ReAct agent implementation in LangChain - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ component_behavior

intermediate

What is the output of this ReAct agent snippet?

Consider this simplified ReAct agent code using LangChain. What will be printed when the agent runs?

LangChain

from langchain.agents import ReActAgent
from langchain.schema import AgentAction, AgentFinish

class SimpleReActAgent(ReActAgent):
    def plan(self, intermediate_steps, **kwargs):
        if not intermediate_steps:
            return AgentAction(tool='search', tool_input='Python', log='Searching for Python')
        else:
            return AgentFinish(return_values={'output': 'Found info on Python'}, log='Done')

agent = SimpleReActAgent()
step1 = agent.plan([])
step2 = agent.plan([step1])
print(step1.log)
print(step2.log)

A Done\nSearching for Python

B Searching for Python\nDone

C Searching for Python\nSearching for Python

D Done\nDone

💡 Hint

Think about what the agent does when there are no intermediate steps versus when there are some.

The agent first plans with no intermediate steps, so it returns an AgentAction with log 'Searching for Python'. On the second call, since there is an intermediate step, it returns AgentFinish with log 'Done'.

❓ state_output

intermediate

What is the value of the agent's memory after these steps?

Given this ReAct agent code snippet, what will be the content of the agent's memory after executing the two steps?

LangChain

from langchain.agents import ReActAgent
from langchain.schema import AgentAction, AgentFinish

class MemoryReActAgent(ReActAgent):
    def __init__(self):
        super().__init__()
        self.memory = []
    def plan(self, intermediate_steps, **kwargs):
        if not intermediate_steps:
            self.memory.append('start')
            return AgentAction(tool='search', tool_input='LangChain', log='Starting search')
        else:
            self.memory.append('finish')
            return AgentFinish(return_values={'output': 'Result found'}, log='Finished')

agent = MemoryReActAgent()
agent.plan([])
agent.plan([AgentAction(tool='search', tool_input='LangChain', log='Starting search')])
memory_content = agent.memory

A []

B ['finish', 'start']

C ['start']

D ['start', 'finish']

💡 Hint

Look at when the memory list is appended to in the plan method.

The memory list appends 'start' on the first plan call (no intermediate steps) and 'finish' on the second call (with intermediate steps).

📝 Syntax

advanced

Which option causes a syntax error in this ReAct agent plan method?

Identify which plan method implementation will cause a syntax error when used in a ReAct agent subclass.

LangChain

def plan(self, intermediate_steps, **kwargs):
    # method body varies per option

A

if not intermediate_steps
    return AgentAction(tool='search', tool_input='Python', log='Searching')
else:
    return AgentFinish(return_values={'output': 'Done'}, log='Finished')

B

if not intermediate_steps:
    return AgentAction(tool='search', tool_input='Python', log='Searching')
return AgentFinish(return_values={'output': 'Done'}, log='Finished')

C

if not intermediate_steps:
    return AgentAction(tool='search', tool_input='Python', log='Searching')
else:
    return AgentFinish(return_values={'output': 'Done'}, log='Finished')

D

)'dehsiniF'=gol ,}'enoD' :'tuptuo'{=seulav_nruter(hsiniFtnegA nruter    
:esle
)'gnihcraeS'=gol ,'nohtyP'=tupni_loot ,'hcraes'=loot(noitcAtnegA nruter    
:spets_etaidemretni ton fi

💡 Hint

Check the syntax of the if statement carefully.

Option A is missing a colon after the if condition, causing a SyntaxError.

🔧 Debug

advanced

Why does this ReAct agent code raise a TypeError?

This ReAct agent subclass code raises a TypeError when calling plan. What is the cause?

LangChain

from langchain.agents import ReActAgent
from langchain.schema import AgentAction

class FaultyAgent(ReActAgent):
    def plan(self, intermediate_steps, **kwargs):
        return AgentAction(tool='search', tool_input=123, log='Searching')

agent = FaultyAgent()
agent.plan([])

A AgentAction requires log to be an int, but a string was given

B Missing return statement in plan method causes TypeError

C AgentAction expects tool_input to be a string, but 123 is an int causing TypeError

D plan method must not accept **kwargs causing TypeError

💡 Hint

Check the types of arguments passed to AgentAction.

AgentAction's tool_input should be a string describing the input to the tool. Passing an integer causes a TypeError.

🧠 Conceptual

expert

Which option best describes the ReAct agent's reasoning process?

In LangChain's ReAct agent implementation, what is the core idea behind the agent's reasoning and acting cycle?

A The agent alternates between thinking (reasoning) and acting (tool use) based on observations to solve complex tasks

B The agent only acts once after reasoning all steps internally without intermediate observations

C The agent randomly chooses tools without reasoning to explore the environment

D The agent uses a fixed sequence of tool calls without adapting to intermediate results

💡 Hint

Consider how ReAct combines reasoning and actions iteratively.

ReAct agents interleave reasoning steps with actions, using observations from tools to inform next reasoning steps, enabling dynamic problem solving.