAG system works and the way it was constructed.

widespread as a result of trendy LLMs are actually extremely succesful at duties like coding, writing, reasoning, and fixing issues throughout completely different fields. This has diminished the necessity to prepare customized fashions and shifted extra consideration towards constructing sensible functions round present LLMs. Instruments like Codex, Claude Code, Cursor and Windsurf are already serving to software program engineers work quicker, whereas companies use brokers for buyer help, automation and different real-world duties.

An AI agent is an utility that makes use of an LLM to cause, plan and use instruments to carry out duties, permitting the mannequin to work together with its surroundings in a sensible and helpful manner.

Elements of an AI Agent

A number of the main elements of most AI brokers are the LLM, instruments, and reminiscence.

• LLM: That is the mind of the AI agent. It’s the massive language mannequin that allows the agent to cause, plan, and determine the way to resolve a given process.
• Instruments: These are helpers, normally within the type of code features, that enable the LLM to work together with its surroundings. Instruments assist the agent hook up with exterior information sources, search the web, retrieve data from databases, entry recordsdata, and perform particular actions. For instance, coding brokers can use instruments to write down, debug, and save recordsdata, analysis brokers can use net search or vector databases to collect data and buyer help brokers can use inside firm paperwork to reply questions primarily based on trusted enterprise information.
• Reminiscence: This permits the agent to retailer related data from interactions and use it later to offer higher and extra constant help. It helps the agent keep context throughout duties and enhance the general person expertise.Reminiscence could also be optionally available throughout early improvement, however it turns into an vital a part of many real-world AI agent techniques, particularly when the agent must deal with follow-up questions, multi-step workflows or personalised interactions. There are two main varieties of reminiscence generally utilized in AI brokers: short-term reminiscence and long-term reminiscence. Quick-term reminiscence retains observe of data inside the present session or process, whereas long-term reminiscence shops helpful data throughout a number of classes or chats so the agent can use it later.

ReAct (Reasoning + Appearing) in Brokers

An AI agent differs from a fundamental chatbot as a result of a chatbot normally follows a extra direct workflow: person question → LLM → response. The LLM receives the person’s message and generates a reply primarily based primarily on the immediate and its present context.

An AI agent goes past this through the use of the LLM to cause in regards to the process, determine what must be executed, select whether or not instruments are wanted, name these instruments, observe the outcomes and proceed till it will possibly produce a helpful reply.

That is the place the ReAct strategy is available in. ReAct means Reasoning + Appearing. It’s an agent sample the place the LLM causes a couple of process and takes actions, normally by way of instruments, primarily based on that reasoning. It entails designing a core logic loop round an LLM.

A fundamental ReAct workflow in an AI agent normally seems to be like this:

Step 1: The agent receives a person question

The LLM causes over the duty and decides whether or not it will possibly reply immediately or wants to make use of instruments. It checks what instruments can be found and decides which of them are wanted to unravel the duty.

Step 2: The agent calls the required instruments

Primarily based on its reasoning, the agent takes motion by calling the mandatory instruments. These instruments might search the online, retrieve paperwork from a vector database, entry recordsdata, run code or hook up with an exterior API. The outcomes returned from these instruments are often called software outputs.

Step 3: The software outputs are despatched again to the LLM

The software outputs are handed again to the LLM as further context. This provides the agent extra related data to work with as a substitute of relying solely on the unique immediate.

Step 4: The LLM checks the proof and generates a response

The LLM opinions the software outputs and checks whether or not they’re sufficient to unravel the duty. If the proof is ample, it generates a grounded response for the person. If not, the agent might repeat the reasoning, tool-calling and remark steps till it has sufficient data to offer a helpful reply.

Construction of AI Brokers

AI Brokers can both be single or multi relying on the design construction.

Single Agent vs Multi-Agent

A single agent is an agent design the place one LLM handles the entire process. It causes, plans and calls the required instruments when wanted. Most AI brokers begin as single-agent techniques as a result of they’re easier, simpler to take care of and normally sufficient for a lot of duties.

A multi-agent system makes use of specialised brokers to unravel completely different components of a process. It usually has a central agent, normally referred to as an orchestrator, supervisor or planner, that coordinates the opposite brokers and decides when every one ought to act. Every specialised agent can have its personal function, instruments and reasoning logic, making the system extra modular and appropriate for complicated workflows.

When to Construct A Multi-Agent System

A single-agent design works nicely for easy duties that require restricted software use. For instance, a private assistant agent that may entry your calendar to e book reminders, a calculator agent that solely makes use of a calculator software, or an online search agent that makes use of an online search API to retrieve up-to-date data.

Nevertheless, a single agent can change into overloaded when the duty requires many instruments, multi-step reasoning, completely different obligations or verification earlier than the ultimate response is returned to the person. Widespread points embrace overloaded prompting, poor software routing, unclear agent obligations and diminished reliability resulting from an excessive amount of complexity in a single agent.

A multi-agent system is a better option when the duty might overwhelm a single-agent design and while you want specialised brokers with clear roles, their very own instruments and separate obligations.

For instance, a software program engineering agent may go higher as a multi-agent system:

Orchestrator → Coder → Tester → Reviewer

The Orchestrator coordinates the workflow, the Coder agent generates the code, the Tester agent checks whether or not the code works, and the Reviewer agent opinions the answer to examine for lacking components or attainable enhancements.

One other instance is a analysis agent that researches a subject, retrieves data from completely different information sources and generates grounded content material:

Orchestrator → Retriever → Author → Verifier

The Retriever agent gathers data from the online and native paperwork saved in a vector database. The Author agent writes primarily based on the retrieved content material. The Verifier agent checks the written content material for errors, citations and factual accuracy earlier than the ultimate response is returned.

Multi-agent techniques make the workflow extra modular and provides every stage a transparent function. Nevertheless, they need to be used solely when the duty genuinely wants that design, as a result of they normally enhance latency, price and upkeep complexity resulting from extra LLM calls and extra transferring components.

A easy rule is:

Use a single agent when the duty is easy, has fewer steps and wishes only some instruments. Use a multi-agent system when the duty requires specialised roles, multi-step reasoning, stronger verification or coordination throughout completely different instruments and workflows.

Walkthrough of A Multi-Agent Mission

I constructed a mission referred to as Multi-Agent RAG Researcher to make the thought of multi-agent techniques extra sensible.

The purpose of the mission is to point out how a central agent can coordinate a number of specialised brokers to analysis a subject, retrieve proof from paperwork and the online, write a grounded content material and confirm the content material earlier than returning it to the person. As a substitute of utilizing one agent to deal with all the things, the system splits the workflow into completely different obligations.

Test the mission on github: https://github.com/ayoolaolafenwa/multi-agent-rag-researcher

Clone Mission repo

git clone https://github.com/ayoolaolafenwa/multi-agent-rag-researcher.git

Clone the repo to followup with the code alongside the put up. When the repo is cloned, the mission construction will seem like this:

.
├── docs/                         # Default PDF recordsdata
├── reminiscence/                       # SQLite-backed session reminiscence helpers
├── qdrant_vector_database/       # PDF ingestion and similarity search
├── ui/                           # Gradio app and UI handlers
├── utils/
│   ├── necessities.txt          # Python dependencies
├── worker_agents/                # Retriever, author, and verifier
├── orchestrator_agent.py         # Primary coordinator
└── run_orchestrator.py           # CLI entry level

Multi-Agent Structure

Knowledge Sources

There are two main information sources:

1. Qdrant Vector Database

Info retrieval from PDFs is dealt with within the following levels:

• A number of PDFs will be loaded from the docs/ folder or uploaded by way of the UI.
• Paperwork are cut up into chunks, transformed into embeddings, and saved in a neighborhood Qdrant assortment.
• Similarity search is then used to retrieve probably the most related chunks throughout the listed paperwork.
• The retrieved chunks embrace quotation metadata equivalent to doc title and web page quantity.

The doc retrieval a part of the mission the place Qdrant vector database is setup, PDF ingestion, chunking, embedding, and similarity search are managed is dealt with in qdrant_vector_database/vector_store.py .

2. Tavily Net Search

Tavily is used to retrieve up-to-date or exterior data from the online. The retriever agent can use it when:

• the listed PDFs don’t cowl the question
• doc proof is weak or incomplete
• newer data is required

Employee Brokers

1. Retriever Agent

The function is:

• It makes use of two instruments: PDF doc retrieval and net search.
• Given a question, it decides whether or not to make use of native paperwork, net search or each.
• If native doc proof is lacking or weak, it will possibly fall again to net search to collect broader or extra up-to-date context.

The code for the retriever agent with tavily net search out there in worker_agents/retriever.py . It makes use of gpt-5.4-mini with low reasoning effort.

2. Author Agent

The function is:

• It receives the retrieved data from the Retriever Agent.
• It writes a grounded draft primarily based on the out there proof.
• It contains supporting citations from PDFs or net sources when they’re out there.

The code for the author agent out there in worker_agents/author.py . It makes use of gpt-5.4 with low reasoning effort.

3. Verifier Agent

The function is:

• It receives the draft from the Author Agent along with the proof.
• It checks whether or not the claims within the draft are supported by the retrieved proof.
• It returns the ultimate verified response.

The code for the employee agent is out there in worker_agents/verifier.py . It makes use of gpt-5.4 with low reasoning effort.

Reminiscence

SQLite is used to offer short-term reminiscence for the multi-agent workflow. For a given session ID, the system shops:

• the newest person question
• the newest retrieved proof for that session

This permits the orchestrator to reuse related proof for follow-up questions as a substitute of retrieving the identical data once more each time.

The code for the reminiscence is out there in reminiscence/reminiscence.py .

Orchestrator

The orchestrator coordinates the three employee brokers: Retriever, Author and Verifier.

How the Orchestrator coordinates the Multi-Agent Workflow

• It receives the person question and, relying on the question, might reply immediately or start the evidence-based workflow.
• For a analysis question, it first checks whether or not related cached proof from the reminiscence for the present session will be reused.
• If cached proof will not be sufficient, it calls the Retriever Agent to collect proof from PDFs, the online or each.
• If there may be doc proof however the proof is weak, the Retriever Agent may fetch up-to-date data from the online to complement the native doc data.
• The orchestrator then passes the energetic proof and the person question to the Author Agent so it will possibly generate a grounded draft.
• Subsequent, it sends the draft and proof to the Verifier Agent, which checks the claims and returns the ultimate verified report.
• In the course of the session, the newest question and retrieved proof are saved in reminiscence for follow-up questions.
• In follow-up questions, the orchestrator might reuse cached proof as a substitute of calling the Retriever Agent once more, then proceed with the Author Agent and Verifier Agent to generate the ultimate response.

The code for the orchestrator is in orchestrator_agent.py . It makes use of gpt-5.4-mini with low reasoning effort.

The orchestrator has a guardrail that retains the system targeted on analysis and factual questions. It refuses unrelated basic duties equivalent to coding assist or simple arithmetic as a result of the purpose of the system is to perform as a analysis assistant.

Word: For the fashions used within the orchestrator and employee brokers, you’ll be able to change them from gpt-5.4 to any openai supplied mannequin of your alternative.

Mission Setup

Conditions

• Python 3.10 or newer
• OpenAI API key: Create an OpenAI Account when you don’t have one and Generate an API Key.
• Tavily API key: Tavily is a specialised web-search software for AI brokers. Create an account on Tavily.com, as soon as your profile is ready up, an API key will likely be generated you could copy into your surroundings. New account receives 1000 free credit that can be utilized for as much as 1000 net searches.

Set up

1. Create and activate a digital surroundings:

python3 -m venv env
supply env/bin/activate

2. Set up the dependencies:

cd multi-agent-rag-researcher
pip3 set up -r utils/necessities.txt

3. Create a utils/var.env file and retailer your API keys:

OPENAI_API_KEY=your_openai_api_key
TAVILY_API_KEY=your_tavily_api_key

4. Place the PDFs you need to index within the docs/ folder, or add PDFs later by way of the UI. The mission already contains present PDFs in docs/, presently Gemma 3 Technical Report.pdf and DeepSeek-V3.2.pdf, so you should use these immediately or change them with your individual paperwork.

Run Mission

Begin the command-line app:

python3 run_orchestrator.py

When the CLI begins, it ingests the PDFs in docs/ into the native Qdrant retailer. Kind q or exit to finish the session.

Run UI for Multi-Agent Chat

Begin the Gradio UI:

python3 ui/gradio_app.py

The UI mechanically masses the default PDFs from docs/ on startup. For those who add new PDFs, they change the energetic listed doc set for that UI session.

Demo Video of the Multi Agent Agent RAG Researcher

Notes

• Session reminiscence is saved in utils/reminiscence.db.
• Native Qdrant information is saved in utils/qdrant_storage/.
• The system is designed for analysis and factual query answering, not for unrelated general-purpose duties.

Conclusion

On this put up, I defined how an AI agent works, the way it makes use of instruments to work together with its surroundings, and the way the ReAct strategy helps it cause, plan, choose instruments and execute particular duties.

I additionally lined the structural design of AI brokers, which will be single-agent or multi-agent techniques. I defined how each designs work, when to decide on every one primarily based on the workflow, and in contrast single-agent implementation with multi-agent structure.

Lastly, I did a walkthrough of the multi-agent design behind my Multi-Agent RAG Researcher mission, displaying the way it makes use of an orchestrator to coordinate three employee brokers, retrieve data from the online and native paperwork, use reminiscence for consistency and write and confirm grounded content material earlier than returning the ultimate output.

Attain to me through:

E mail: [email protected]

Linkedin: https://www.linkedin.com/in/ayoola-olafenwa-003b901a9/

References

https://builders.openai.com/cookbook

https://builders.openai.com/api/docs/guides/function-calling