mlsanityData to 14 Oct 2026

LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

arXiv 2508.17692 ↗First posted 25 Aug 2025cs.AI cs.CLcited by 26

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

also in 1 more
Abstract (arXiv)

Recent advances in LLM-based agents highlight the importance of their reasoning frameworks, which guide the problem-solving process in diverse ways. This survey introduces a unified formal language to systematically categorize these frameworks at three compositional levels: single-agent, tool-based, and multi-agent methods. Following our taxonomy, we review key application scenarios across scientific discovery, healthcare, software engineering, society, economics, and general-purpose tasks. It also compares the distinct features and evaluation strategies of each category. Through our taxonomy and comparisons, our survey explores the designs and strengths of LLM-based agentic frameworks in different scenarios, reviewing the fast-paced development of complex agentic systems in the real world.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 78 of its 460 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

78 of 460 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution26 May
  2. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment22 Apr
  3. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems12 Apr
  4. 2024An LLM-Tool Compiler for Fused Parallel Function Calling7 May

Other references · 74

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  6. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  7. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  8. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  9. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 627
  10. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  11. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  12. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
38 more
  1. 2024Understanding the planning of LLM agents: A surveycited by 421
  2. 2025Small Language Models are the Future of Agentic AIcited by 270
  3. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  4. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  5. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
  6. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  7. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 170
  8. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  9. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 168
  10. 2025Progent: Securing AI Agents with Privilege Controlcited by 141
  11. 2025MemOS: A Memory OS for AI Systemcited by 138
  12. 2023GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigationcited by 137
  13. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  14. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  15. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  16. 2024The Prompt Report: A Systematic Survey of Prompt Engineering Techniquescited by 121
  17. 2025xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluationscited by 120
  18. 2024GUI Agents with Foundation Models: A Comprehensive Surveycited by 111
  19. 2025A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)cited by 101
  20. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 98
  21. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 86
  22. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directionscited by 77
  23. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 72
  24. 2024Large Language Model Agent in Financial Trading: A Surveycited by 60
  25. 2025TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Toolscited by 59
  26. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Userscited by 55
  27. 2025A Survey of Large Language Model Agents for Question Answeringcited by 48
  28. 2024LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptionscited by 47
  29. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 47
  30. 2024Y Social: an LLM-powered Social Media Digital Twincited by 44
  31. 2025Sleep-time Compute: Beyond Inference Scaling at Test-timecited by 43
  32. 2024FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Modelscited by 40
  33. 2025Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactionscited by 40
  34. 2024MetaOpenFOAM: an LLM-based multi-agent framework for CFDcited by 39
  35. 2022REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screeningcited by 38
  36. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisationcited by 35
  37. 2024ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agentscited by 35
  38. 2025Evaluating Agent-based Program Repair at Googlecited by 35

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 21.

26 papers.

Sort:

By area:

  1. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 47
  2. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 16
  3. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
  4. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 14
  5. 2026The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systemscited by 9
  6. 2025SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoningcited by 7
  7. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 7
  8. 2026E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoningcited by 6
  9. 2026TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoningcited by 5
  10. 2026FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environmentscited by 4
  11. 2026Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societiescited by 2
  12. 2026DeepTutor: Towards Agentic Personalized Tutoringcited by 2
14 more
  1. 2025SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphscited by 1
  2. 2025Mathematical Framing for Different Agent Strategiescited by 1
  3. 2026From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agentscited by 1
  4. 20261D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-Worldcited by 1
  5. 2026Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generationcited by 1
  6. 2026FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verificationcited by 1
  7. 2025Voice-Interactive Surgical Agent for Multimodal Patient Data Controlcited by 0
  8. 2026OUTLINEFORGE: Hierarchical Reinforcement Learning with Explicit States for Scientific Writingcited by 0
  9. 2026Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Researchcited by 0
  10. 2026Agentic Frameworks for Reasoning Tasks: An Empirical Studycited by 0
  11. 2026Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futurescited by 0
  12. 2026Agents in the Wild: Where Research Meets Deploymentcited by 0
  13. 2026APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuningcited by 0
  14. 2026Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  2. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
  3. 2026A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigms
  4. 2025Agentic Large Language Models, a survey
  5. 2023A Survey on Large Language Model based Autonomous Agents
  6. 2025Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
  7. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
  8. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review