Reasoning Patterns

This guide helps you understand how to interact effectively with agents operating under different reasoning patterns ReAct, Reflection, CodeAct, and DeepAgent. Each mode offers distinct strengths and is suited for specific types of queries.

1. ReAct Mode (Reasoning + Acting)

What is ReAct?

ReAct (Reason + Act) enables the agent to think step-by-step and take real-world actions using tools like Web Search, RAG (Retrieval-Augmented Generation), and File Attachments.

It decides which tool to use by analyzing the user's query and routes it to the appropriate tool dynamically, based on the task at hand.

What ReAct Can Do:

Think step-by-step to solve multi-part queries.

Route queries to the best-suited tool (e.g., WebSearch, RAG, Attachments).

Use tools to retrieve or process external information.

What ReAct Cannot Do:

Execute code or scripts.

Generate or manipulate downloadable files (e.g., Excel, PDFs).

Perform deep iterative revisions on its own outputs.

Correct Usage:

User: "What is the latest update on AI regulation in the EU?"
Agent (ReAct): Uses WebSearch and RAG tools to gather and summarize current information.

Incorrect Usage:

User: "Execute this Python script and return the result."
Problem: ReAct does not support code execution. Use CodeAct instead.

2. Reflection Mode

What is Reflection?

Reflection enhances the agent's intelligence by enabling it to evaluate its own answers, spot errors, and revise responses over multiple iterations.

It combines deep thinking with the ability to use tools (same as ReAct: WebSearch, RAG, Attachments), making it highly effective for tasks that need both external information and internal reasoning.

What Reflection Can Do:

Reflect on and revise previous answers.

Use external tools just like ReAct (e.g., search, documents).

Improve answer quality through self-assessment.

Provide more thoughtful and accurate responses.

What Reflection Cannot Do:

Execute or write live code.

Generate downloadable files like Excel, PDFs.

Perform real-time computations or data analysis.

Correct Usage:

User: "What are the key arguments in favor of renewable energy?"
Agent (Reflection): Provides a response, rethinks the logic, and returns a refined, structured answer.

Incorrect Usage:

User: "Create a plot of sales data from this Excel file."
Problem: Reflection does not execute code or analyze structured data. Use CodeAct.

3. CodeAct Mode

What is CodeAct?

CodeAct allows the agent to generate, execute, and refine code to solve problems. It's ideal for tasks requiring logic, computation, data manipulation, or output generation.

CodeAct also supports:

Generating and downloading files (e.g., CSVs, Excel)

Plotting graphs

Analyzing uploaded structured data

What CodeAct Can Do:

Write and run Python code.

Analyze uploaded files like Excel, CSV.

Generate plots and charts.

Create downloadable data files.

What CodeAct Cannot Do:

Access the internet or search the web.

Use external tools like WebSearch or RAG.

Perform real-time information retrieval.

Correct Usage:

User: "Plot a line graph of temperatures from this CSV file."
Agent (CodeAct): Analyzes the file, writes and runs code, returns the graph.

Incorrect Usage:

User: "Search GitHub for Langfuse examples."
Problem: CodeAct can't perform web searches. Use ReAct.

4. DeepAgent Mode

What is DeepAgent?

DeepAgent is an open source agent harness built for complex, long-running tasks. It combines LangChain and LangGraph to handle planning, sub-agent delegation, and persistent memory across multi-step workflows.

What DeepAgent Can Do:

Decompose complex tasks into subtasks and track progress through planning tools.

Spawn sub-agents to handle independent subtasks in parallel.

Persist knowledge across sessions using a virtual filesystem.

Compress and manage context natively for long-running tasks.

What DeepAgent Cannot Do:

Handle simple, single-step queries (use ReAct instead).

Perform self-reflective answer revision (use Reflection instead).

Correct Usage:

User: "Research the competitive landscape for our product and generate a summary report."
Agent (DeepAgent): Decomposes the task, spawns sub-agents for research and summarization, and returns a structured report.

Incorrect Usage:

User: "What is the capital of France?"
Problem: DeepAgent is built for complex, long-horizon tasks. Use ReAct for simple lookups.

Summary

Feature	ReAct	Reflection	CodeAct	DeepAgent
Step-by-step reasoning	Yes	Yes	Yes	Yes
Use of external tools	Yes (Web, RAG, Attachments)	Yes (same tools as ReAct)	No	Yes (via sub-agents)
Self-reflection and revision	No	Yes	No	Yes
Code execution & file creation	No	No	Yes	Yes
Data analysis & plotting	No	No	Yes	Yes
Multi-step task planning	No	No	No	Yes
Sub-agent delegation	No	No	No	Yes
Long-running task support	No	No	No	Yes
Persistent memory across sessions	No	No	No	Yes

Before you ask a question, check the active reasoning pattern of the agent. Selecting the right mode ensures you get the most relevant and useful response.

Use ReAct for: live searches, reading from uploaded files, or when external tools are required.

Use Reflection for: complex logic problems that may require answer refinement.

Use CodeAct for: coding tasks, data analysis, graphing, and generating downloadable content.

Use DeepAgent for: complex, long-horizon tasks requiring planning, sub-agent delegation, and persistent memory across steps.

Reasoning Patterns

1. ReAct Mode (Reasoning + Acting)#

What is ReAct?#

What ReAct Can Do:#

What ReAct Cannot Do:#

Correct Usage:#

Incorrect Usage:#

2. Reflection Mode#

What is Reflection?#

What Reflection Can Do:#

What Reflection Cannot Do:#

Correct Usage:#

Incorrect Usage:#

3. CodeAct Mode#

What is CodeAct?#

What CodeAct Can Do:#

What CodeAct Cannot Do:#

Correct Usage:#

Incorrect Usage:#

4. DeepAgent Mode#

What is DeepAgent?#

What DeepAgent Can Do:#

What DeepAgent Cannot Do:#

Correct Usage:#

Incorrect Usage:#

Summary#

1. ReAct Mode (Reasoning + Acting)

What is ReAct?

What ReAct Can Do:

What ReAct Cannot Do:

Correct Usage:

Incorrect Usage:

2. Reflection Mode

What is Reflection?

What Reflection Can Do:

What Reflection Cannot Do:

Correct Usage:

Incorrect Usage:

3. CodeAct Mode

What is CodeAct?

What CodeAct Can Do:

What CodeAct Cannot Do:

Correct Usage:

Incorrect Usage:

4. DeepAgent Mode

What is DeepAgent?

What DeepAgent Can Do:

What DeepAgent Cannot Do:

Correct Usage:

Incorrect Usage:

Summary