ACT: Knowledgeable Agents to Design and Perform Complex Tasks

Large language models enhance collaborative task execution in multi-agent systems. Current studies divide a complex task into manageable components for agents to solve. However, agents often lack a clear understanding of the overall task and each other's roles, hindering synergy and solution integration. We propose a method called knowledgeable Agents to design and perform Complex Tasks (ACT), where: (1) Agents independently manage their knowledge and tasks while collaboratively designing the complex task into a more comprehensible form. In parallel, each agent also acquires knowledge of others, defined as a structured description of how other agents approach their tasks based on the agent's own task resolution. (2) Each agent updates its knowledge and refines its task through interactions with others. By referencing structured knowledge, the agents effectively integrate their tasks to collaboratively solve the complex task. Three evaluations, including creative writing and tool utilization, show that ACT outperforms existing methods in terms of accuracy when solving complex tasks. Detailed prompt examples are included in the appendix to facilitate future research reuse.