mlsanityData to 7 Oct 2026

Flow: Modularized Agentic Workflow Automation

arXiv 2501.07834 ↗First posted 14 Jan 2025cs.AI cs.LG cs.MAcited by 31

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An effective workflow adjustment is crucial in real-world scenarios, as the initial plan must adjust to unforeseen challenges and changing conditions in real time to ensure the efficient execution of complex tasks. In this paper, we define workflows as an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by LLM agents through dynamic subtask allocation adjustment based on historical performance and previous AOVs. To further enhance framework performance, we emphasize modularity in workflow design based on evaluating parallelism and dependency complexity. With this design, our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance. Empirical results across various practical tasks demonstrate significant improvements in the efficiency of multi-agent frameworks through dynamic workflow refinement and modularization. The code is available at: https://github.com/tmllab/2025_ICLR_FLOW.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 36 references that are in the map. First posted on arXiv 14 Jan 2025.

Builds on

19 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024AFlow: Automating Agentic Workflow Generation14 Oct
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 17

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  6. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  7. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  8. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  9. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  10. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  11. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  12. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
5 more
  1. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  2. 2024Language Agents as Optimizable Graphscited by 81
  3. 2024TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generationcited by 50
  4. 2023DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacycited by 34
  5. 2023Rational Decision-Making Agent with Internalized Utility Judgmentcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 14.

31 papers.

Sort:

By area:

  1. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 22
  2. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 22
  3. 2025RobustFlow: Towards Robust Agentic Workflow Generationcited by 19
  4. 2025Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platformscited by 18
  5. 2025Position: The Real Barrier to LLM Agent Usability is Agentic ROIcited by 12
  6. 2025Sherlock: Reliable and Efficient Agentic Workflow Executioncited by 10
  7. 2025Aime: Towards Fully-Autonomous Multi-Agent Frameworkcited by 9
  8. 2025Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safetycited by 7
  9. 2026Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Taskscited by 7
  10. 2025PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analysescited by 6
  11. 2026InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seekingcited by 5
  12. 2026On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Lengthcited by 5
19 more
  1. 2025Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflowscited by 3
  2. 2025ALLOY: Generating Reusable Agent Workflows from User Demonstrationcited by 3
  3. 2026Can Agents Secure Hardware? Evaluating Agentic LLM-Driven Obfuscation for IP Protectioncited by 3
  4. 2025SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detectioncited by 2
  5. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  6. 2026SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learningcited by 2
  7. 2025Risk-Sensitive Agent Compositionscited by 1
  8. 2025Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectivescited by 1
  9. 2025FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaborationcited by 1
  10. 2025GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Predictioncited by 1
  11. 2026APWA: A Distributed Architecture for Parallelizable Agentic Workflowscited by 1
  12. 2026How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysiscited by 1
  13. 2026Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesiscited by 1
  14. 2025Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Unitscited by 0
  15. 2026AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflowscited by 0
  16. 2026Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Executioncited by 0
  17. 2026Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agentscited by 0
  18. 2026MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graphcited by 0
  19. 2026MoFlow: Multi-Objective Agentic Workflow Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
  2. 2026FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
  3. 2026Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows
  4. 2025A Survey on Agent Workflow -- Status and Future
  5. 2024Benchmarking Agentic Workflow Generation
  6. 2026Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline
  7. 2025Self-Organizing Agent Network for LLM-based Workflow Automation
  8. 2025LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation