mlsanityData to 14 Oct 2026

Flows: Building Blocks of Reasoning and Collaborating AI

arXiv 2308.01285 ↗First posted 2 Aug 2023cs.AI cs.HCcited by 25

Not on the map. Why?

Abstract (arXiv)

Recent advances in artificial intelligence (AI) have produced highly capable and controllable systems. This creates unprecedented opportunities for structured reasoning as well as collaboration among multiple AI systems and humans. To fully realize this potential, it is essential to develop a principled way of designing and studying such structured interactions. For this purpose, we introduce the conceptual framework Flows. Flows are self-contained building blocks of computation, with an isolated state, communicating through a standardized message-based interface. This modular design simplifies the process of creating Flows by allowing them to be recursively composed into arbitrarily nested interactions and is inherently concurrency-friendly. Crucially, any interaction can be implemented using this framework, including prior work on AI-AI and human-AI interactions, prompt engineering schemes, and tool augmentation. We demonstrate the potential of Flows on competitive coding, a challenging task on which even GPT-4 struggles. Our results suggest that structured reasoning and collaboration substantially improve generalization, with AI-only Flows adding +21 and human-AI Flows adding +54 absolute points in terms of solve rate. To support rapid and rigorous research, we introduce the aiFlows library embodying Flows. The aiFlows library is available at https://github.com/epfl-dlab/aiflows. Data and Flows for reproducing our experiments are available at https://github.com/epfl-dlab/cc_flows.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 36 of its 83 references that are in the map. First posted on arXiv 2 Aug 2023.

Builds on

36 of 83 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  10. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  11. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  12. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
24 more
  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  4. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  5. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  6. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  8. 2023Teaching Large Language Models to Self-Debugcited by 988
  9. 2021Measuring Coding Challenge Competence With APPScited by 902
  10. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  11. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  12. 2023Language Models can Solve Computer Taskscited by 372
  13. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 356
  14. 2022Generating Sequences by Learning to Self-Correctcited by 277
  15. 2022Data Contamination: From Memorization to Exploitationcited by 236
  16. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
  17. 2016DeepCoder: Learning to Write Programscited by 149
  18. 2022Explanations Can Reduce Overreliance on AI Systems During Decision-Makingcited by 111
  19. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  20. 2022PEER: A Collaborative Language Modelcited by 86
  21. 2022Learning to Model Editing Processescited by 30
  22. 2023When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programmingcited by 25
  23. 2022Language Model Decoding as Likelihood-Utility Alignmentcited by 5
  24. 2021Ideal Partition of Resources for Metareasoningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 14; 2025: 3; 2026: 4.

25 papers.

Sort:

By area:

  1. 2024Large Language Models: A Surveycited by 525
  2. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  3. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  4. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 178
  5. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  6. 2024AIOS: LLM Agent Operating Systemcited by 97
  7. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 86
  8. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 83
  9. 2024Evaluating Language Model Agency through Negotiationscited by 48
  10. 2025Repo2Run: Automated Building Executable Environment for Code Repository at Scalecited by 39
  11. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 37
  12. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 37
13 more
  1. 2024ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertisecited by 21
  2. 2023INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repaircited by 18
  3. 2024AutoSAT: Automatically Optimize SAT Solvers via Large Language Modelscited by 15
  4. 2026AIRA_2: Overcoming Bottlenecks in AI Research Agentscited by 12
  5. 2024AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agentscited by 8
  6. 2024CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Modelscited by 7
  7. 2025CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generationcited by 6
  8. 2024Fleet of Agents: Coordinated Problem Solving with Large Language Modelscited by 5
  9. 2026What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Searchcited by 5
  10. 2026GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Servingcited by 3
  11. 2026What makes prompts a graph: necessary and sufficient conditions for prompt graph engineeringcited by 1
  12. 2024Emojinize: Enriching Any Text with Emoji Translationscited by 0
  13. 2024AutoGRAMS: Autonomous Graphical Agent Modeling Softwarecited by 0