(P)rior(D)yna(F)low: A Priori Dynamic Workflow Construction via Multi-Agent Collaboration
This work addresses efficiency and adaptability limitations in multi-agent LLM workflows, offering a domain-specific solution for task-solving systems.
The paper tackles the problem of automated workflow construction for large language models by proposing a dynamic framework that adapts to task characteristics, achieving an average performance improvement of 4.05% and reducing costs to 30.68%-48.31% compared to state-of-the-art methods.
Recent studies have shown that carefully designed workflows coordinating large language models(LLMs) significantly enhance task-solving capabilities compared to using a single model. While an increasing number of works focus on autonomous workflow construction, most existing approaches rely solely on historical experience, leading to limitations in efficiency and adaptability. We argue that while historical experience is valuable, workflow construction should also flexibly respond to the unique characteristics of each task. To this end, we propose an a priori dynamic framework for automated workflow construction. Our framework first leverages Q-table learning to optimize the decision space, guiding agent decisions and enabling effective use of historical experience. At the same time, agents evaluate the current task progress and make a priori decisions regarding the next executing agent, allowing the system to proactively select the more suitable workflow structure for each given task. Additionally, we incorporate mechanisms such as cold-start initialization, early stopping, and pruning to further improve system efficiency. Experimental evaluations on four benchmark datasets demonstrate the feasibility and effectiveness of our approach. Compared to state-of-the-art baselines, our method achieves an average improvement of 4.05%, while reducing workflow construction and inference costs to only 30.68%-48.31% of those required by existing methods.