# Best-of-N Sampling

> Generate N candidates, score them with a reward model or rule-based scorer, return the best — quality lift without retraining.

- **Category**: Agentic AI
- **Subcategory**: Verification & Reflection
- **Canonical URL**: https://designpattern.fyi/patterns/best_of_n/

---

## Description
**Intent**: Trade inference cost for quality by picking the best output from multiple candidates.

**Context**: Your LLM output quality varies noticeably from sample to sample — code reviews, translations, customer replies. You have a scorer that can rank candidates, and running the model a few extra times per prompt is affordable.

**Solution**: Generate N candidates at non-zero temperature. Score each with a reward model or rule-based scorer. Return the top-1 (or top-K). The BoNBoN approach fine-tunes a model to mimic the BoN distribution directly, eliminating per-inference sampling cost at serving time.


## Use Cases
- A scorer or reward model exists that ranks candidates better than the generator selects them.
- Quality lift from selecting the best of N samples justifies the N-fold inference cost.
- Temperature can be raised enough to produce meaningfully diverse candidates.





## Trade-offs


### Advantages

- Quality lift without retraining the base model.

- Simple trade-off knob: increase N for more quality, decrease for less cost.




### Considerations & Drawbacks

- Cost scales linearly with N — expensive at large N.

- Reward hacking: candidates can game a flawed scorer, giving the illusion of quality.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/best-of-n-sampling/)