SkillRet-Embedding-8B

This is a sentence-transformers model fine-tuned for AI agent skill retrieval. Given a natural-language user request, the model retrieves relevant agent skills from a large skill library.

The model is fine-tuned from Qwen/Qwen3-Embedding-8B on the SkillRet benchmark training split using contrastive learning (MultipleNegativesRankingLoss).

📄 Technical report: SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents (arXiv:2605.05726)

Usage

Sentence Transformers

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("ThakiCloud/SkillRet-Embedding-8B", trust_remote_code=True)

query_prompt = "Instruct: Given a skill search query, retrieve relevant skills that match the query\nQuery: "

queries = [
    query_prompt + "Help me set up a CI/CD pipeline for my Python project"
]
skills = [
    "ci-cd-setup | Configure continuous integration and deployment pipelines ...",
    "python-debugging | Debug Python applications using pdb and logging ...",
]

q_emb = model.encode(queries, normalize_embeddings=True)
s_emb = model.encode(skills, normalize_embeddings=True)

similarities = q_emb @ s_emb.T
print(similarities)

Training Details

• Base model: Qwen3-Embedding-8B (8B parameters)
• Training data: SkillRet benchmark training split (127,190 query–skill pairs from 63,259 queries and 10,123 skills)
• Loss: MultipleNegativesRankingLoss (InfoNCE) with cross-GPU negative sharing
• Hardware: 4× NVIDIA B200 GPUs (DDP)
• Effective batch size: 80 (20 per device × 4 GPUs)
• Max sequence length: 8,192 tokens
• Learning rate: 2e-5
• Epochs: 1
• Precision: BF16

Evaluation Results

Evaluated on the SkillRet benchmark test split (4,997 queries, 6,660 skills).

Metric	@5	@10	@15
NDCG	0.8123	0.8345	0.8418
Recall	0.8558	0.9123	0.9355
Completeness	0.7562	0.8463	0.8841

For comparison with the 0.6B variant, see ThakiCloud/SkillRet-Embedding-0.6B.

Intended Use

This model is designed for retrieving agent skills given natural-language user requests. It is part of the SkillRet benchmark submission for evaluating skill retrieval systems for AI agents.

Limitations

• Optimized for English-language queries and agent skills.
• Performance may vary on domains outside the SkillRet benchmark distribution.
• The model retrieves skills but does not execute them.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 5.4.1
• Transformers: 5.5.4
• PyTorch: 2.7.1+cu128

Citation

If you use this model or the SkillRet benchmark, please cite:

@article{cho2026skillret,
  title   = {SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents},
  author  = {Cho, Hongcheol and Kang, Ryangkyung and Kim, Youngeun},
  journal = {arXiv preprint arXiv:2605.05726},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.05726}
}

Paper: https://arxiv.org/abs/2605.05726