README.md

---
license: mit
language:
- en
base_model:
- intfloat/e5-base-v2
pipeline_tag: sentence-similarity
---

## Introduction

This is the Agentic-R trained in our paper: Agentic-R: Learning to Retrieve for Agentic Search
 ([📝arXiv](https://arxiv.org/pdf/2601.11888)). Please refer our [🧩github repository](https://github.com/8421BCD/Agentic-R) for the detailed usage of our Agentic-R.

## Usage

Our **Agentic-R** query encoder is designed for agentic search scenarios.  
For queries, the input format is:
`query: <original_question> [SEP] <agent_query>`.
Passages use the standard `passage:` prefix following E5.

Below is an example of how to compute embeddings using sentence_transformers:

```python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("liuwenhan/Agentic-R_e5")

input_texts = [
    # Query encoder input:
    # original_question [SEP] current_query
    "query: Who wrote The Old Man and the Sea? [SEP] Old Man and the Sea",

    # Passages
    "passage: The Old Man and the Sea is a short novel written by the American author Ernest Hemingway in 1951.",
    "passage: Ernest Hemingway was an American novelist, short-story writer, and journalist, born in 1899."
]

embeddings = model.encode(
    input_texts,
    normalize_embeddings=True
)
```
Notes:

`original_question` refers to the user’s initial question.

`agent_query` refers to the intermediate query generated during the agent’s reasoning process.

Always include `[SEP]` to separate the two parts of the query.

We recommend setting `normalize_embeddings=True` for cosine similarity–based retrieval.