Saved in:
Bibliographic Details
Main Authors: Hao, Pan, Kang, Dongyeop, Hinds, Nicholas, Wang, Qianwen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.15559
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916853827239936
author Hao, Pan
Kang, Dongyeop
Hinds, Nicholas
Wang, Qianwen
author_facet Hao, Pan
Kang, Dongyeop
Hinds, Nicholas
Wang, Qianwen
contents Multi-agent workflows have become an effective strategy for tackling complicated tasks by decomposing them into multiple sub-tasks and assigning them to specialized agents. However, designing optimal workflows remains challenging due to the vast and intricate design space. Current practices rely heavily on the intuition and expertise of practitioners, often resulting in design fixation or an unstructured, time-consuming exploration of trial-and-error. To address these challenges, this work introduces FLOWFORGE, an interactive visualization tool to facilitate the creation of multi-agent workflow through i) a structured visual exploration of the design space and ii) in-situ guidance informed by established design patterns. Based on formative studies and literature review, FLOWFORGE organizes the workflow design process into three hierarchical levels (i.e., task planning, agent assignment, and agent optimization), ranging from abstract to concrete. This structured visual exploration enables users to seamlessly move from high-level planning to detailed design decisions and implementations, while comparing alternative solutions across multiple performance metrics. Additionally, drawing from established workflow design patterns, FLOWFORGE provides context-aware, in-situ suggestions at each level as users navigate the design space, enhancing the workflow creation process with practical guidance. Use cases and user studies demonstrate the usability and effectiveness of FLOWFORGE, while also yielding valuable insights into how practitioners explore design spaces and leverage guidance during workflow development.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlowForge: Guiding the Creation of Multi-agent Workflows with Design Space Visualization as a Thinking Scaffold
Hao, Pan
Kang, Dongyeop
Hinds, Nicholas
Wang, Qianwen
Human-Computer Interaction
Multi-agent workflows have become an effective strategy for tackling complicated tasks by decomposing them into multiple sub-tasks and assigning them to specialized agents. However, designing optimal workflows remains challenging due to the vast and intricate design space. Current practices rely heavily on the intuition and expertise of practitioners, often resulting in design fixation or an unstructured, time-consuming exploration of trial-and-error. To address these challenges, this work introduces FLOWFORGE, an interactive visualization tool to facilitate the creation of multi-agent workflow through i) a structured visual exploration of the design space and ii) in-situ guidance informed by established design patterns. Based on formative studies and literature review, FLOWFORGE organizes the workflow design process into three hierarchical levels (i.e., task planning, agent assignment, and agent optimization), ranging from abstract to concrete. This structured visual exploration enables users to seamlessly move from high-level planning to detailed design decisions and implementations, while comparing alternative solutions across multiple performance metrics. Additionally, drawing from established workflow design patterns, FLOWFORGE provides context-aware, in-situ suggestions at each level as users navigate the design space, enhancing the workflow creation process with practical guidance. Use cases and user studies demonstrate the usability and effectiveness of FLOWFORGE, while also yielding valuable insights into how practitioners explore design spaces and leverage guidance during workflow development.
title FlowForge: Guiding the Creation of Multi-agent Workflows with Design Space Visualization as a Thinking Scaffold
topic Human-Computer Interaction
url https://arxiv.org/abs/2507.15559