Skip to content

Agent Loop

Introduction

The core characteristic of an Agent is not tool usage, memory, or planning.

The defining characteristic of an Agent is the ability to operate in a continuous loop.

Unlike a traditional LLM that generates a single response, an Agent repeatedly:

  1. Observes the environment
  2. Reasons about the current state
  3. Decides what to do next
  4. Executes an action
  5. Evaluates the result

This process continues until the goal is achieved.


LLM vs Agent

LLM

A traditional LLM interaction is usually a single step.

User Input
     ↓
    LLM
     ↓
 Response

Example:

User:
What is the capital of France?

LLM:
Paris.

The execution ends immediately after the response is generated.


Agent

An Agent continuously interacts with its environment.

Goal
  ↓
Observe
  ↓
Reason
  ↓
Act
  ↓
Observe
  ↓
Reason
  ↓
Act

The process stops only when:

Goal Achieved

or

Task Aborted

The Basic Agent Loop

Most Agent systems can be represented as:

Observe
   ↓
Think
   ↓
Act
   ↓
Observe

A more detailed version:

Observation
     ↓
Reasoning
     ↓
Planning
     ↓
Action
     ↓
Environment
     ↓
Observation

This cycle forms the foundation of modern Agent systems.


Step 1: Observation

The Agent gathers information about the current state.

Sources may include:

  • User requests
  • Files
  • Databases
  • APIs
  • Web pages
  • Tool outputs

Example:

Goal:
Fix a failing unit test

Observation:

Test suite reports:

testCreateUser failed

The Agent now has context for decision making.


Step 2: Reasoning

The Agent analyzes available information.

Example:

The test is failing because
the expected value differs
from the actual value.

Reasoning is usually performed by an LLM.

The output is not yet an action.

It is a decision about what should happen next.


Step 3: Planning

The Agent determines the next step.

Example:

1. Open source file
2. Locate implementation
3. Compare logic
4. Modify code
5. Run tests

Planning can be:

Reactive

One step at a time

or

Structured

Generate complete plan first

Different Agent architectures choose different approaches.


Step 4: Action

The Agent executes a task.

Examples:

Read file
Search web
Call API
Execute code
Write file

Actions allow the Agent to interact with the outside world.

Without actions, an Agent becomes a chatbot.


Step 5: Feedback

Every action produces a result.

Example:

Run tests

Output:

3 tests passed
1 test failed

The Agent receives new information and enters the next iteration.

Observation

The loop continues.


Example: Coding Agent

Goal:

Fix failing test

Loop execution:

Observe:
Read test failure

Reason:
Identify likely bug

Act:
Open source file

Observe:
Review implementation

Reason:
Find incorrect logic

Act:
Modify code

Act:
Run tests

Observe:
All tests pass

Goal Achieved

Example: Research Agent

Goal:

Create report about AI coding agents

Loop execution:

Search web

Read articles

Extract information

Identify missing data

Search again

Generate report

Goal Achieved

The Agent repeatedly acquires new information before producing a final result.


Why the Loop Matters

Without a loop:

Input
 ↓
Output

The system cannot adapt.

With a loop:

Observe
 ↓
Act
 ↓
Observe
 ↓
Act

The system can respond to changing conditions.

This ability is what makes Agents useful for complex tasks.


Common Agent Loop Variations

OODA Loop

Originally developed for military decision making.

Observe
 ↓
Orient
 ↓
Decide
 ↓
Act

Many Agent systems resemble this structure.


ReAct

One of the most influential Agent patterns.

Thought
 ↓
Action
 ↓
Observation

Repeated until completion.


Plan-and-Execute

Create Plan
      ↓
Execute Step
      ↓
Execute Step
      ↓
Execute Step

Suitable for long tasks.


Reflection Loop

Adds self-review.

Generate
    ↓
Review
    ↓
Improve

Used by advanced Agent systems.


Modern Agent Runtime

Most production agents implement a loop similar to:

while not goal_completed:

    observe()

    think()

    choose_action()

    execute_action()

    evaluate_result()

This runtime loop is the heart of every Agent system.

Whether the Agent is:

  • a coding assistant
  • a research assistant
  • a browser agent
  • a multi-agent system

the same fundamental pattern exists.


Key Takeaways

The Agent Loop is the core mechanism of an Agent.

Agent Loop:

Observe
→ Reason
→ Plan
→ Act
→ Observe

An LLM typically generates one response.

An Agent continuously interacts with its environment.

The ability to repeatedly observe and act
is what transforms an LLM-powered system
into an Agent.

Comments