Scikit-learn
Joblib
English
protocol-routing
llm-routing
multi-agent-systems
cost-aware-inference
protocol-selection
calibration
reasoning
reproducibility
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
Publish the trained metadata-only router checkpoint with its fitted feature builders, verified label map, and a runnable example
0181745 verified Download router_metadata_only/metrics.csv from AgentsSci/EMNLP_Cost-Aware-Protocol-Routing: direct link, hf CLI and curl.
- Browser
- Download file 376 Bytes
-
https://huggingface.co/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/resolve/main/router_metadata_only/metrics.csv
- Command line
-
hf download hf://AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/router_metadata_only/metrics.csv
-
curl -L -o metrics.csv https://huggingface.co/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/resolve/main/router_metadata_only/metrics.csv
376 Bytes
| model_name,split,n_examples,accuracy,macro_f1,realized_solve_rate,avg_total_tokens,avg_model_calls,avg_wall_time_seconds,avg_excess_cost_tokens_vs_oracle,missed_success_rate | |
| metadata_only_logreg,dev,416,0.569712,0.267917,0.627404,51731.351,15.312,89.666,19073.486,0.323834 | |
| metadata_only_logreg,test,423,0.572104,0.229503,0.607565,44298.277,14.069,84.125,20451.118,0.342711 | |