Function calling in LLMs in Agentic AI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

How does function calling improve LLM responses?

Large Language Models (LLMs) can call external functions during a conversation. What is the main benefit of this feature?

A It prevents the LLM from making any mistakes in grammar.

B It allows the LLM to access real-time or external data beyond its training.

C It makes the LLM generate longer text outputs automatically.

D It reduces the model size by offloading computations to the function.

💡 Hint

Think about how LLMs can get information they don't know internally.

Function calling lets LLMs request data or perform actions outside their training, like fetching current weather or database info, improving response accuracy.

❓ Predict Output

intermediate

Output of LLM function call simulation

Given the following Python simulation of an LLM calling a function, what is the printed output?

Agentic AI

def get_temperature(city):
    return f"The temperature in {city} is 22°C."

user_input = "What's the temperature in Paris?"

# Simulate LLM detecting function call
if "temperature" in user_input:
    city = user_input.split()[-1].strip('?')
    response = get_temperature(city)
else:
    response = "I don't know."

print(response)

A The temperature in Paris is 22°C.

B I don't know.

C The temperature in Paris is 22F.

D SyntaxError

💡 Hint

Look at how the city name is extracted and passed to the function.

The code extracts 'Paris' from the input and calls get_temperature('Paris'), which returns the temperature string with 22°C.

❓ Model Choice

advanced

Choosing the best LLM model for function calling

You want to build a chatbot that uses function calling to fetch live stock prices. Which model type is best suited for this?

A A large LLM trained only on static text data without function calling.

B A small LLM without function calling support but fine-tuned on finance data.

C A rule-based chatbot with no machine learning.

D A large LLM with built-in function calling and API integration capabilities.

💡 Hint

Consider which model can dynamically call external APIs for live data.

A large LLM with function calling and API integration can request live stock prices dynamically, making it the best choice.

❓ Hyperparameter

advanced

Effect of temperature setting on function calling outputs

When using an LLM with function calling, how does increasing the temperature hyperparameter affect the function call behavior?

A It makes the LLM more likely to call functions randomly, even when not needed.

B It makes the LLM more deterministic and less creative in calling functions.

C It has no effect on function calling decisions, only on text generation style.

D It disables function calling entirely.

💡 Hint

Think about how temperature affects randomness in LLM outputs.

Higher temperature increases randomness, so the LLM might call functions more freely, sometimes unnecessarily.

🔧 Debug

expert

Why does this LLM function call fail to execute?

Consider this snippet where an LLM is supposed to call a function to get current time, but it never executes the function. What is the likely cause?

Agentic AI

def get_current_time():
    from datetime import datetime
    return datetime.now().strftime('%H:%M:%S')

llm_response = '{"function_call": {"name": "get_current_time"}}'

# Code to parse and execute function call
import json
response_dict = json.loads(llm_response)

if response_dict.get('function_call'):
    func_name = response_dict['function_call']['name']
    if func_name == 'get_current_time':
        result = get_current_time()
    else:
        result = None
else:
    result = None

print(result)

A The JSON string is malformed and causes a parsing error.

B The function get_current_time is not defined in the code.

C The function get_current_time is assigned but not called, so result is the function object, not its output.

D The print statement is missing parentheses causing a syntax error.

💡 Hint

Check if the function is called or just referenced.

The code assigns the function object to result without calling it (missing parentheses), so printing result shows the function object, not the time string.