IS-CoT: 通过交错结构思维打破长文本生成崩溃
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
AI总结：
针对大语言模型在长文本生成中因静态层次规划导致长度崩溃的问题，提出交错结构思维链（IS-CoT）框架，通过动态规划-写作-反思循环实现持续策略调整，训练IS-Writer-8B模型在长文本基准上取得最优性能。
摘要：
生成连贯且可控的长文本内容仍然是大语言模型（LLMs）面临的一个持久挑战。虽然推理增强模型在逻辑密集型领域已展现出成功，但我们的评估揭示，它们在开放式写作中遭受严重的长度崩溃，当目标长度超过2,000词时性能急剧下降。我们将这一失败归因于静态层次规划的局限性，它难以在扩展上下文中提供动态指导。为弥补这一差距，我们引入了交错结构思维链（IS-CoT）框架。与外部智能体工作流不同，IS-CoT将动态的规划-写作-反思循环嵌入生成过程，无需额外辅助即可实现持续策略调整和全局对齐。基于该框架，我们通过多教师管道构建了一个高质量的交错推理轨迹数据集，并训练了IS-Writer-8B。实验表明，IS-Writer-8B在具有挑战性的长文本基准上取得了最先进的性能（例如，在LongBench-Write上比DeepSeek-V3.2高出+3.08），展现出与显著更大的专有模型相竞争的长度合规性和连贯性。
英文摘要：
Generating coherent and controllable long-form content remains a persistent challenge for Large Language Models (LLMs). While reasoning-enhanced models have demonstrated success in logic-intensive domains, our evaluation reveals that they suffer from a severe length collapse in open-ended writing, where performance degrades sharply as target lengths exceed 2,000 words. We attribute this failure to the limitation of static hierarchical planning, which struggles to provide dynamic guidance over extended contexts. To bridge this gap, we introduce the Interleaved Structural Chain-of-Thought (IS-CoT) framework. Unlike external agentic workflows, IS-CoT embeds a dynamic Plan-Write-Reflect cycle into the generation process, enabling continuous strategy adaptation and global alignment without additional assistance. Based on this framework, we construct a high-quality dataset of interleaved reasoning traces via a multi-teacher pipeline and train IS-Writer-8B. Experiments demonstrate that IS-Writer-8B achieves state-of-the-art performance on challenging long-form benchmarks (e.g., +3.08 vs. DeepSeek-V3.2 on LongBench-Write), exhibiting robust length compliance and coherence competitive with significantly larger proprietary models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
