The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915908010639360 |
|---|---|
| author | Xu, Haoyuan Li, Chang Ma, Xinyan Ou, Xianhao Zhang, Zihan He, Tao Liu, Xiangyu Wang, Zixiang Liang, Jiafeng Chu, Zheng Liu, Runxuan Mu, Rongchuan Tu, Dandan Liu, Ming Qin, Bing |
| author_facet | Xu, Haoyuan Li, Chang Ma, Xinyan Ou, Xianhao Zhang, Zihan He, Tao Liu, Xiangyu Wang, Zixiang Liang, Jiafeng Chu, Zheng Liu, Runxuan Mu, Rongchuan Tu, Dandan Liu, Ming Qin, Bing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22862 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration Xu, Haoyuan Li, Chang Ma, Xinyan Ou, Xianhao Zhang, Zihan He, Tao Liu, Xiangyu Wang, Zixiang Liang, Jiafeng Chu, Zheng Liu, Runxuan Mu, Rongchuan Tu, Dandan Liu, Ming Qin, Bing Software Engineering Computation and Language 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. |
| title | The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration |
| topic | Software Engineering Computation and Language |
| url | https://arxiv.org/abs/2603.22862 |