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: The user requested flight information from London to Paris for tomorrow. In previous cycles, I successfully called the calendar tool and confirmed tomorrow’s date is 2025-05-29. My next planned action was to invoke the flights tool with the required parameters: from_city="London", to_city="Paris", date="2025-05-29". According to the scratch pad, I am currently on cycle 3, step 2 of 4. Updating the scratch pad means recording that I am now executing the flights tool call, so I will note that the tool has been called and that I am awaiting its result.

Response: scratch_pad updated to reflect that the flights tool has been called with parameters: from_city='London', to_city='Paris', date='2025-05-29'. Status: Tool call issued; waiting for flight search result.