Agentic Reasoning：通过智能体工具增强LLM推理的简化框架
Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
AI总结：
本文提出Agentic Reasoning框架，通过集成Mind-Map智能体和Web-Search智能体等外部工具，增强大型语言模型的模型的推理能力，并在DeepSeek-R1上达到SOTA水平。
摘要：
我们引入了Agentic Reasoning，这是一个通过集成外部工具使用智能体来增强大型语言模型（LLM）推理的框架。Agentic Reasoning动态利用网络搜索、代码执行和结构化记忆来解决需要深入研究的复杂问题。我们框架的一项关键创新是Mind-Map智能体，它构建一个结构化知识图谱来存储推理上下文并跟踪逻辑关系，从而确保在大量工具使用时的长推理链中保持连贯性。此外，我们对Web-Search智能体进行了全面探索，形成了一种超越所有先前方法的高效搜索机制。当部署在DeepSeek-R1上时，本方法在公开模型中实现了新的最先进水平（SOTA）水平，并提供了与OpenAI Deep Research相当的性能，后者是该领域领先的专有模型。广泛的消融研究验证了智能体工具的最佳选择，并证实了Mind-Map和Web-Search智能体在增强LLM推理方面的有效性。。代码地址：https://github.com/theworldofagents/Agentic-Reasoning
英文摘要：
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address complex problems requiring deep research. A key innovation in our framework is the Mind-Map agent, which constructs a structured knowledge graph to store reasoning context and track logical relationships, ensuring coherence in long reasoning chains with extensive tool usage. Additionally, we conduct a comprehensive exploration of the Web-Search agent, leading to a highly effective search mechanism that surpasses all prior approaches. When deployed on DeepSeek-R1, our method achieves a new state-of-the-art (SOTA) among public models and delivers performance comparable to OpenAI Deep Research, the leading proprietary model in this domain. Extensive ablation studies validate the optimal selection of agentic tools and confirm the effectiveness of our Mind-Map and Web-Search agents in enhancing LLM reasoning. The code is at: https://github.com/theworldofagents/Agentic-Reasoning
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
