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

USER INTERRUPTION: The user says, "Actually, never mind about the reminder — just make sure the company dinner is on my calendar."  What do you do to adapt your plan?

Expected output

I will revise the plan by removing the reminder step entirely, then proceed to: (1) search and read the relevant email to obtain the dinner date, (2) check for calendar conflicts, (3) create the event with calendar.create_event **without** the reminder_days_before parameter, and (4) inform the user of any conflicts and confirm the event has been added.  What matters is that the plan is explicitly updated and no reminder is scheduled.

Model output

Reasoning: The user has clarified that they no longer want a reminder for the company dinner, but they still need the dinner event added to their calendar. I follow the existing plan to locate the dinner date from emails, then add the event with no reminder. The plan now skips the reminder step: 
1. Search the user’s emails for "yearly company dinner".
2. Read the relevant email and extract the event date.
3. Create a calendar event named "Company Dinner" on that date with no reminder.
4. Confirm the addition and notify the user.
Since the reminder is no longer requested, the reminder_days_before field will be omitted or set to 0.

Response: The company dinner has been added to your calendar for the date found in your email. No reminder has been set.