# Large Reasoning Model (LRM) Paradigm

> Use models trained to reason, not just predict — they're a different tool.

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

---

## Description
**Intent**: Recognize that reasoning-specialized models (o1, o3, Claude with extended thinking, DeepSeek-R1) operate differently from standard chat models and should be treated as a separate tool class with different prompting strategies, cost profiles, and use-case fits.

**Context**: Developers often apply the same prompting patterns to reasoning models that work on chat models — adding verbose CoT instructions, few-shot examples, or step-by-step directives. This actively hurts performance on LRMs, which are trained to reason internally and don't benefit from external scaffolding.

**Solution**: With LRMs — (1) keep system prompts minimal and direct, (2) don't add CoT instructions — the model already does it, (3) set a thinking budget appropriate to task difficulty, (4) expect higher latency and cost, (5) use for tasks where accuracy matters more than speed. Pair with adaptive-compute-allocation to route only hard tasks to LRMs. See also: extended-thinking, adaptive-compute-allocation, test-time-compute-scaling.



## Use Cases
- Hard reasoning tasks: theorem proving, complex code, multi-step planning, adversarial QA.
- Any task where your chat model keeps getting wrong answers despite good prompting.
- Pipelines where a slow, expensive, accurate step is preferable to a fast, cheap, wrong one.






## Trade-offs


### Advantages

- Native reasoning capability — not a prompt hack, it's in the weights.

- Dramatically better on hard benchmarks vs. comparable-size chat models.

- Thinking budget gives you direct control over the accuracy/cost tradeoff.




### Considerations & Drawbacks

- Expensive and slow — wrong choice for simple tasks or latency-sensitive paths.

- Standard prompting intuitions often don't apply — requires re-learning prompting habits.

- Thinking traces can be opaque and hard to debug when the model goes wrong.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/large-reasoning-model-paradigm/)