tencent/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 for recall.

• 📄 Paper: Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing
• 💻 Code: Tencent/R3-Skill

Usage

from sentence_transformers import CrossEncoder

model = CrossEncoder("tencent/R3-rerank-0.6b", trust_remote_code=True)
scores = model.predict([("I need to compose music", "music-composer | Composes original music | ...")])

Citation

@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},
}