paper-with-me

홈 › Papers

Flows: Building Blocks of Reasoning and Collaborating AI

2023-08-02 · Martin Josifoski, Lars Klein, Maxime Peyrard, Nicolas Baldwin, Yifei Li, Saibo Geng, Julian Paul Schnitzler, Yuxing Yao, Jiheng Wei, Debjit Paul, Robert West

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.

📄 PDF Abstract BibTeX arXiv:2308.01285

Code (2)

epfl-dlab/aiflows 공식 구현
epfl-dlab/cc_flows 공식 구현

Tasks

Prompt Engineering

Methods 이 논문이 사용한 방법론

Library 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Composing Verifiable Conceptual Models via Building Blocks: Towards Design-Time Verification of Agentic AI Workflows

2026-06-19 · Noe Y. Flandre, Alexander C. Nwala, Philippe J. Giabbanelli arxiv

Agentic AI systems orchestrate multiple LLM-based agents through workflow architectures that coordinate decisions, tools, and external actions. While current platforms emphasize runtime safeguards, little support exists …

Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale

2025-12-23 · Linfeng Zhang, Siheng Chen, Yuzhu Cai, Jingyi Chai 외 arxiv

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science …

Conformal Embedding Flows: Tractable Density Estimation on Learned Manifolds

2021-06-02 · ICML Workshop INNF 2021 7 · Brendan Leigh Ross, Jesse C Cresswell

Normalizing flows are generative models that provide tractable density estimation by transforming a simple distribution into a complex one. However, flows cannot directly model data supported on an unknown low-dimensiona…

Density Estimation

Generative Flows on Synthetic Pathway for Drug Design

2024-10-06 · Seonghwan Seo, Minsu Kim, Tony Shen, Martin Ester 외

Generative models in drug discovery have recently gained attention as efficient alternatives to brute-force virtual screening. However, most existing models do not account for synthesizability, limiting their practical u…

Drug DesignDrug Discovery

Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows

2021-06-09 · NeurIPS 2021 12 · Brendan Leigh Ross, Jesse C. Cresswell

Normalizing flows are generative models that provide tractable density estimation via an invertible transformation from a simple base distribution to a complex target distribution. However, this technique cannot directly…

Density Estimation