ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912816452075520 |
|---|---|
| author | Le, Quy Minh Luu, Minh Sao Khue Tran, Khanh-Tung Nguyen, Duc-Hai Pham, Hoang-Quoc-Viet Le, Quan Lam, Hoang Thanh Nguyen, Hoang D. |
| author_facet | Le, Quy Minh Luu, Minh Sao Khue Tran, Khanh-Tung Nguyen, Duc-Hai Pham, Hoang-Quoc-Viet Le, Quan Lam, Hoang Thanh Nguyen, Hoang D. |
| contents | Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for training tool use in agentic models with flexible reinforcement learning, thereby easing the barriers for researchers and practitioners to adapt LLM-based agents to specific domains. It supports a wide range of training strategies, including reinforcement learning algorithms such as GRPO and DPO, as well as supervised learning. ToolBrain enables custom reward callables directly on an agent's execution traces or simply utilizes an automated LLM-as-a-judge system for reward generation. It is packed with useful capabilities, including knowledge distillation from large to small models, automatic task generation from tool descriptions, seamless tool retrieval, efficient fine-tuning pipelines with QLoRA through Unsloth, and quantized inference via bitsandbytes. We demonstrate ToolBrain through an Email Search Agent case study, showing measurable improvements in tool-use skills under a realistic workflow, while keeping the codebase simple and extensible. Our framework is publicly available at https://toolbrain.org/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00023 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools Le, Quy Minh Luu, Minh Sao Khue Tran, Khanh-Tung Nguyen, Duc-Hai Pham, Hoang-Quoc-Viet Le, Quan Lam, Hoang Thanh Nguyen, Hoang D. Artificial Intelligence Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for training tool use in agentic models with flexible reinforcement learning, thereby easing the barriers for researchers and practitioners to adapt LLM-based agents to specific domains. It supports a wide range of training strategies, including reinforcement learning algorithms such as GRPO and DPO, as well as supervised learning. ToolBrain enables custom reward callables directly on an agent's execution traces or simply utilizes an automated LLM-as-a-judge system for reward generation. It is packed with useful capabilities, including knowledge distillation from large to small models, automatic task generation from tool descriptions, seamless tool retrieval, efficient fine-tuning pipelines with QLoRA through Unsloth, and quantized inference via bitsandbytes. We demonstrate ToolBrain through an Email Search Agent case study, showing measurable improvements in tool-use skills under a realistic workflow, while keeping the codebase simple and extensible. Our framework is publicly available at https://toolbrain.org/. |
| title | ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.00023 |