mlsanityData to 7 Oct 2026

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows

arXiv 2403.11322 ↗First posted 17 Mar 2024cs.CL cs.AIcited by 65

Not on the map. Why?

Cited by 46 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

It is a notable trend to use Large Language Models (LLMs) to tackle complex tasks, e.g., tasks that require a sequence of actions and dynamic interaction with tools and external environments. In this paper, we propose StateFlow, a novel LLM-based task-solving paradigm that conceptualizes complex task-solving processes as state machines. In StateFlow, we distinguish between "process grounding" (via state and state transitions) and "sub-task solving" (through actions within a state), enhancing control and interpretability of the task-solving procedure. A state represents the status of a running process. The transitions between states are controlled by heuristic rules or decisions made by the LLM, allowing for a dynamic and adaptive progression. Upon entering a state, a series of actions is executed, involving not only calling LLMs guided by different prompts, but also the utilization of external tools as needed. Our results show that StateFlow significantly enhances LLMs' efficiency. For instance, StateFlow achieves 13% and 28% higher success rates compared to ReAct in InterCode SQL and ALFWorld benchmark, with 5x and 3x less cost respectively. We also show that StateFlow can be combined with iterative refining methods like Reflexion to further improve performance.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 46 of its 66 references that are in the map. First posted on arXiv 17 Mar 2024.

Builds on

46 of 66 references.

References · 46

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  11. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  12. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
34 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  2. 2023Teaching Large Language Models to Self-Debugcited by 963
  3. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  4. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  5. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  6. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  7. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  8. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  9. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  10. 2023Cognitive Architectures for Language Agentscited by 422
  11. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 414
  12. 2023Augmented Language Models: a Surveycited by 398
  13. 2023Language Models can Solve Computer Taskscited by 371
  14. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
  15. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  16. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  17. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  18. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  19. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  20. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 195
  21. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  22. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  23. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  24. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  25. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  26. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  27. 2022Language Model Cascadescited by 104
  28. 2023Cumulative Reasoning with Large Language Modelscited by 94
  29. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  30. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 67
  31. 2023IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Modelscited by 26
  32. 2021You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradientcited by 14
  33. 2019DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruningcited by 13
  34. 2023HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shiftscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 21; 2026: 31.

65 papers.

Sort:

By area:

  1. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  2. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
  3. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  4. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  5. 2024Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligencecited by 80
  6. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 76
  7. 2024Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agentscited by 35
  8. 2025ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflectioncited by 30
  9. 2025Thought Communication in Multiagent Collaborationcited by 28
  10. 2025SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinementcited by 27
  11. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-trackingcited by 21
  12. 2025MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machinescited by 17
38 more
  1. 2025Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Modelscited by 15
  2. 2025ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigationcited by 15
  3. 2024HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflowscited by 13
  4. 2024EcoAct: Economic Agent Determines When to Register What Actioncited by 11
  5. 2025Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environmentscited by 11
  6. 2025Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agentscited by 11
  7. 2025Agent-S: LLM Agentic workflow to automate Standard Operating Procedurescited by 10
  8. 2024Cognitive Kernel: An Open-source Agent System towards Generalist Autopilotscited by 9
  9. 2026Live-Evo: Online Evolution of Agentic Memory from Continuous Feedbackcited by 8
  10. 2025GeoFlow: Agentic Workflow Automation for Geospatial Taskscited by 7
  11. 2024PRACT: Optimizing Principled Reasoning and Acting of LLM Agentcited by 6
  12. 2025Automating Structural Engineering Workflows with Large Language Model Agentscited by 6
  13. 2026The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Checkcited by 6
  14. 2024QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQLcited by 5
  15. 2025AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robotcited by 5
  16. 2025Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reductioncited by 4
  17. 2026MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learningcited by 4
  18. 2026Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agentscited by 4
  19. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 4
  20. 2024Memory-Augmented Agent Training for Business Document Understandingcited by 3
  21. 2025Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scalecited by 3
  22. 2026Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidthcited by 3
  23. 2026GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Servingcited by 3
  24. 2025Evaluating LLMs on Sequential API Call Through Automated Test Generationcited by 2
  25. 2025Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizerscited by 2
  26. 2026PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaborationcited by 2
  27. 2026PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agentscited by 2
  28. 2026Automata from Agent Traces: Failure and Next-Step Predictioncited by 2
  29. 2026When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflowscited by 2
  30. 2024Mediating Modes of Thought: LLM's for design scriptingcited by 1
  31. 2025SHERPA: A Model-Driven Framework for Large Language Model Executioncited by 1
  32. 2026SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatchcited by 1
  33. 2026Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agentscited by 1
  34. 2026StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discoverycited by 1
  35. 2026LogicHunter: Testing LLM Agent Frameworks with an Agentic Oraclecited by 1
  36. 2026What makes prompts a graph: necessary and sufficient conditions for prompt graph engineeringcited by 1
  37. 2026CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansioncited by 1
  38. 2025The Art of Tool Interface Designcited by 0

50 most cited of 65 All 65 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
  2. 2024WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
  3. 2026FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
  4. 2026From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
  5. 2025CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision
  6. 2026ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
  7. 2026AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
  8. 2025Accelerating Language Model Workflows with Prompt Choreography