Flows: Building Blocks of Reasoning and Collaborating AI

by   Martin Josifoski, et al.

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 of Flows: a systematic approach to modeling complex interactions. Flows are self-contained building blocks of computation, with an isolated state, communicating through a standardized message-based interface. This modular design allows Flows to be recursively composed into arbitrarily nested interactions, with a substantial reduction of complexity. 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 the task of 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. The library comes with a repository of Flows that can be easily used, extended, and composed into novel, more complex 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.


page 6

page 8


XCloud: Design and Implementation of AI Cloud Platform with RESTful API Service

In recent years, artificial intelligence (AI) has aroused much attention...

LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents

In the last few decades we have witnessed a significant development in A...

AI for Closed-Loop Control Systems — New Opportunities for Modeling, Designing, and Tuning Control Systems

Control Systems, particularly closed-loop control systems (CLCS), are fr...

NIMS-OS: An automation software to implement a closed loop between artificial intelligence and robotic experiments in materials science

NIMS-OS (NIMS Orchestration System) is a Python library created to reali...

Towards Effective Human-AI Collaboration in GUI-Based Interactive Task Learning Agents

We argue that a key challenge in enabling usable and useful interactive ...

Structured access to AI capabilities: an emerging paradigm for safe AI deployment

Structured capability access ("SCA") is an emerging paradigm for the saf...

Preference Discovery in Large Product Lines

When AI tools can generate many solutions, some human preference must be...

Please sign up or login with your details

Forgot password? Click here to reset