Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915737965166592 |
|---|---|
| author | Gao, Xingjie Huang, Pengcheng Liu, Zhenghao Yan, Yukun Wang, Shuo Chen, Zulong Qian, Chen Yu, Ge Gu, Yu |
| author_facet | Gao, Xingjie Huang, Pengcheng Liu, Zhenghao Yan, Yukun Wang, Shuo Chen, Zulong Qian, Chen Yu, Ge Gu, Yu |
| contents | Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving tools. Existing trajectory-centric paradigms primarily rely on memorizing static solution paths during training, which limits the ability of LLMs to generalize tool usage to newly introduced or previously unseen tools. In this paper, we propose ToolMaster, a framework that shifts tool use from imitating golden tool-calling trajectories to actively learning tool usage through interaction with the environment. To optimize LLMs for tool planning and invocation, ToolMaster adopts a trial-and-execution paradigm, which trains LLMs to first imitate teacher-generated trajectories containing explicit tool trials and self-correction, followed by reinforcement learning to coordinate the trial and execution phases jointly. This process enables agents to autonomously explore correct tool usage by actively interacting with environments and forming experiential knowledge that benefits tool execution. Experimental results demonstrate that ToolMaster significantly outperforms existing baselines in terms of generalization and robustness across unseen or unfamiliar tools. All code and data are available at https://github.com/NEUIR/ToolMaster. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12762 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction Gao, Xingjie Huang, Pengcheng Liu, Zhenghao Yan, Yukun Wang, Shuo Chen, Zulong Qian, Chen Yu, Ge Gu, Yu Software Engineering Artificial Intelligence Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving tools. Existing trajectory-centric paradigms primarily rely on memorizing static solution paths during training, which limits the ability of LLMs to generalize tool usage to newly introduced or previously unseen tools. In this paper, we propose ToolMaster, a framework that shifts tool use from imitating golden tool-calling trajectories to actively learning tool usage through interaction with the environment. To optimize LLMs for tool planning and invocation, ToolMaster adopts a trial-and-execution paradigm, which trains LLMs to first imitate teacher-generated trajectories containing explicit tool trials and self-correction, followed by reinforcement learning to coordinate the trial and execution phases jointly. This process enables agents to autonomously explore correct tool usage by actively interacting with environments and forming experiential knowledge that benefits tool execution. Experimental results demonstrate that ToolMaster significantly outperforms existing baselines in terms of generalization and robustness across unseen or unfamiliar tools. All code and data are available at https://github.com/NEUIR/ToolMaster. |
| title | Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2601.12762 |