paper-with-me

홈 › Papers

Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning

2025-10-08 · Wenxun Wu, Yuanyang Li, Guhan Chen, Linyue Wang, Hongyang Chen arxiv

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on benchmarks involving mathematical reasoning. However, language models relying solely on direct inference still struggle with tasks demanding up-to-date knowledge or computational tools such as calculators and code interpreters for complex arithmetic operations. To overcome these limitations, we propose Tool-Augmented Policy Optimization (TAPO), a novel reinforcement learning framework that systematically integrates multi-hop reasoning with adaptive tool-calling capabilities. Our approach employs a modified version of Dynamic Sampling Policy Optimization (DAPO), a recently developed RL paradigm, which we adapt specifically for tool invocation scenarios, enabling models to dynamically interleave complex reasoning with on-demand tool usage (including search APIs and Python interpreters). To support this research, we introduce two new datasets: TAPO-easy-60K and TAPO-hard-18K, specifically designed to train and evaluate both fact-based reasoning and mathematical calculation capabilities. Our experiments on Qwen2.5-3B and Qwen2.5-7B models demonstrate the effectiveness of our approach, with both models achieving state-of-the-art performance on tasks requiring external knowledge and mathematical computation among methods with comparable parameters. Notably, TAPO achieves more efficient tool utilization than baseline methods while preventing excessive calls caused by reward hacking. These results highlight the significant potential of combining advanced reasoning with tool usage to enhance model performance in knowledge-intensive and computationally demanding tasks.

📄 PDF Abstract BibTeX arXiv:2510.07038

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningMathematical Reasoning

Similar Papers 제목 키워드 기반

Synergizing RAG and Reasoning: A Systematic Review

2025-04-22 · Yunfan Gao, Yun Xiong, Yijie Zhong, Yuxi Bi 외

Recent breakthroughs in large language models (LLMs), particularly in reasoning capabilities, have propelled Retrieval-Augmented Generation (RAG) to unprecedented levels. By synergizing retrieval mechanisms with advanced…

RAGRetrievalRetrieval-augmented Generation

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

2026-03-03 · Siwei Zhang, Yun Xiong, Xi Chen, Zi'an Jia 외 arxiv

Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning.…

Reinforcement Learning

Adaptive Tool Generation with Models as Tools and Reinforcement Learning

2025-10-08 · Chenpeng Wang, Xiaojie Cheng, Chunye Wang, Linfeng Yang 외 arxiv

Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deployment. We propose MTR, a simulation-firs…

Reinforcement Learning

Experience Augmented Policy Optimization for LLM Reasoning

2026-06-29 · Jinda Lu, Kexin Huang, Junkang Wu, Shuo Yang 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing RLVR methods typically rely on on-policy optimizati…

Reinforcement Learning

Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees

2024-06-11 · Sijia Chen, Yibo Wang, Yi-Feng Wu, Qing-Guo Chen 외

Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to enhance their reasoning capabilities on complex tasks, thus taking on the role of intelligent agents interacting with the real wor…