Related papers: Switchcraft: AI Model Router for Agentic Tool Call…

We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize this setting as sequential decision making in context space…

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 model (LLM) query routers are critical to modern AI platforms as they seek to improve efficiency by assigning inference queries to accurate, yet low-cost models. Parametric routers typically use trained neural networks for…

Transfer learning can be seen as a data- and compute-efficient alternative to training models from scratch. The emergence of rich model repositories, such as TensorFlow Hub, enables practitioners and researchers to unleash the potential of…

Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with…

Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled today by fixed templates or hand-tuned heuristics that apply the same…

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…

Current research on tool learning primarily focuses on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness, a crucial factor in human problem-solving. In this paper, we address the selection…

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…

AI products often route requests through version aliases, service tiers, tool choices, regional endpoints, fallback rules, or safety handling before responding. These routing steps are documented product surfaces in several widely used AI…

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and…

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…

As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable. While model routing is effective for single-turn queries,…

Trip planning for intelligent vehicles increasingly requires selecting optimal routes rather than merely producing feasible itineraries, as interacting factors such as travel time, energy consumption, and traffic conditions directly affect…

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based…

LLM routing aims to achieve a favorable quality--cost trade-off by dynamically assigning easy queries to smaller models and harder queries to stronger ones. However, across both unimodal and multimodal settings, we uncover a pervasive yet…

Large Language Model (LLM) agents have emerged as powerful tools for automating complex tasks by leveraging the reasoning and decision-making abilities of LLMs. However, a major bottleneck in current agent frameworks lies in the high…

Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files, run code, call APIs, etc. Further, modern reasoning-based…