AICLFeb 7, 2025

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

arXiv:2502.04644v2107 citationsh-index: 9Has CodeACL
AI Analysis

This addresses the challenge of complex reasoning tasks requiring deep research for users of LLMs, representing a strong incremental improvement with novel agent components.

The paper tackles the problem of enhancing large language model reasoning by integrating external tool-using agents, achieving state-of-the-art performance comparable to leading proprietary models like OpenAI Deep Research.

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

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes