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_evaluation.csv from AgentsSci/EMNLP_Cost-Aware-Protocol-Routing: direct link, hf CLI and curl.
- Browser
- Download file 900 Bytes
-
https://huggingface.co/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/resolve/main/artifacts/heldout_router_evaluation.csv
- Command line
-
hf download hf://AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/artifacts/heldout_router_evaluation.csv
-
curl -L -o heldout_router_evaluation.csv https://huggingface.co/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing/resolve/main/artifacts/heldout_router_evaluation.csv
900 Bytes
| solver,setting,n,baseline_solve,router_solve,router_ci,oracle_solve,oracle_gap,oracle_label_macro_f1,route_baseline,route_single,route_per,route_broadcast,route_none | |
| Gemma-4-31B-it,OmniMath,628,0.6943,0.7659,"[0.7309,0.7978]",0.9570,0.1911,0.2676,0.4984,0.2404,0.1274,0.0557,0.0780 | |
| gpt-oss-120b,OmniMath,628,0.5685,0.6672,"[0.6306,0.7038]",0.9268,0.2596,0.2835,0.4570,0.1990,0.1561,0.0717,0.1162 | |
| Gemma-4-31B-it,LAB-Bench strict,112,0.4464,0.7054,"[0.6161,0.7857]",0.9107,0.2054,0.4949,0.5714,0.0357,0.0625,0.2679,0.0625 | |
| gpt-oss-120b,LAB-Bench strict,112,0.1875,0.5625,"[0.4732,0.6607]",0.7679,0.2054,0.4986,0.1429,0.1518,0.2946,0.2500,0.1607 | |
| Gemma-4-31B-it,LAB-Bench text-no-tool,232,0.4181,0.7759,"[0.7198,0.8276]",0.9612,0.1853,0.4854,0.3664,0.4310,0.0431,0.1379,0.0216 | |
| gpt-oss-120b,LAB-Bench text-no-tool,232,0.3060,0.5733,"[0.5086,0.6379]",0.8621,0.2888,0.4558,0.3491,0.2974,0.0302,0.1638,0.1595 | |