BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:SQI556FQrecord.jsonopen to challenge →
read the original abstract
Large language models (LLMs) are powerful tools but are often expensive to deploy at scale. LLM query routing mitigates this by dynamically assigning queries to models of varying cost and quality to obtain a desired trade-off. Prior query routing approaches generate only one response from the selected model and a single response from a small (inexpensive) model was often not good enough to beat a response from a large (expensive) model due to which they end up overusing the large model and missing out on potential cost savings. However, it is well known that for small models, generating multiple responses and selecting the best can enhance quality while remaining cheaper than a single large-model response. We leverage this idea to propose BEST-Route, a novel routing framework that chooses a model and the number of responses to sample from it based on query difficulty and the quality thresholds. Experiments on real-world datasets demonstrate that our method reduces costs by up to 60% with less than 1% performance drop.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
LQM-ContextRoute routes LLM tool calls via latency-quality matching in a contextual bandit, improving F1 by 2.18 pp, accuracy by up to 18 pp, and NDCG by 2.91-3.22 pp over SW-UCB on web-search, StrategyQA, and retriev...
-
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.
-
Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
LQM-ContextRoute routes tool calls by expected quality per service cycle using contextual bandits and LLM-as-judge feedback, yielding +2.18 pp F1, up to +18 pp accuracy, and +2.91-3.22 pp NDCG gains over SW-UCB on web...
-
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
-
Learning Agent Routing From Early Experience
BoundaryRouter routes queries to LLM or agent using early experience memory from a seed set, cutting inference time 60.6% versus always using agents and raising performance 28.6% versus always using direct LLM inference.
-
RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving
Joint resource allocation and routing for multi-model LLM serving can produce up to 87% variation in achievable output quality across setups on the same GPU cluster.
-
EntroRouter: Learning Efficient Model Routing via Entropy Regulation
EntroRouter applies entropy regulation in a single-round routing framework to decouple reasoning from routing, retaining 98.3% of top expert accuracy at 48.25% lower compute cost.
-
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gai...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.