paper-with-me

Papers

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools

2025-09-24 · Quy Minh Le, Minh Sao Khue Luu, Khanh-Tung Tran, Duc-Hai Nguyen, Hoang-Quoc-Viet Pham, Quan Le, Hoang Thanh Lam, Hoang D. Nguyen arxiv

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/.

📄 PDF Abstract BibTeX arXiv:2510.00023

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningKnowledge Distillation

Similar Papers 제목 키워드 기반

Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning

2025-11-18 · Mingyue Cheng, Shuo Yu, Daoyu Wang, Qingchuan Li 외 arxiv

Large language models (LLMs) have rapidly evolved from single-turn text generators into the foundation of increasingly capable agents. As these agents take on more complex reasoning, decision making, tool use, and long-h…

Reinforcement LearningDecision Making

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents

2025-09-26 · Yansong Ning, Rui Liu, Jun Wang, Kai Chen 외 arxiv

Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring an enjoyable user experience. Despite its benefits, existin…

Reinforcement Learning

MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use

2025-08-26 · Weikang Zhao, Xili Wang, Chengdi Ma, Lingbin Kong 외 arxiv

With the recent rapid advancement of Agentic Intelligence, agentic tool use in LLMs has become increasingly important. During multi-turn interactions between agents and users, the dynamic, uncertain, and stochastic natur…

Reinforcement Learning

Visual Agentic Reinforcement Fine-Tuning

2025-05-20 · Ziyu Liu, Yuhang Zang, Yushan Zou, Zijian Liang 외

A key trend in Large Reasoning Models (e.g., OpenAI's o3) is the native agentic ability to use external tools such as web browsers for searching and writing/executing code for image manipulation to think with images. In …

Image Manipulation

PyVision: Agentic Vision with Dynamic Tooling

2025-07-10 · Shitian Zhao, Haoquan Zhang, Shaoheng Lin, Ming Li 외

LLMs are increasingly deployed as agents, systems capable of planning, reasoning, and dynamically calling external tools. However, in visual reasoning, prior approaches largely remain limited by predefined workflows and …

Visual Reasoning