---
title: R3-rerank-0.6b
canonical_url: "https://www.modelscope.ai/models/Tencent-Hunyuan/R3-rerank-0.6b"
md_url: "https://www.modelscope.ai/models/Tencent-Hunyuan/R3-rerank-0.6b.md"
repository: Tencent-Hunyuan/R3-rerank-0.6b
last_updated: 2026-07-09
license: apache-2.0
pipeline_tag: text-ranking
tasks:
  - text-ranking
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Qwen/Qwen3-Reranker-0.6B
base_model_relation: finetune
parameters: 595.8M
tensor_type:
  - F32
library_name:
  - sentence-transformers
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 131
stars: 0
tags:
  - sentence-transformers
  - cross-encoder
  - agent-skill-retrieval
---

# R3-rerank-0.6b

> R3-rerank-0.6b - An open-source model by Tencent-Hunyuan on ModelScope. The latest agent skill reranking model at the 0.6B scale. R3-Reranker is the cross-encoder (rerank) stage of R3-Skill's two-stage retriever for query-conditional agent skill retrieval.…

Tencent-Hunyuan/R3-rerank-0.6b is a 595.8M-parameter text-ranking model on ModelScope. licensed under apache-2.0. derived from Qwen/Qwen3-Reranker-0.6B.

- **Repository**: Tencent-Hunyuan/R3-rerank-0.6b
- **License**: apache-2.0
- **Tasks**: text-ranking
- **Parameters**: 595.8M
- **Base model**: Qwen/Qwen3-Reranker-0.6B
- **Tags**: sentence-transformers, cross-encoder, agent-skill-retrieval
- **Downloads**: 131
- **Stars**: 0
- **Last updated**: 2026-07-09

Source: https://www.modelscope.ai/models/Tencent-Hunyuan/R3-rerank-0.6b

---

# R3-Rerank-0.6B

The latest agent skill reranking model at the 0.6B scale. **R3-Reranker** is the cross-encoder
(rerank) stage of R3-Skill's two-stage retriever for query-conditional agent skill retrieval. It
scores each (query, skill) pair jointly, paired with
[R3-Embedding-0.6B](https://huggingface.co/tencent/R3-embedding-0.6b) for recall.

- 📄 Paper: [Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing](https://arxiv.org/abs/2606.03565)
- 💻 Code: [Tencent/R3-Skill](https://github.com/Tencent/R3-Skill)

## Usage

```python
from sentence_transformers import CrossEncoder

model = CrossEncoder("tencent/R3-rerank-0.6b")
query = "I need to compose music"
skills = [  # The format is "name | description | skill_md"
    "music-composer | Composes original music | Creates music for various media formats ...",
    "music-lyricist | Writes lyrics for songs | Creates lyrics for various music genres ...",
    "music-editor | Edits and mixes music tracks | Provides audio editing and mixing services ...",
]
pairs = [(query, skill) for skill in skills]
scores = model.predict(pairs)
print(scores)
# [ 0.34937477 -1.7738094  -1.6604462 ]
```

## Citation

```bibtex
@inproceedings{r3skill2026,
  title  = {Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing},
  author = {Wang, Zifei and Wen, Wei and Ji, Qiang and Qiao, Ruizhi and Sun, Xing},
  year   = {2026},
  url    = {https://arxiv.org/abs/2606.03565},
}
```