Reasoning

Reasoning is an advanced capability of AI that enables it to tackle complex tasks through explicit, step-by-step logical inference. Reasoning models break down problems into smaller sub-tasks rather than solving them in a single pass. Compared to direct answer generation, it offers two key advantages:

1. Improved problem-solving intelligence
2. Transparent and traceable intermediate reasoning steps

This functionality is particularly well-suited for domains that require multi-step reasoning, such as scientific analysis, legal interpretation, or strategic decision-making. However, since the reasoning step needs additional computation and memory usage, it can increase latency and overall resource consumption. Therefore, it’s important to enable reasoning only when necessary, based on the complexity of your use case.

Reasoning may not be supported on some models. The Qwen3 model currently available in Ailoy supports reasoning.

How to enable reasoning

In Ailoy, You can activate reasoning feature by simply specifying an option reasoning.

Python

for resp in agent.query(
    "Please solve me a simultaneous equation: x+y=3, 4x+3y=12",
    reasoning=True
):
    agent.print(resp)

JavaScript(Node)

for await (const resp of agent.query(
  "Please solve me a simultaneous equation: x+y=3, 4x+3y=12",
  { reasoning: true }
)) {
  agent.print(resp);
}

note

Note: Qwen3-0.6b is too small to perform effective reasoning. We recommend using a model with bigger parameters for reasoning tasks.