ReAct agent implementation in LangChain - Performance & Optimization

Performance: ReAct agent implementation

MEDIUM IMPACT

This affects the responsiveness and speed of AI agent interactions by controlling how reasoning and actions are processed and rendered.

Implementing a ReAct agent that processes reasoning and actions sequentially with blocking calls

LangChain

async function reactAgent(input) {
  const reasoningPromise = reason(input);
  const actionPromise = reasoningPromise.then(reasoning => act(reasoning));
  return await actionPromise;
}

Chains promises to avoid unnecessary blocking, allowing partial processing and better responsiveness.

📈 Performance GainReduces blocking time, improving INP by allowing earlier interaction readiness.

Implementing a ReAct agent that processes reasoning and actions sequentially with blocking calls

LangChain

async function reactAgent(input) {
  const reasoning = await reason(input); // blocks until done
  const action = await act(reasoning); // blocks until done
  return action;
}

Sequential awaits cause blocking, increasing response time and reducing interaction speed.

📉 Performance CostBlocks rendering and user interaction for the entire reasoning and action duration, increasing INP.

Performance Comparison

Pattern	DOM Operations	Reflows	Paint Cost	Verdict
Sequential blocking awaits	Minimal DOM changes	0 reflows	Low paint cost	[!] OK but blocks interaction
Asynchronous promise chaining	Minimal DOM changes	0 reflows	Low paint cost	[OK] Good for responsiveness

Rendering Pipeline

The ReAct agent's reasoning and action steps affect the interaction responsiveness stage by controlling when results are ready to render or respond to user input.

→JavaScript Execution

→Interaction Responsiveness

→Rendering

⚠️ BottleneckJavaScript Execution blocking due to synchronous or sequential awaits

Core Web Vital Affected

INP

This affects the responsiveness and speed of AI agent interactions by controlling how reasoning and actions are processed and rendered.

Optimization Tips

1Avoid sequential blocking awaits in ReAct agents to improve responsiveness.

2Use asynchronous promise chaining to allow incremental processing.

3Monitor JavaScript execution time to reduce interaction delays.

Performance Quiz - 3 Questions

What is the main performance issue with sequential await calls in a ReAct agent?

A They increase bundle size significantly

B They block interaction until all steps complete

C They cause excessive DOM reflows

D They cause layout shifts

DevTools: Performance

How to check: Record a performance profile while interacting with the agent. Look for long tasks or blocking JavaScript execution during reasoning and action steps.

What to look for: Long blocking tasks indicate poor responsiveness; shorter, asynchronous tasks show better INP.

Practice

1. What is the main purpose of a ReAct agent in LangChain?

easy

A. To store data without processing or reasoning

B. To only perform simple, single-step actions without reasoning

C. To replace language models with rule-based systems

D. To combine reasoning and actions step-by-step to solve complex tasks

Solution

1. Step 1: Understand the ReAct agent concept

   The ReAct agent is designed to think (reason) and act (perform tasks) in steps.

2. Step 2: Identify its main use

   It helps solve problems that need multiple steps, like searching and calculating.

3. Final Answer:

   To combine reasoning and actions step-by-step to solve complex tasks -> Option D

4. Quick Check:

   ReAct agent = reasoning + actions [OK]

Hint: ReAct means think and act together step-by-step [OK]

Common Mistakes:

• Thinking it only acts without reasoning
• Confusing it with simple action-only agents
• Assuming it replaces language models

2. Which of the following is the correct way to create a ReAct agent in LangChain?

easy

A. agent = ReActAgent(llm=llm, tools=tools)

B. agent = ReActAgent(tools=llm, llm=tools)

C. agent = ReActAgent()

D. agent = ReActAgent(llm)

Solution

1. Step 1: Recall ReAct agent constructor parameters

   The ReAct agent requires a language model (llm) and a list of tools (tools) as named arguments.

2. Step 2: Check each option for correct syntax

   agent = ReActAgent(llm=llm, tools=tools) correctly passes llm and tools by name. agent = ReActAgent(tools=llm, llm=tools) swaps them incorrectly. agent = ReActAgent() misses required arguments. agent = ReActAgent(llm) passes only llm without tools.

3. Final Answer:

   agent = ReActAgent(llm=llm, tools=tools) -> Option A

4. Quick Check:

   Correct parameters = llm and tools [OK]

Hint: Pass llm and tools as named parameters to ReActAgent [OK]

Common Mistakes:

• Swapping llm and tools arguments
• Omitting required parameters
• Passing parameters positionally without names

3. Given this code snippet, what will be the output behavior of the ReAct agent?

from langchain.agents import ReActAgent
from langchain.llms import OpenAI

llm = OpenAI(temperature=0)
tools = [search_tool, calculator_tool]
agent = ReActAgent(llm=llm, tools=tools)

response = agent.run('What is the capital of France and what is 5 plus 3?')

medium

A. The agent will first search for the capital of France, then calculate 5 plus 3, returning both answers.

B. The agent will only perform the search and ignore the calculation.

C. The agent will return an error because multiple tools cannot be used.

D. The agent will calculate 5 plus 3 first, then search for the capital.

Solution

1. Step 1: Understand ReAct agent multi-tool usage

   The ReAct agent can use multiple tools and decides which to use based on the question.

2. Step 2: Analyze the question and agent behavior

   The question asks two things: capital of France (search) and 5 plus 3 (calculator). The agent will perform both actions step-by-step.

3. Final Answer:

   The agent will first search for the capital of France, then calculate 5 plus 3, returning both answers. -> Option A

4. Quick Check:

   Multi-tool agent answers multi-part questions [OK]

Hint: ReAct agents use all needed tools for multi-part questions [OK]

Common Mistakes:

• Thinking agent uses only one tool per run
• Assuming order is reversed without reason
• Believing multiple tools cause errors

4. What is the likely cause of this error when running a ReAct agent?

TypeError: ReActAgent.__init__() missing 1 required positional argument: 'llm'

medium

A. The ReActAgent does not accept an llm argument.

B. The tools list was empty, causing the error.

C. The ReActAgent was created without passing the required language model (llm) argument.

D. The run method was called with an invalid input string.

Solution

1. Step 1: Interpret the error message

   The error says the __init__ method is missing the required 'llm' argument.

2. Step 2: Identify correct constructor usage

   ReActAgent requires an llm parameter when created. Missing it causes this TypeError.

3. Final Answer:

   The ReActAgent was created without passing the required language model (llm) argument. -> Option C

4. Quick Check:

   Missing llm argument = TypeError [OK]

Hint: Always pass llm when creating ReActAgent [OK]

Common Mistakes:

• Forgetting to pass llm argument
• Confusing tools argument with llm
• Misreading error as related to run method

5. You want to build a ReAct agent that can handle a question requiring web search, math calculation, and database lookup. Which setup correctly supports this multi-step reasoning and acting?

hard

A. Create separate agents for each tool and run them independently without combining

B. Create a ReActAgent with llm and a tools list including search_tool, calculator_tool, and db_tool

C. Use only the calculator_tool since it can handle all tasks internally

D. Create a ReActAgent with llm but no tools, relying on the model alone

Solution

1. Step 1: Identify the need for multiple tools

   The question requires web search, math calculation, and database lookup, so multiple tools are needed.

2. Step 2: Choose the correct agent setup

   ReActAgent supports multiple tools passed as a list along with the llm to reason and act step-by-step.

3. Step 3: Evaluate other options

   Separate agents won't combine reasoning easily; calculator_tool alone can't do all tasks; no tools means no external actions.

4. Final Answer:

   Create a ReActAgent with llm and a tools list including search_tool, calculator_tool, and db_tool -> Option B

5. Quick Check:

   Multi-tool ReActAgent = best for multi-step tasks [OK]

Hint: Pass all needed tools in one ReActAgent for multi-step tasks [OK]

Common Mistakes:

• Trying to run separate agents instead of one combined
• Assuming one tool can do all tasks
• Not passing any tools to the agent