The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration

TL;DR

This paper reviews the evolution of large language model agents from single-tool calls to complex multi-tool orchestration, highlighting recent advances, challenges, and future directions.

Contribution

It provides a comprehensive analysis of multi-tool LLM agents, unifying task formulations, and organizing research around key dimensions such as planning, safety, efficiency, and evaluation.

Findings

Multi-tool orchestration enables complex, long-horizon tasks for LLM agents.

Recent progress includes improved safety, efficiency, and capability in multi-tool systems.

Benchmarking and applications have expanded across software engineering and mobile systems.

Abstract

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model could select and execute a correct single tool call. As agent systems evolve, however, the central problem has shifted from isolated invocation to multi-tool orchestration over long trajectories with intermediate state, execution feedback, changing environments, and practical constraints such as safety, cost, and verifiability. We comprehensively review recent progress in multi-tool LLM agents and analyzes the state of the art in this rapidly developing area. First, we unify task formulations and distinguish single-call tool use from long-horizon orchestration. Then, we organize the literature around six core dimensions: inference-time planning and execution, training and trajectory construction, safety and control, efficiency under resource constraints, capability completeness in open environments, and benchmark design and evaluation. We further summarize representative applications in software engineering, enterprise workflows, graphical user interfaces, and mobile systems. Finally, we discuss major challenges and outline future directions for building reliable, scalable, and verifiable multi-tool agents.