长文本生成是 LLM 的硬伤，IS-CoT 用动态规划循环解决了长度崩溃，做内容生成或写作助手的团队可以直接参考这个 8B 模型的训练方法。
大型语言模型在生成长文本时面临严重的长度崩溃问题，当目标长度超过 2000 词时性能急剧下降。研究者提出 IS-CoT（交错结构思维链）框架，通过嵌入动态的“计划-写作-反思”循环，实现持续策略调整和全局对齐，无需外部辅助。基于该框架训练的 IS-Writer-8B 模型在 LongBench-Write 等基准上取得最优性能，比 DeepSeek-V3.2 高出 3.08 分，长度合规性和连贯性可与更大规模专有模型竞争。该工作揭示了静态分层规划在长上下文中的局限性，为长文本生成提供了新思路。
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
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.