Figure 1 - available via license: Creative Commons Attribution-ShareAlike 4.0 International
Content may be subject to copyright.
Download
View publication
The GenAgent framework builds collaborative AI systems by creating workflows. The workflows are converted into code so that LLM agents can better understand them. GenAgent can learn from human-designed workflows and create new ones. The generated workflows can be interpreted as collaborative systems to complete complex tasks.

The GenAgent framework builds collaborative AI systems by creating workflows. The workflows are converted into code so that LLM agents can better understand them. GenAgent can learn from human-designed workflows and create new ones. The generated workflows can be interpreted as collaborative systems to complete complex tasks.

Source publication
Figure 1: The GenAgent framework builds collaborative AI systems by...
Figure 11: Prompt Template of RefineAgent.
GenAgent: Build Collaborative AI Systems with Automated Workflow Generation -- Case Studies on ComfyUI
Preprint
Full-text available
  • Sep 2024
Much previous AI research has focused on developing monolithic models to maximize their intelligence and capability, with the primary goal of enhancing performance on specific tasks. In contrast, this paper explores an alternative approach: collaborative AI systems that use workflows to integrate models, data sources, and pipelines to solve complex...
Cite
Download full-text

Context in source publication

Context 1
... this paper, we define the automatic design of collaborative AI systems as a problem of automatic workflow design, as shown in Figure 1. A workflow serves as a high-level abstraction of a collaborative AI system. ...

Similar publications

Figure 2. Properties of the SmARTR networks Requirements, volume...
Figure 3. Visualization capabilities and applications of the SmARTR...
Figure 4. SmARTR-enhanced renderings of intact specimens Cinematic...
Figure 6. Cinematic cutaway views of vertebrate samples implemented...
Figure 7. Comparative view of internal organs from different vertebrate...
The SmARTR pipeline: A modular workflow for the cinematic rendering of 3D scientific imaging data
Article
Full-text available
  • Nov 2024
Advancements in noninvasive surface and internal imaging techniques, along with computational methods, have revolutionized 3D visualization of organismal morphology—enhancing research, medical anatomical analysis, and facilitating the preservation and digital archiving of scientific specimens. We introduce the SmARTR pipeline (Small Animal Realisti...
View