# RaDeR

> RaDeR (Reasoning-aware Dense Retrieval) is a research model specifically trained on datasets that require reasoning, enabling it to learn how to retrieve relevant theorems and principles during intermediate reasoning steps. This approach allows the retriever to better generalize to diverse reasoning-intensive retrieval tasks.

- **URL:** https://arxiv.org/abs/2505.18405
- **Category:** Machine Learning Models
- **Tags:** dense-retrieval, reasoning-aware, research
- **Updated:** 2026-04-04 23:01
- **Canonical page:** https://vectordb.ever.works/items/rader

## Details

# RaDeR

RaDeR (Reasoning-aware Dense Retrieval) is a research model specifically trained on datasets that require reasoning, enabling it to learn how to retrieve relevant theorems and principles during intermediate reasoning steps. This approach allows the retriever to better generalize to diverse reasoning-intensive retrieval tasks.

[https://arxiv.org/abs/2505.18405](https://arxiv.org/abs/2505.18405)

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/rader._