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
Download artifacts/heldout_router_paired_differences.csv from AgentsSci/EMNLP_Cost-Aware-Protocol-Routing: direct link, hf CLI and curl.
- Browser
- Download file 571 Bytes
-
https://huggingface.co/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/resolve/main/artifacts/heldout_router_paired_differences.csv
- Command line
-
hf download hf://AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/artifacts/heldout_router_paired_differences.csv
-
curl -L -o heldout_router_paired_differences.csv https://huggingface.co/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/resolve/main/artifacts/heldout_router_paired_differences.csv
571 Bytes
| solver,setting,n,router_minus_tier_majority_points,router_minus_tier_majority_ci_points,router_minus_baseline_points,router_minus_baseline_ci_points | |
| Gemma-4-31B-it,OmniMath,628,7.2,"[4.0,10.2]",7.2,"[4.0,10.2]" | |
| gpt-oss-120b,OmniMath,628,3.3,"[0.0,6.5]",9.9,"[6.5,13.2]" | |
| Gemma-4-31B-it,LAB-Bench strict,112,25.0,"[16.1,33.9]",25.9,"[17.9,34.0]" | |
| gpt-oss-120b,LAB-Bench strict,112,-8.0,"[-17.0,1.8]",37.5,"[28.6,46.4]" | |
| Gemma-4-31B-it,LAB-Bench text-no-tool,232,10.8,"[5.2,16.4]",35.8,"[29.7,42.2]" | |
| gpt-oss-120b,LAB-Bench text-no-tool,232,0.9,"[-5.2,6.5]",26.7,"[20.7,32.8]" | |