Related papers: Reward-Based Online LLM Routing via NeuralUCB
The availability of a wide range of large language models (LLMs) embedded in various agentic systems has significantly increased the potential of model selection strategies to improve the cost-performance tradeoff. Existing strategies…
Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each problem to the smallest model likely to solve it, reducing compute…
Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e.g., edge) devices, tend to lag behind in terms of…
Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks, but their deployment comes at a high computational and financial cost. On the other hand, smaller language models…
A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as a large pretrained model or human expert), an approach known…
Researchers and practitioners operating on a limited budget face the cost-performance trade-off dilemma. The challenging decision often centers on whether to use a large LLM with better performance or a smaller one with reduced costs. This…
Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of…
Large language models (LLMs) deliver superior performance but require substantial computational resources and operate with relatively low efficiency, while smaller models can efficiently handle simpler tasks with fewer resources. LLM…
The rapid emergence of diverse large language models (LLMs) has spurred the development of LLM routers that assign user queries to the most suitable model. However, existing LLM routers typically perform a single-round, one-to-one mapping…
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…
This paper is about optimally controlling skill-based queueing systems such as data centers, cloud computing networks, and service systems. By means of a case study using a real-world data set, we investigate the practical implementation of…
Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption,…
As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost…
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…
Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging process due to the inefficiencies and inconsistencies inherent in conventional reward engineering methodologies. Recent…
We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We…
Large Language Model (LLM)-based systems, i.e. interconnected elements that include an LLM as a central component, such as conversational agents, are usually designed with monolithic, static architectures that rely on a single,…
The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…
Vehicle routing problems (VRPs) are central to combinatorial optimization with significant practical implications. Recent advancements in neural combinatorial optimization (NCO) have demonstrated promising results by leveraging neural…
With the rapid advancement of large language models (LLMs), the diversity of multi-LLM tasks and the variability in their pricing structures have become increasingly important, as costs can vary greatly between different LLMs. To tackle…