Scribd
Upload
876 views9 pages

LangGraph: Multi-Agent Systems

LangGraph: multi-agent systems

Uploaded by

alfonso77
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
876 views9 pages

LangGraph: Multi-Agent Systems

LangGraph: multi-agent systems

Uploaded by

alfonso77
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

MULTI-AGENT

SYSTEMS

SARVESHWARAN R
[email protected]
Agents in LangGraph
We want LLM systems that can pick their own control flow!

An agent is a system that uses an LLM to decide the control flow


of an application.

Ex: RAG performs retrieval of relevant documents to a question,


and passes those documents to an LLM in order to ground the
response. Often a control flow of steps before or after an LLM is
called a "chain."

An agent gives an LLM some degree of control over the sequence


of steps in the application
Control of an Application
Using an LLM to route between two potential paths

Using an LLM to decide which of many tools to call

Using an LLM to decide whether the generated answer is sufficient or more work is
need

Other extreme -> A fully


One extreme -> a router autonomous long-running
allows an LLM to select a agent may have complete
single step from a freedom to select any
specified set of options sequence of steps that it
wants for a given problem.
01
MULTI-AGENT
ARCHITECTURES
AN AGENT IS A SYSTEM THAT USES AN LLM TO DECIDE THE
CONTROL FLOW OF AN APPLICATION
02 NETWORK AGENT

Each agent can communicate with every other agent.

Any agent can decide which other agent to call next.

Divide-and-conquer approach - Specialized agent for each


task
03 SUPERVISOR AGENT

Each agent communicates with a single supervisor agent.

Supervisor agent makes decisions on which agent should


be called next.
04 HIERARCHICAL AGENT
Define a multi-agent system with a supervisor of supervisors.

Generalization of the supervisor architecture and allows for


more complex control flows.
Challenges
There is often a trade-off between control and reliability.

As we give LLMs more control, the application often become less


reliable.

This can be due to factors such as LLM non-determinism and / or


errors in selecting tools (or steps) that the agent uses (takes).
CONGRATULATIONS

You have reached the end, now

If you want to help your network

REPOST THIS

SARVESHWARAN R

You might also like