## Diagram: LLM Agent Workflow for Cost-Effective Smartphone Purchase
### Overview
This diagram illustrates the workflow of a Large Language Model (LLM) agent using both text/JSON as action and code as action to determine the most cost-effective country to purchase a smartphone model "CodeAct 1". The diagram depicts a series of interactions between the LLM agent, available APIs, and the environment, culminating in the identification of the country with the lowest final price. The diagram is split into two main sections, one for LLM Agent using Text/JSON as Action and one for CodeAct: LLM Agent using Code as Action. A central arrow indicates "Fewer Actions Required!".
### Components/Axes
The diagram consists of the following components:
* **Instruction:** "Determine the most cost-effective country to purchase the smartphone model “CodeAct 1”. The countries to consider are the USA, Japan, Germany, and India." (Top-center)
* **Available APIs:** A list of five APIs with their descriptions and return types.
* `lookup_rates(country: str) -> (float, float)`
* `convert_and_tax(price: float, exchange_rate: float, tax_rate: float) -> float`
* `estimate_final_price(converted_price: float, shipping_cost: float) -> float`
* `lookup_phone_price(model: str, country: str) -> float`
* `estimate_shipping_cost(destination_country: str) -> float` (Top-right)
* **LLM Agent (Text/JSON):** A sequence of "Think" and "Action" steps.
* **LLM Agent (Code):** A sequence of "Think" and "Action" steps, including a code block.
* **Environment:** Displays the output of API calls.
* **Control & Data Flow of Code Simplifies Complex Operations:** A box with text and an arrow pointing to the CodeAct section. (Center-right)
* **Re-use Win Functionary by Infrastructure Software System (Library):** A box with text and a small icon. (Bottom-right)
* **Response:** "USA is the most cost-effective country." (Bottom-center)
### Detailed Analysis or Content Details
**LLM Agent (Text/JSON) Steps:**
1. **Think:** "I should calculate the phone price in USD for each country, then find the most cost-effective country."
2. **Action:** `lookup_rates`, Germany
* **JSON:** `{"tool": "lookup_rates", "country": "Germany"}`
* **Environment:** `1.1, 0.19`
3. **Action:** `lookup_phone_price`, CodeAct 1, Germany
* **JSON:** `{"tool": "lookup_phone_price", "model": "CodeAct 1", "country": "Germany"}`
* **Environment:** `780`
4. **Action:** `convert_and_tax`, 780, 1.1, 0.19
* **JSON:** `{"tool": "convert_and_tax", "price": 780, "exchange_rate": 1.1, "tax_rate": 0.19}`
* **Environment:** `916.3`
5. **Action:** `lookup_rates`, Japan
* **JSON:** `{"tool": "lookup_rates", "country": "Japan"}`
* **Environment:** `0.009, 0.1`
6. **Action:** `lookup_phone_price`, CodeAct 1, Japan
* **JSON:** `{"tool": "lookup_phone_price", "model": "CodeAct 1", "country": "Japan"}`
* **Environment:** `900`
**LLM Agent (Code) Steps:**
1. **Think:** "I should calculate the phone price in USD for each country, then find the most cost-effective country."
2. **Action:**
* Code Block:
```python
countries = ['USA', 'Japan', 'Germany', 'India']
final_prices = {}
for country in countries:
exchange_rate, tax_rate = lookup_rates(country)
local_price = lookup_phone_price("Act 1", country)
converted_price = convert_and_tax(
local_price, exchange_rate, tax_rate
)
shipping_cost = estimate_shipping_cost(country)
final_price = estimate_final_price(converted_price, shipping_cost)
final_prices[country] = final_price
most_cost_effective_country = min(final_prices, key=final_prices.get)
most_cost_effective_price = final_prices[most_cost_effective_country]
print(most_cost_effective_country, most_cost_effective_price)
```
3. **Action:** `lookup_rates`, "USA"
* **JSON:** `{"tool": "lookup_rates", "country": "USA"}`
* **Environment:** `1, 0.08`
**Response:** "USA is the most cost-effective country."
### Key Observations
* The diagram demonstrates a comparison between using text/JSON actions versus a code-based action for the same task.
* The code-based approach appears more concise and efficient, as it iterates through all countries within a single action.
* The diagram highlights the use of multiple APIs to calculate the final price, including exchange rates, taxes, and shipping costs.
* The "Fewer Actions Required!" arrow suggests that the code-based approach requires fewer interactions with the environment.
### Interpretation
The diagram illustrates a modern approach to problem-solving using LLM agents. The agent is not simply providing answers but is actively interacting with tools (APIs) and the environment to gather information and make decisions. The comparison between the text/JSON and code-based approaches suggests that leveraging code execution within LLM agents can significantly improve efficiency and reduce the number of steps required to achieve a desired outcome. The diagram also emphasizes the importance of infrastructure software systems (libraries) for reusability and streamlining complex operations. The final response, identifying the USA as the most cost-effective country, is the result of a complex series of calculations and interactions orchestrated by the LLM agent. The diagram is a visual representation of the agent's reasoning process and the data flow involved in arriving at this conclusion. The diagram is a demonstration of the power of combining LLMs with code execution for complex tasks.
