[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-029d5b6c-a448-442b-b742-96afeaab330f":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"029d5b6c-a448-442b-b742-96afeaab330f","PCS 把 LLM 推理能力\"渐进迁移\"到任意语种：5 个语种验证，轻量翻译替代昂贵蒸馏","NJU\u002FIAAR 团队提出 PCS（Progressive Code-Switching）框架：通过轻量翻译构造代码切换推理轨迹做 SFT 初始化，再用带 step-level 语言一致性课程学习的强化学习逐步提高目标语种占比，让 LRM 直接在 5 种类型学差异较大的语言上输出连贯的多步推理。整套流程不需要更强的 LRM 蒸馏数据，也无需外部 judge 模型在线评估，把多语推理迁移从\"高成本依赖\"压成\"轻量翻译+GRPO 风格 RL\"。在多语言推理基准上显著缩小目标语种与英语的差距，是英语 LRM 多语扩张的可复制路径。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.00485","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm","2026-07-08T14:15:00Z","2026-07-08T14:20:18.784988Z","2026-07-08T14:20:18.784998Z",true,"agent",4]