Collective Critics for Creative Story Generation

Abstract

Generating long, coherent narratives with several thousand words remains a difficult challenge for Large Language Models (LLMs). Prior studies have attempted to alleviate this issue by introducing frame- works that first construct a story plan and then generate the final story based on that plan. However, most of these approaches concentrate primarily on preserving narrative coherence, often neglecting two crucial elements for engaging storytelling: the creativity embedded in the planning process and the ex- pressiveness of the final narrative. In this work, we present CRITICS(Collective Critics for Creative Story Generation), a framework designed to address these limitations through a two-stage process: CR- PLAN for plan refinement and CRTEXT for story generation. Our framework incorporates a collective critique mechanism in which a group of LLM-based critics and a designated leader collaboratively refine both the plan and the story across multiple iterative rounds. Through extensive human evaluation, we show that CRITICS markedly improves story creativity and reader engagement, while still preserving strong narrative coherence. Moreover, because the framework is structured around a collaborative cri- tique workflow, human writers can seamlessly participate in any role—leader, critic, or author—enabling dynamic and interactive human–AI co-creation of long-form stories.