{"ID":2882207,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10419","arxiv_id":"2508.10419","title":"ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning","abstract":"Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and its high computational cost, retrieval-based approaches remain a pivotal role in practice. However, traditional RAG methods could fall short due to their stateless, single-step retrieval process, which often overlooks the dynamic nature of capturing interconnected relations within long-range context. In this work, we propose ComoRAG, holding the principle that narrative reasoning is not a one-shot process, but a dynamic, evolving interplay between new evidence acquisition and past knowledge consolidation, analogous to human cognition on reasoning with memory-related signals in the brain. Specifically, when encountering a reasoning impasse, ComoRAG undergoes iterative reasoning cycles while interacting with a dynamic memory workspace. In each cycle, it generates probing queries to devise new exploratory paths, then integrates the retrieved evidence of new aspects into a global memory pool, thereby supporting the emergence of a coherent context for the query resolution. Across four challenging long-context narrative benchmarks (200K+ tokens), ComoRAG outperforms strong RAG baselines with consistent relative gains up to 11% compared to the strongest baseline. Further analysis reveals that ComoRAG is particularly advantageous for complex queries requiring global context comprehension, offering a principled, cognitively motivated paradigm towards retrieval-based stateful reasoning. Our framework is made publicly available at https://github.com/EternityJune25/ComoRAG.","short_abstract":"Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and its high computational cost, retrieval-based approaches remain a...","url_abs":"https://arxiv.org/abs/2508.10419","url_pdf":"https://arxiv.org/pdf/2508.10419v3","authors":"[\"Juyuan Wang\",\"Rongchen Zhao\",\"Wei Wei\",\"Yufeng Wang\",\"Mo Yu\",\"Jie Zhou\",\"Jin Xu\",\"Liyan Xu\"]","published":"2025-08-14T07:52:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"LoRA\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":610868,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2882207,"paper_url":"https://arxiv.org/abs/2508.10419","paper_title":"ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning","repo_url":"https://github.com/EternityJune25/ComoRAG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}