The Decomposition Dilemma: When Do Multi-Agent LLM Workflows Help Grounded Knowledge Generation?
TL;DR
A preliminary task-level comparison of a Direct Generation Workflow and a Decomposed Generation Workflow under matched inputs and evaluation conditions provides preliminary evidence that the value of multi-agent decomposition is task-dependent.
Abstract
Large Language Model (LLM) workflows increasingly decompose knowledge-intensive generation into planning, role assignment, subtask execution, and synthesis. Although this structure may support specialization, it also adds coordination and computational overhead. We present a preliminary task-level comparison of a Direct Generation Workflow and a Decomposed Generation Workflow under matched inputs and evaluation conditions. The study covers three grounded knowledge-generation tasks: public-event narrative synthesis, project-grounded research ideation, and scientific related-work generation. Across the evaluated configurations, decomposition produces the largest mean Task Quality Score (TQS) gain for research ideation (+0.053), a smaller gain for related-work generation (+0.025), and only a modest gain for public-event narrative synthesis (+0.013). These improvements require 95.1–126.2 seconds of additional runtime on average. The results provide preliminary evidence that the value of multi-agent decomposition is task-dependent.
