mlsanityData to 7 Oct 2026

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

arXiv 2502.04644 ↗First posted 7 Feb 2025cs.AI cs.CLcited by 106

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

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

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 15 of its 23 references that are in the map. First posted on arXiv 7 Feb 2025.

Builds on

15 of 23 references.

References · 15

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  4. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  6. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  7. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 379
  8. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 250
  9. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
  10. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 140
  11. 2024LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoningcited by 90
  12. 2024O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?cited by 90
3 more
  1. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 89
  2. 2023Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizationscited by 59
  3. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 43; 2026: 63.

106 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning datasetcited by 165
  3. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 129
  4. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  5. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 114
  6. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 107
  7. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  8. 2025History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRLcited by 35
  9. 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoningcited by 34
  10. 2026When Single-Agent with Skills Replace Multi-Agent Systems and When They Failcited by 34
  11. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 31
  12. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
38 more
  1. 2025TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Roboticscited by 27
  2. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 25
  3. 2025DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Taskscited by 24
  4. 2025Code Researcher: Deep Research Agent for Large Systems Code and Commit Historycited by 19
  5. 2025PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approachcited by 19
  6. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 18
  7. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 18
  8. 2025WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollbackcited by 14
  9. 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGymcited by 14
  10. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
  11. 2025Git Context Controller: Manage the Context of LLM-based Agents like Gitcited by 13
  12. 2025RollArt: Disaggregated Multi-Task Agentic RL Training at Scalecited by 11
  13. 2025RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMscited by 10
  14. 2025MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibilitycited by 9
  15. 2025Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLMcited by 8
  16. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  17. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 8
  18. 2026The Interplay of Harness Design and Post-Training in LLM Agentscited by 8
  19. 2025LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Servicescited by 7
  20. 2026One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligencecited by 7
  21. 2026Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modelingcited by 7
  22. 2025What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extractioncited by 6
  23. 2025Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safetycited by 6
  24. 2026RMA: an Agentic System for Research-Level Mathematical Problemscited by 6
  25. 2026Uncertainty-Aware Clarification in LLM Agents with Information Gaincited by 6
  26. 2026Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix Itcited by 6
  27. 2025NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoningcited by 5
  28. 2025PRInTS: Reward Modeling for Long-Horizon Information Seekingcited by 5
  29. 2025HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimizationcited by 5
  30. 2026RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generationcited by 5
  31. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  32. 2025CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoningcited by 4
  33. 2025Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Trainingcited by 4
  34. 2026From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscapecited by 4
  35. 2026HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agentscited by 4
  36. 2025Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learningcited by 3
  37. 2025PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Readingcited by 3
  38. 2026MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agentscited by 3

50 most cited of 106 All 106 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
  2. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
  3. 2024Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
  4. 2026A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigms
  5. 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  6. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  7. 2024AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents
  8. 2025Exploring the Necessity of Reasoning in LLM-based Agent Scenarios