If your context is full of similar past action-observation pairs, the model will tend to follow that pattern, even when it’s no longer optimal.
This can be dangerous in tasks that involve repetitive decisions or actions. For example, when using Manus to help review a batch of 20 resumes, the agent often falls into a rhythm—repeating similar actions simply because that’s what it sees in the context. This leads to drift, overgeneralization, or sometimes hallucination.
The fix is to increase diversity. Manus introduces small amounts of structured variation in actions and observations—different serialization templates, alternate phrasing, minor noise in order or formatting. This controlled randomness helps break the pattern and tweaks the model’s attention. In other words, don’t few-shot yourself into a rut. The more uniform your context, the more brittle your agent becomes.
Best to keep diversity in your few-shot examples, lest you inadvertently create an unthinking rule where you meant to demonstrate an understanding.