# ReST-EM

> Self-improve the model by training on its own high-quality outputs.

- **Category**: Agentic AI
- **Subcategory**: Reasoning
- **Canonical URL**: https://designpattern.fyi/patterns/rest_em/

---

## Description
**Intent**: Bootstrap a stronger reasoning model by collecting the model's own correct outputs, filtering them through a verifier, and fine-tuning on the winners — repeating the cycle.

**Context**: Getting high-quality reasoning traces for fine-tuning is expensive when it requires human labelers. ReST-EM sidesteps this by using the model itself as a data generator and a verifier (or an external oracle) as the quality filter — an EM loop where E-step = generate, M-step = fine-tune on correct outputs.

**Solution**: (1) Sample many completions from the current model for each training problem. (2) Filter completions using a verifier (unit tests, a ground-truth checker, a reward model). (3) Fine-tune the model on the passing completions. (4) Repeat with the improved model. Each iteration raises the quality floor. Requires control over fine-tuning — not an API prompting pattern. See also: STaR-bootstrapping, generate-and-test-strategy, reflexion.



## Use Cases
- Fine-tuning pipelines where you have verifiable tasks but no human reasoning traces.
- Code generation, math, or logic domains where correctness is programmatically checkable.
- Distilling reasoning capability from a large model into a smaller one via self-generated data.






## Trade-offs


### Advantages

- Generates training data without human annotation — scales cheaply.

- Each iteration genuinely improves the model's reasoning floor.

- Works well in domains with strong verifiers (code, math).




### Considerations & Drawbacks

- Requires fine-tuning access — not applicable to API-only deployments.

- Verifier quality gates everything; a weak verifier trains on wrong answers.

- Can reinforce confident-but-wrong reasoning patterns if the verifier has blind spots.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/rest-em/)