{"ID":5551672,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T13:20:54.626185648Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00918","arxiv_id":"2607.00918","title":"From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","abstract":"Although large language models (LLMs) have demonstrated impressive creative fiction generation, they struggle to maintain narrative consistency and coherent plot lines in long-form stories. In this work, we introduce a unified framework for long-form narrative generation and verification. MAGNET, a multi-agent goal-driven narrative engine for storytelling, generates stories with persona-grounded character agents that propose actions based on a shared world state and evolving story goals, while ATLAS is a graph-based pipeline that compares scene-level world representations across a generated story to detect hallucinations. By evaluating MAGNET using an LLM editor, pairwise rubric scoring, and ATLAS, we show that our framework produces coherent narratives compared to single-model prompting and IBSEN. At 100 pages, MAGNET reduced annotations and hallucinations by 41 and 50%, respectively, compared to the single model baseline and by 34 and 45%, respectively, compared to IBSEN, with pairwise rubric evaluation showing similar results. These results suggest that long-form narratives can emerge from explicit world-state tracking and goal-driven multi-agent generation, providing a foundation for controllable and structurally coherent long-form narrative generation.","short_abstract":"Although large language models (LLMs) have demonstrated impressive creative fiction generation, they struggle to maintain narrative consistency and coherent plot lines in long-form stories. In this work, we introduce a unified framework for long-form narrative generation and verification. MAGNET, a multi-agent goal-dri...","url_abs":"https://arxiv.org/abs/2607.00918","url_pdf":"https://arxiv.org/pdf/2607.00918v1","authors":"[\"Aayush Aluru\",\"Chloe Ho\",\"Muhammad Hammouri\",\"Kerry Luo\",\"Myra Malik\",\"Ryan Lagasse\",\"Arjun Bahuguna\",\"Vasu Sharma\"]","published":"2026-07-01T13:23:07Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}