arXiv · cs.AI · Qi Wang, Kang Xu, Chengcheng Wan, Jiangtao Wang · 10 小时前模型评分41
RECAST：无需隐藏推理通道，从 Claude-Sonnet-5.5 等闭源模型重建思维链
RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces
导读
RECAST 提出一种基于重建的框架，仅凭问题和目标模型的最终答案，就能重建第一人称结构化推理过程，并清理成可直接用于监督微调（受监督微调（SFT，Supervised Fine-Tuning），Supervised Fine-Tuning）的数据。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：ai-tooling，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We present RECAST, a reconstruction-based framework that conditions a decoder on the question and the target model's final answer, reconstructs a first-person structured rationale, cleans it, and builds SFT-ready data.”
- “The system is open-source and packaged as an agent skill: one prompt deploys it and runs the complete pipeline to produce SFT-ready CoT data.”
- “This preprint describes the system, its threat model, and a controlled artifact validation; it does not claim large-scale benchmark improvements.”
来源：arXiv · cs.AI · arxiv.org