The latest agent skill retrieval model at the 0.6B scale.
R3-Embedding
is the bi-encoder
(recall) stage of R3-Skill's two-stage retriever for query-conditional agent skill retrieval. It
embeds a query and every skill independently and ranks candidates by cosine similarity, paired
with
R3-Rerank-0.6B
for reranking.
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("tencent/R3-embedding-0.6b", trust_remote_code=True)
qv = model.encode(
["Instruct: Given a user request, retrieve the agent skill that solves it.\nQuery: I need to compose music"],
normalize_embeddings=True,
)
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},
}
Runs of tencent R3-embedding-0.6b on huggingface.co
1.4K
Total runs
0
24-hour runs
-45
3-day runs
-142
7-day runs
1.2K
30-day runs
More Information About R3-embedding-0.6b huggingface.co Model
R3-embedding-0.6b huggingface.co is an AI model on huggingface.co that provides R3-embedding-0.6b's model effect (), which can be used instantly with this tencent R3-embedding-0.6b model. huggingface.co supports a free trial of the R3-embedding-0.6b model, and also provides paid use of the R3-embedding-0.6b. Support call R3-embedding-0.6b model through api, including Node.js, Python, http.
R3-embedding-0.6b huggingface.co is an online trial and call api platform, which integrates R3-embedding-0.6b's modeling effects, including api services, and provides a free online trial of R3-embedding-0.6b, you can try R3-embedding-0.6b online for free by clicking the link below.
tencent R3-embedding-0.6b online free url in huggingface.co:
R3-embedding-0.6b is an open source model from GitHub that offers a free installation service, and any user can find R3-embedding-0.6b on GitHub to install. At the same time, huggingface.co provides the effect of R3-embedding-0.6b install, users can directly use R3-embedding-0.6b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.