All research
Research · Better Router lineage
Adaptive routing under quality, cost, latency, and reliability.
A reproducible study asking whether learned policies can outperform a deterministic Better Router–style baseline when choosing among heterogeneous LLM arms.
Open research repositoryStudy scope
Better Router Adaptive compares four routing strategies on a canonical RouterBench-derived dataset: a deterministic rules proxy, an XGBoost utility predictor, a LinUCB contextual bandit, and an offline oracle upper bound.
Methods and protocol
Utility function
Primary score balances quality, normalized cost, normalized latency, and error rate: U = 0.65Q − 0.20Cn − 0.10Ln − 0.05E.
Data contract
Canonical rows keyed by prompt_id and model_id with controlled task groups, provenance fields, and RouterBench SHA-256 verification before any pickle conversion.
Evaluation discipline
Splits by prompt_id—never by row leakage—with regret, confidence intervals, and artifacts generated from runs rather than hand-written results.
Publications and repositories
Publications and repositories
Evidence and status
Research · Better Router lineage
- No empirical conclusions on XGBoost or LinUCB are claimed yet.
- README figures use a synthetic fixture labeled as demonstration—not final experimental evidence.
- Study remains isolated from production Better Router until shadow evaluation and privacy review.