Pith. sign in

REVIEW 10 cited by

CARROT: A Cost Aware Rate Optimal Router

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.03261 v2 pith:NFLFPT4J submitted 2025-02-05 stat.ML cs.LGcs.NImath.STstat.TH

CARROT: A Cost Aware Rate Optimal Router

classification stat.ML cs.LGcs.NImath.STstat.TH
keywords carrotcostroutingoptimalrouterawareintroducellms
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

With the rapid growth in the number of Large Language Models (LLMs), there has been a recent interest in LLM routing, or directing queries to the cheapest LLM that can deliver a suitable response. We conduct a minimax analysis of the routing problem, providing a lower bound and finding that a simple router that predicts both cost and accuracy for each question can be minimax optimal. Inspired by this, we introduce CARROT, a Cost AwaRe Rate Optimal rouTer that selects a model based on estimates of the models' cost and performance. Alongside CARROT, we also introduce the Smart Price-aware ROUTing (SPROUT) dataset to facilitate routing on a wide spectrum of queries with the latest state-of-the-art LLMs. Using SPROUT and prior benchmarks such as Routerbench and open-LLM-leaderboard-v2 we empirically validate CARROT's performance against several alternative routers.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

    cs.LG 2026-07 conditional novelty 7.0

    CABS-C and CABS-D use correlation graphs plus surrogate rewards to cut effective exploration in contextual bandits for LLM routing, with CABS-D giving best-of-both-worlds regret and better empirical accuracy-cost frontiers.

  2. Flexible Routing via Uncertainty Decomposition

    cs.LG 2026-05 unverdicted novelty 7.0

    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.

  3. Switchcraft: AI Model Router for Agentic Tool Calling

    cs.AI 2026-05 unverdicted novelty 7.0

    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.

  4. SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks

    cs.SE 2026-06 unverdicted novelty 6.0

    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.

  5. The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers

    cs.LG 2026-05 unverdicted novelty 6.0

    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.

  6. Natural Language Query to Configuration for Retrieval Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    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.

  7. Capturing LLM Capabilities via Evidence-Calibrated Query Clustering

    cs.AI 2026-05 unverdicted novelty 6.0

    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.

  8. Capturing LLM Capabilities via Evidence-Calibrated Query Clustering

    cs.AI 2026-05 unverdicted novelty 6.0

    ECC calibrates semantic embeddings with posterior model comparisons and Bradley-Terry capability profiles to create flexible, mixed-membership query clusters that improve LLM capability ranking.

  9. R2-Router: A New Paradigm for LLM Routing with Reasoning

    cs.CL 2026-02 conditional novelty 6.0

    R2-Router jointly selects the LLM and an output-token budget, modeling each model as a quality-cost curve rather than a fixed point, and reports 4-5x cost savings on its new R2-Bench.

  10. Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes

    cs.CL 2026-08 conditional novelty 4.0

    Statistical classifiers built on LLM activation norms and coordinates match or beat trained MLP heads on coarse intent routing and resist camouflage better, while MLPs win on fine-grained subfield distinctions.