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’s new instruction cancels the previous request for a reminder and focuses solely on adding the company dinner event to the calendar. Previously, the agent was waiting for the user to specify how many days in advance the reminder should be set. Now, I adapt the plan by canceling that step and proceeding to extract the event details from the emails as originally planned. Once the details are confirmed (like the event date), I will update the calendar by creating the event without setting any reminder. This adaptation ensures the agent aligns with the user’s updated intent.

Response: I will cancel the reminder step and continue by searching for the year’s company dinner details in your emails, then add the event to your calendar without a reminder.