Lookahead Routing for Large Language Models

TL;DR

Lookahead routing predicts potential model outputs to make more informed decisions in large language model systems, significantly improving efficiency and accuracy across diverse tasks.

Contribution

The paper introduces Lookahead, a novel routing framework that anticipates model outputs to enhance routing decisions in multi-model LLM systems.

Findings

Outperforms existing routing baselines by 7.7% on average.

Effective across instruction, reasoning, and code generation tasks.

Demonstrates the benefit of predicting latent representations for routing.

Abstract

Large language model (LLM) routers improve the efficiency of multi-model systems by directing each query to the most appropriate model while leveraging the diverse strengths of heterogeneous LLMs. Most existing approaches frame routing as a classification problem based solely on the input query. While this reduces overhead by avoiding inference across all models, it overlooks valuable information that could be gleaned from potential outputs and fails to capture implicit intent or contextual nuances that often emerge only during response generation. These limitations can result in suboptimal routing decisions, particularly for complex or ambiguous queries that require deeper semantic understanding. To address this challenge, we propose Lookahead, a routing framework that "foresees" potential model outputs by predicting their latent representations and uses these predictions to guide model selection, thus enabling more informed routing without full inference. Within this framework, we implement two approaches based on causal and masked language models. Empirical evaluations across seven public benchmarks - spanning instruction following, mathematical reasoning, and code generation - show that Lookahead consistently outperforms existing routing baselines, achieving an average performance gain of 7.7% over the state-of-the-art. Our code is available at https://github.com/huangcb01/lookahead-routing.