Flows: Building Blocks of Reasoning and Collaborating AI
- URL: http://arxiv.org/abs/2308.01285v3
- Date: Wed, 7 Feb 2024 10:15:53 GMT
- Title: Flows: Building Blocks of Reasoning and Collaborating AI
- Authors: Martin Josifoski, Lars Klein, Maxime Peyrard, Nicolas Baldwin, Yifei
Li, Saibo Geng, Julian Paul Schnitzler, Yuxing Yao, Jiheng Wei, Debjit Paul,
Robert West
- Abstract summary: Flows are self-contained building blocks of computation, with an isolated state.
We demonstrate the potential of Flows on competitive coding, a challenging task on which even GPT-4 struggles.
To support rapid and rigorous research, we introduce the aiFlows library embodying Flows.
- Score: 24.57836563784203
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Flow State: Humans Enabling AI Systems to Program Themselves [0.24578723416255752]
We introduce Pocketflow, a platform centered on Human-AI co-design.
Pocketflow is a Python framework built upon a deliberately minimal yet synergistic set of core abstractions.
It provides a robust, vendor-agnostic foundation with very little code that demonstrably reduces overhead.
arXiv Detail & Related papers (2025-04-03T05:25:46Z) - Large Action Models: From Inception to Implementation [51.81485642442344]
Large Action Models (LAMs) are designed for action generation and execution within dynamic environments.
LAMs hold the potential to transform AI from passive language understanding to active task completion.
We present a comprehensive framework for developing LAMs, offering a systematic approach to their creation, from inception to deployment.
arXiv Detail & Related papers (2024-12-13T11:19:56Z) - GenAgent: Build Collaborative AI Systems with Automated Workflow Generation -- Case Studies on ComfyUI [64.57616646552869]
This paper explores collaborative AI systems that use to enhance performance to integrate models, data sources, and pipelines to solve complex and diverse tasks.
We introduce GenAgent, an LLM-based framework that automatically generates complex, offering greater flexibility and scalability compared to monolithic models.
The results demonstrate that GenAgent outperforms baseline approaches in both run-level and task-level evaluations.
arXiv Detail & Related papers (2024-09-02T17:44:10Z) - Employing Artificial Intelligence to Steer Exascale Workflows with Colmena [37.42013214123005]
Colmena allows scientists to define how their application should respond to events as a series of cooperative agents.
We describe the challenges we overcame while deploying applications on exascale systems, and the science we have enhanced through AI.
Our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.
arXiv Detail & Related papers (2024-08-26T17:21:19Z) - Online Joint Fine-tuning of Multi-Agent Flows [12.851745991007169]
I describe a procedure for online joint fine-tuning of an entire flow inspired by the Learning to Search framework.
The approach leverages simulator access to reduce preferences over entire episodes to preferences over individual node outputs.
I apply to the multi-hop QA dataset Musique achieving a state-of-the-art result.
arXiv Detail & Related papers (2024-06-06T21:21:03Z) - Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning [89.89857766491475]
We propose a complex reasoning schema over KG upon large language models (LLMs)
We augment the arbitrary first-order logical queries via binary tree decomposition to stimulate the reasoning capability of LLMs.
Experiments across widely used datasets demonstrate that LACT has substantial improvements(brings an average +5.5% MRR score) over advanced methods.
arXiv Detail & Related papers (2024-05-02T18:12:08Z) - Using AI libraries for Incompressible Computational Fluid Dynamics [0.7734726150561089]
We present a novel methodology to bring the power of both AI software and hardware into the field of numerical modelling.
We use the proposed methodology to solve the advection-diffusion equation, the non-linear Burgers equation and incompressible flow past a bluff body.
arXiv Detail & Related papers (2024-02-27T22:00:50Z) - Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflow [18.15979295351043]
Generative AI brings novel and impressive abilities to help people in everyday tasks.
It is uncertain how useful generative AI are after the novelty wears off.
We conducted a three-week longitudinal study with 12 users to understand the familiarization and customization of generative AI tools for science communication.
arXiv Detail & Related papers (2024-02-15T11:39:11Z) - Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL)
This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
arXiv Detail & Related papers (2023-12-22T17:57:57Z) - A User-Centred Framework for Explainable Artificial Intelligence in
Human-Robot Interaction [70.11080854486953]
We propose a user-centred framework for XAI that focuses on its social-interactive aspect.
The framework aims to provide a structure for interactive XAI solutions thought for non-expert users.
arXiv Detail & Related papers (2021-09-27T09:56:23Z) - The MineRL BASALT Competition on Learning from Human Feedback [58.17897225617566]
The MineRL BASALT competition aims to spur forward research on this important class of techniques.
We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions.
We provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline.
arXiv Detail & Related papers (2021-07-05T12:18:17Z) - Deep Imitation Learning for Bimanual Robotic Manipulation [70.56142804957187]
We present a deep imitation learning framework for robotic bimanual manipulation.
A core challenge is to generalize the manipulation skills to objects in different locations.
We propose to (i) decompose the multi-modal dynamics into elemental movement primitives, (ii) parameterize each primitive using a recurrent graph neural network to capture interactions, and (iii) integrate a high-level planner that composes primitives sequentially and a low-level controller to combine primitive dynamics and inverse kinematics control.
arXiv Detail & Related papers (2020-10-11T01:40:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.