ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems

• URL: http://arxiv.org/abs/2409.01392v2
• Date: Tue, 26 Nov 2024 14:32:46 GMT
• Title: ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
• Authors: Xiangyuan Xue, Zeyu Lu, Di Huang, Zidong Wang, Wanli Ouyang, Lei Bai,
• Abstract summary: This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
• Score: 80.69865295743149
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast, this work attempts to study using LLM-based agents to design collaborative AI systems autonomously. To explore this problem, we first introduce ComfyBench to evaluate agents's ability to design collaborative AI systems in ComfyUI. ComfyBench is a comprehensive benchmark comprising 200 diverse tasks covering various instruction-following generation challenges, along with detailed annotations for 3,205 nodes and 20 workflows. Based on ComfyBench, we further develop ComfyAgent, a novel framework that empowers LLM-based agents to autonomously design collaborative AI systems by generating workflows. ComfyAgent is based on two core concepts. First, it represents workflows with code, which can be reversibly converted into workflows and executed as collaborative systems by the interpreter. Second, it constructs a multi-agent system that cooperates to learn from existing workflows and generate new workflows for a given task. While experimental results demonstrate that ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15\% of creative tasks. LLM-based agents still have a long way to go in autonomously designing collaborative AI systems. Progress with ComfyBench is paving the way for more intelligent and autonomous collaborative AI systems.

Related papers

• ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation [71.31634636156384]
  We introduce ComfyGPT, the first self-optimizing multi-agent system designed to generate ComfyUI based on task descriptions automatically. ComfyGPT comprises four specialized agents: ReformatAgent, FlowAgent, RefineAgent, and ExecuteAgent. FlowDataset is a large-scale dataset containing 13,571 workflow-description pairs, and FlowBench is a benchmark for evaluating workflow generation systems.
  arXiv  Detail & Related papers  (2025-03-22T06:48:50Z)
• Towards Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approach [35.05793485239977]
  We propose AgentNet, a novel framework for supporting interaction, collaborative learning, and knowledge transfer among AI agents. We consider two application scenarios, digital-twin-based industrial automation and metaverse-based infotainment system, to describe how to apply AgentNet.
  arXiv  Detail & Related papers  (2025-03-20T00:48:44Z)
• PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC [98.82146219495792]
  In this paper, we propose a hierarchical agent framework named PC-Agent. From the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content. From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture.
  arXiv  Detail & Related papers  (2025-02-20T05:41:55Z)
• TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks [52.46737975742287]
  We build a self-contained environment with data that mimics a small software company environment. We find that with the most competitive agent, 24% of the tasks can be completed autonomously. This paints a nuanced picture on task automation with LM agents.
  arXiv  Detail & Related papers  (2024-12-18T18:55:40Z)
• MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration [8.078098082305575]
  This paper introduces MorphAgent, a novel framework for decentralized multi-agent collaboration. MorphAgent employs self-evolving agent profiles, optimized through three key metrics. Our experimental results show that MorphAgent outperforms traditional static-role MAS in terms of task performance and adaptability to changing requirements.
  arXiv  Detail & Related papers  (2024-10-19T09:10:49Z)
• xLAM: A Family of Large Action Models to Empower AI Agent Systems [111.5719694445345]
  We release xLAM, a series of large action models designed for AI agent tasks. xLAM consistently delivers exceptional performance across multiple agent ability benchmarks.
  arXiv  Detail & Related papers  (2024-09-05T03:22:22Z)
• Optimizing Collaboration of LLM based Agents for Finite Element Analysis [1.5039745292757671]
  This paper investigates the interactions between multiple agents within Large Language Models (LLMs) in the context of programming and coding tasks. We utilize the AutoGen framework to facilitate communication among agents, evaluating different configurations based on the success rates from 40 random runs for each setup.
  arXiv  Detail & Related papers  (2024-08-23T23:11:08Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)
• Scaling Large-Language-Model-based Multi-Agent Collaboration [75.5241464256688]
  Pioneering advancements in large language model-powered agents have underscored the design pattern of multi-agent collaboration. Inspired by the neural scaling law, this study investigates whether a similar principle applies to increasing agents in multi-agent collaboration.
  arXiv  Detail & Related papers  (2024-06-11T11:02:04Z)
• S-Agents: Self-organizing Agents in Open-ended Environments [15.700383873385892]
  We introduce a self-organizing agent system (S-Agents) with a "tree of agents" structure for dynamic workflow. This structure can autonomously coordinate a group of agents, efficiently addressing the challenges of open and dynamic environments. Our experiments demonstrate that S-Agents proficiently execute collaborative building tasks and resource collection in the Minecraft environment.
  arXiv  Detail & Related papers  (2024-02-07T04:36:31Z)
• Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution [92.84441068115517]
  Investigate-Consolidate-Exploit (ICE) is a novel strategy for enhancing the adaptability and flexibility of AI agents. ICE promotes the transfer of knowledge between tasks for genuine self-evolution. Our experiments on the XAgent framework demonstrate ICE's effectiveness, reducing API calls by as much as 80%.
  arXiv  Detail & Related papers  (2024-01-25T07:47:49Z)
• CCA: Collaborative Competitive Agents for Image Editing [59.54347952062684]
  This paper presents a novel generative model, Collaborative Competitive Agents (CCA) It leverages the capabilities of multiple Large Language Models (LLMs) based agents to execute complex tasks. The paper's main contributions include the introduction of a multi-agent-based generative model with controllable intermediate steps and iterative optimization.
  arXiv  Detail & Related papers  (2024-01-23T11:46:28Z)
• TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System [14.019244136838017]
  TrainerAgent is a multi-agent framework including Task, Data, Model and Server agents. These agents analyze user-defined tasks, input data, and requirements (e.g., accuracy, speed), optimizing them from both data and model perspectives to obtain satisfactory models, and finally deploy these models as online service. This research presents a significant advancement in achieving desired models with increased efficiency and quality as compared to traditional model development.
  arXiv  Detail & Related papers  (2023-11-11T17:39:24Z)
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration [55.35849138235116]
  We propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($textDyLAN$) for LLM-powered agent collaboration. We demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost.
  arXiv  Detail & Related papers  (2023-10-03T16:05:48Z)
• AutoAgents: A Framework for Automatic Agent Generation [27.74332323317923]
  AutoAgents is an innovative framework that adaptively generates and coordinates multiple specialized agents to build an AI team according to different tasks. Our experiments on various benchmarks demonstrate that AutoAgents generates more coherent and accurate solutions than the existing multi-agent methods.
  arXiv  Detail & Related papers  (2023-09-29T14:46:30Z)
• Self-collaboration Code Generation via ChatGPT [35.88318116340547]
  Large Language Models (LLMs) have demonstrated remarkable code-generation ability, but struggle with complex tasks. We present a self-collaboration framework for code generation employing LLMs, exemplified by ChatGPT. To effectively organize and manage this virtual team, we incorporate software-development methodology into the framework.
  arXiv  Detail & Related papers  (2023-04-15T16:33:32Z)

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.