WorkTeam: Constructing Workflows from Natural Language with Multi-Agents
This addresses the challenge of automating workflow creation for enterprises, offering a more effective solution than existing methods, though it appears incremental as it builds on multi-agent approaches for NL2Workflow.
The paper tackles the problem of constructing workflows from natural language instructions, which is hindered by the need for expert knowledge and limitations of single LLM agents, by proposing WorkTeam, a multi-agent framework that increases the success rate of workflow construction, as demonstrated on a new dataset of 3,695 real-world business samples.
Workflows play a crucial role in enhancing enterprise efficiency by orchestrating complex processes with multiple tools or components. However, hand-crafted workflow construction requires expert knowledge, presenting significant technical barriers. Recent advancements in Large Language Models (LLMs) have improved the generation of workflows from natural language instructions (aka NL2Workflow), yet existing single LLM agent-based methods face performance degradation on complex tasks due to the need for specialized knowledge and the strain of task-switching. To tackle these challenges, we propose WorkTeam, a multi-agent NL2Workflow framework comprising a supervisor, orchestrator, and filler agent, each with distinct roles that collaboratively enhance the conversion process. As there are currently no publicly available NL2Workflow benchmarks, we also introduce the HW-NL2Workflow dataset, which includes 3,695 real-world business samples for training and evaluation. Experimental results show that our approach significantly increases the success rate of workflow construction, providing a novel and effective solution for enterprise NL2Workflow services.