Opper

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.

Input Tokens

Output Tokens

Duration

Cost

Context

Input

You have decided to call the flight tool, update the scratch pad

Expected output

The scratch pad is updated with the new action, example model_output: Current step: Called 'flights' tool with parameters (from_city: London, to_city: Paris, date: 2025-05-29); waiting for tool result.
Remaining goals:
- Receive and process the flight search result.
- Summarize available flight options and present them to the user.
Notes:
- Ensure the result includes key details (flight numbers, times, prices if available).
- Store the raw flight result in working memory for reference.
- Prepare final summary once results are in.
Progress: Step 3 of 4.

Model output

Reasoning: We already obtained tomorrow’s date (2025-05-29) via the calendar tool. The next direct step is to query the flights tool with the route and date. I updated the scratch pad to reflect the decision, the exact parameters to use, confirmation of date format, and the remaining goals and next action.

Response: Current step: Call 'flights' tool to retrieve available flights from London to Paris for 2025-05-29.
Tool call parameters: {from_city: 'London', to_city: 'Paris', date: '2025-05-29'}
Remaining goals:
- Capture flights tool result in working memory.
- Compile and present the results to the user.
Notes:
- Date format confirmed (YYYY-MM-DD); '2025-05-29' is valid.
- Using city names is acceptable; tool accepts city name or code.
Progress: Step 3 of 4.
Next action: Execute flights tool call with the above parameters.