A router that decomposes uncertainty to flexibly route queries between cheap models and oracles while providing regret bounds and supporting abstention in classification tasks with multiple annotations.
Carrot: A cost aware rate optimal router
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Switchcraft routes agentic tool-calling queries to the lowest-cost model that preserves correctness, reaching 82.9% accuracy and 84% cost reduction on five benchmarks.
SWE-Router introduces trajectory-conditioned value-based routing for LLM agents on SWE tasks, with a Bayes-optimality theorem and empirical cost savings while retaining most strong-model performance.
LLM routers across 21 methods on 5 benchmarks converge to similar accuracy below oracle due to learning global performance trends rather than fine-grained query signals.
BRANE maps queries to optimal retrieval pipeline configurations using LLM-derived features and per-configuration correctness predictors, improving the cost-quality Pareto frontier on three benchmarks.
ECC calibrates semantic embeddings with model comparisons via Bradley-Terry profiles and mixture weights to cluster queries by latent LLM capabilities, claiming 17-18 point gains in ranking quality over baselines.
citing papers explorer
-
Flexible Routing via Uncertainty Decomposition
A router that decomposes uncertainty to flexibly route queries between cheap models and oracles while providing regret bounds and supporting abstention in classification tasks with multiple annotations.
-
Switchcraft: AI Model Router for Agentic Tool Calling
Switchcraft routes agentic tool-calling queries to the lowest-cost model that preserves correctness, reaching 82.9% accuracy and 84% cost reduction on five benchmarks.
-
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
SWE-Router introduces trajectory-conditioned value-based routing for LLM agents on SWE tasks, with a Bayes-optimality theorem and empirical cost savings while retaining most strong-model performance.
-
The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers
LLM routers across 21 methods on 5 benchmarks converge to similar accuracy below oracle due to learning global performance trends rather than fine-grained query signals.
-
Natural Language Query to Configuration for Retrieval Agents
BRANE maps queries to optimal retrieval pipeline configurations using LLM-derived features and per-configuration correctness predictors, improving the cost-quality Pareto frontier on three benchmarks.
-
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
ECC calibrates semantic embeddings with model comparisons via Bradley-Terry profiles and mixture weights to cluster queries by latent LLM capabilities, claiming 17-18 point gains in ranking quality over baselines.