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.

Agents – cerebras/llama-4-maverick-17b-128e-instruct Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

Context

Input

The flights.search_flights call has returned 6 available flights from London to Paris for tomorrow. What is the next tool you will call, and why?

Expected output

The next tool is memory, to store the flights tool call result.

Model output

Reasoning: The task is to determine the next tool to call after the flights.search_flights call has returned 6 available flights from London to Paris for tomorrow. The context provided indicates that the user wants the cheapest flights from London to Paris for tomorrow and return the top 3 options. The current step is to filter the available flights by price and select the top 3 cheapest options. The next logical step is to use the 'flights.filter_by_price' method to achieve this. After filtering, the results will be stored in memory using the 'memory.store_item' method.

Response: flights.filter_by_price