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.

100
Duration
24s
Input Tokens
3370
Output Tokens
948
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: Analyzed the tools and their schemas: the database tool has a list_orders action that requires only customer_id. There’s no built-in status filter, so I’d retrieve all orders for cust_42 in one call and then filter for status = 'open' in post-processing to minimize tool calls.

Response: Tool: database, method/action: list_orders. Params: {"action":"list_orders","customer_id":"cust_42"}