paper-with-me

홈 › Papers

Advancing SLM Tool-Use Capability using Reinforcement Learning

2025-09-03 · Dhruvi Paprunia, Vansh Kharidia, Pankti Doshi arxiv

In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use tools effectively has become a defining feature of Large Language Models (LLMs), allowing them to access external data and internal resources. As AI agents grow more sophisticated, tool-use capabilities have become indispensable. While LLMs have made significant progress in this area, Small Language Models (SLMs) still face challenges in accurately integrating tool use, especially in resource-constrained settings. This study investigates how Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), can enhance the tool-use accuracy of SLMs. By designing a well-defined reward system that reinforces structured JSON output, correct tool selection, and precise parameter usage, we demonstrate that GRPO enables SLMs to achieve significant improvements in tool-use capabilities (function calling/JSON output). Our approach provides a computationally efficient training method that enhances SLMs practical deployment in real-world AI applications.

📄 PDF Abstract BibTeX arXiv:2509.04518

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs

2026-02-03 · Zhiyuan Yao, Yi-Kai Zhang, Yuxin Chen, Yueqing Sun 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform roll…

Reinforcement Learning

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL

2026-01-07 · Yi Yao, He Zhu, Piaohong Wang, Jincheng Ren 외 arxiv

The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for …

Reinforcement Learning

Integrating Distributed Architectures in Highly Modular RL Libraries

2020-07-06 · Albert Bou, Sebastian Dittert, Gianni de Fabritiis

Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popu…

reinforcement-learningReinforcement Learning (RL)

Visual Reasoning through Tool-supervised Reinforcement Learning

2026-04-21 · Qihua Dong, Gozde Sahin, Pei Wang, Zhaowei Cai 외 arxiv

In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we propose a novel Tool-supervised Reinforcem…

Reinforcement LearningVisual Reasoning

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

2026-04-20 · Guanting Dong, Junting Lu, Junjie Huang, Wanjun Zhong 외 arxiv

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interf…

Reinforcement Learning