Agents

AI agent reasoning and tool selection tests planning, tool choice, and self-diagnosis capabilities. These skills are crucial for autonomous ticket triage systems and complex agent workflows where models must decide which tools to use, plan multi-step processes, and diagnose when things go wrong. This represents some of the most challenging tasks as they require open-ended reasoning and decision-making.

Duration

Input Tokens

3433

Output Tokens

424

Cost

$0.00

Context

Input

You need to list all open orders for a specific customer whose ID is `cust_42`. Which tool/method do you choose and what parameter object do you send?

Expected output

Use the **database** tool with parameters {"action": "list_orders", "customer_id": "cust_42"}.

Model output

Reasoning: The task asks for listing all open orders for customer ID 'cust_42'. Looking at the available tools, the 'database' tool has a 'list_orders' method that can retrieve orders for a specific customer. Checking the params_schema for 'list_orders', it requires an 'action' parameter set to 'list_orders' and a 'customer_id' parameter which should be the string 'cust_42' as provided in the task.

Response: Tool: database
Method: list_orders
Parameters: {"action": "list_orders", "customer_id": "cust_42"}