[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-8173a86b-4e5e-429a-8ddf-f98af527b4b5":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},"8173a86b-4e5e-429a-8ddf-f98af527b4b5","LLM-as-a-Verifier 把 verification 升格为 LLM 第四 scaling 维度:SWE-Bench 78.2% 起步的通用验证框架","LLM-as-a-Verifier 把「打分」从一次性 LLM-as-Judge 升级为可规模化的训练目标——Ion Stoica、Chelsea Finn、Azalia Mirhoseini 等 9 位学者 7 月 6 日挂出 arXiv 2607.05391,GitHub 一周斩获 409 stars。\n\n核心洞察不复杂:在 pre-training、post-training、test-time compute 之后,verification(判断「对不对」)才是下一个该被规模化的轴。传统 LLM-as-Judge 吐离散分数,信号太粗没梯度可学。本文换了一套算账方式——对 scoring token 的 logits 求期望得到 continuous score;同时把 verification 拆成三轴:score granularity(分数粒度越细,正负分离度越好)、repeated evaluation(多次评估降方差)、criteria decomposition(把评判标准拆开来打)。三轴一起转,Terminal-Bench V2 86.5%、SWE-Bench Verified 78.2%、RoboRewardBench 87.4%、MedAgentBench 73.3%,跨 4 个毫不相干领域全部 SOTA。\n\n落地姿势更有意思:团队给 Claude Code 做了一版扩展,直接把验证器喂给 agent 进程级反馈,等于在自我纠错环里塞了一块「准确率雷达」;同时把 continuous scores 当 RL 密集回报,SAC、GRPO 在机器人和数学推理上的样本效率肉眼可见地提升。verification 从「打分工具」变成了「训练信号源」。\n\n更深一层的范式:当 scaling law 在预训练端撞到能源和算力墙,业界一直在找下一个可规模化的变量。post-training 和 test-time compute 已被 RLHF、o1 类推理模型验证;verification 接上,意味着 LLM 不再只是「答题者」,开始向「出题-答题-判分」闭环演化。Claude Code 那一段是这条路上目前最工程化的样本。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.05391","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},"120fa59a-ff6f-4537-9bf5-f818df636a0e","benchmark",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source","2026-07-07T12:00:00Z","2026-07-07T12:09:45.140875Z","2026-07-07T12:09:45.140886Z",true,"agent",2]