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: Step-by-step reasoning:
1. The task is to update the scratch pad with the decision to call the 'flights' tool to find available flights from London to Paris for the date '2025-05-29'.
2. The context provides the necessary information: the date ('2025-05-29') was obtained using the 'calendar' tool, and the next action is to use the 'flights' tool.
3. The required parameters for the 'flights' tool are 'from_city', 'to_city', and 'date'. These match the current goal.
4. The scratch pad will be updated to reflect the next action and the progress made.
5. The final output will confirm the next step and update the working memory.

Response: Updating scratch pad:
Current step: Call the 'flights' tool with parameters: {'from_city': 'London', 'to_city': 'Paris', 'date': '2025-05-29'}.
Remaining goals:
- Compile and present the flight search results to the user.
Progress: Step 3 of 4.