Scikit-learn
Joblib
English
protocol-routing
llm-routing
multi-agent-systems
cost-aware-inference
protocol-selection
calibration
reasoning
reproducibility
arxiv:2608.14927
emnlp2026
Instructions to use AgentsSci/EMNLP_Cost-Aware-Protocol-Routing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use AgentsSci/EMNLP_Cost-Aware-Protocol-Routing with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("AgentsSci/EMNLP_Cost-Aware-Protocol-Routing", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Commit History
13 days ago
-
Update paper links and citation to published EMNLP Findings version
Verified signaturec408e07
-
Add pretty_name, quiet the version-warning wall in the example, and record the root widget copy's checksum
Verified signature294c751 -
Title it a model card and drop the research-artifact tag, now that a checkpoint ships
Verified signaturee0961d3 -
Publish the trained metadata-only router checkpoint with its fitted feature builders, verified label map, and a runnable example
Verified signature0181745 -
Remove library_name so HF stops advertising a joblib checkpoint that does not exist; add inference:false, dataset cross-link, arXiv tag
Verified signaturea7d0dd1 -
Release v1.0.0 accompanying the EMNLP 2026 camera-ready paper (arXiv:2608.14927)
Verified signature0d3ef4a
-
initial commit
Verified signatureaa4c112