mlsanityData to 7 Oct 2026

AFlow: Automating Agentic Workflow Generation

arXiv 2410.10762 ↗First posted 14 Oct 2024cs.AI cs.CL cs.LGcited by 395

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

also in 1 more
Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code is available at https://github.com/FoundationAgents/AFlow.

Key facts. Cited by 395 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 43 of its 57 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

43 of 57 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct

Other references · 42

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  9. 2021Program Synthesis with Large Language Modelscited by 3,509
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  11. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  12. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
30 more
  1. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  2. 2023Large Language Models as Optimizerscited by 830
  3. 2023Large Language Modelscited by 774
  4. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  5. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  6. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  7. 2024Automated Design of Agentic Systemscited by 360
  8. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 319
  9. 2024TextGrad: Automatic "Differentiation" via Textcited by 250
  10. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  11. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  12. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  13. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  14. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  15. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
  16. 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
  17. 2024Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineeringcited by 100
  18. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  19. 2024The Dawn of Natural Language to SQL: Are We Fully Ready?cited by 78
  20. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 76
  21. 2023Lemur: Harmonizing Natural Language and Code for Language Agentscited by 71
  22. 2024Archon: An Architecture Search Framework for Inference-Time Techniquescited by 59
  23. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  24. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Modelscited by 37
  25. 2024MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devicescited by 29
  26. 2024HAIChart: Human and AI Paired Visualization Systemcited by 26
  27. 2024Generative AI for Visualization: State of the Art and Future Directionscited by 23
  28. 2024MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agentscited by 21
  29. 2023LLM As DBAcited by 18
  30. 2023VerifAI: Verified Generative AIcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 123; 2026: 266.

395 papers.

Sort:

By area:

  1. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  4. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  5. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  6. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  7. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  8. 2025Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Stepcited by 130
  9. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 129
  10. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  11. 2026Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnessescited by 119
  12. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 114
38 more
  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  3. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 106
  4. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
  5. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  6. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systemscited by 86
  7. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  8. 2025ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learningcited by 78
  9. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 75
  10. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64
  11. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 56
  12. 2025KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflowscited by 56
  13. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  14. 2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 50
  15. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  16. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  17. 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systemscited by 45
  18. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 42
  19. 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworkscited by 38
  20. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoningcited by 37
  21. 2026HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundrycited by 37
  22. 2025Flow: Modularized Agentic Workflow Automationcited by 31
  23. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  24. 2025Enabling Agents to Communicate Entirely in Latent Spacecited by 31
  25. 2025KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakescited by 30
  26. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  27. 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestrationcited by 30
  28. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 28
  29. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  30. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 22
  31. 2025Position: Agent Should Invoke External Tools ONLY When Epistemically Necessarycited by 22
  32. 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoningcited by 22
  33. 2025Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Taskscited by 22
  34. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  35. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 22
  36. 2025A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworkscited by 21
  37. 2025Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarkingcited by 21
  38. 2026Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluationcited by 21

50 most cited of 395 All 395 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generation
  2. 2025Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow
  3. 2025A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators
  4. 2026AAFLOW: Scalable Patterns for Agentic AI Workflows
  5. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflows
  6. 2024Benchmarking Agentic Workflow Generation
  7. 2025AdaptFlow: Adaptive Workflow Optimization via Meta-Learning
  8. 2026Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows