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: I have reviewed the context, which details that the user wants available flights from London to Paris for tomorrow. The previous cycle with the calendar tool provided '2025-05-29' as tomorrow's date. The flights tool is available and requires 'from_city', 'to_city', and 'date' parameters. The scratch_pad shows that I need to use the flights tool next. Since the calendar's output matches the tool's required date format and there's an explicit next step in the scratch_pad, I need to update the scratch pad to reflect the action: calling the flights tool with the appropriate parameters.

Response: Scratch pad update:
Current step: Call 'flights' tool with parameters:
- from_city: London
- to_city: Paris
- date: 2025-05-29
Action: Executing 'flights' tool to retrieve available flights from London to Paris for 2025-05-29.
Remaining goals:
- Compile and present the flight results to the user.
Notes:
- Store the flights tool result in working memory for summary.
Progress: Step 3 of 4.