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: Based on the context provided, I can see that we are in cycle 3 of processing the user's request for flights from London to Paris for tomorrow. The calendar tool has already been called and returned that tomorrow's date is 2025-05-29. Now, according to the scratch pad notes and remaining goals, the next logical step is to call the flights tool with the required parameters (from_city: London, to_city: Paris, date: 2025-05-29). This directly follows the plan outlined in the trajectory and meets the user's original request.

Response: Current step: Calling flights tool with parameters (from_city: 'London', to_city: 'Paris', date: '2025-05-29')
Remaining goals:
- Compile and present the flight results to the user.
Notes:
- Flight search parameters match tool requirements.
- Store flight search result in working memory for summary.
Progress: Step 3 of 4.