[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-openskill-unsupervised-agent-skill-verifier":3,"topics-all":33,"news-related-9a676112-c689-4a79-8216-604f2d0c76a0":52},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":20,"news_slug":26,"published_at":27,"created_at":28,"modified_at":29,"is_published":30,"publish_type":31,"image_url":13,"view_count":32},"9a676112-c689-4a79-8216-604f2d0c76a0","OpenSkill 框架：让 LLM Agent 在无监督条件下从零自建技能与验证器","arXiv 2606.06741 提出的 OpenSkill 给\"自进化 Agent\"换了一个干净的问题设定：真实开放部署中往往没有可用学习循环——既无整理好的技能库，也无成功轨迹，更无显式验证信号；留给 Agent 的只有任务提示。OpenSkill 让 Agent 从文档、代码仓库和开放网页中获取带\"锚定\"的领域知识与验证依据，再把这种知识合成为可迁移的技能，并用自建的虚拟任务进行强化——这些任务以锚定为基础，而不是目标答案，从而在完全不接触目标监督的情况下完成自我打磨。\n\n论文在三个基准上对两个目标 Agent 进行测试，在满足\"无监督\"约束的前提下拿到了最高的自动通过率。更有意思的是两件事：OpenSkill 学到的技能可以跨模型迁移而无需针对性微调；它自建的验证器虽然从未见过真实结果，但与 ground-truth 的判定高度一致。\n\n这件事值得说道的点在于：过去一年自进化相关工作几乎都建立在\"先有可用监督\"或\"先有 golden trajectory\"的前提上，这种前提在工业部署中很难凑齐。OpenSkill 把\"无监督 + 跨模型可迁移\"摆到了台面上，相当于把 Agent 训练的数据门槛拉回到了\"只要有公开文档\"的水平。结合近期 self-evolution 类论文频出的趋势，这条路如果走通，企业 Agent 的迭代周期会从\"月\"缩短到\"周\"。但也要冷静：跨模型迁移在 reasoning-heavy 任务上的边界、自建验证器在长尾分布上的鲁棒性，目前都还没有系统数据。算法很优雅，下一步要看的不是论文分数，而是真生产环境里跑不跑得动。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.06741","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17],{"id":11,"name":12,"slug":12,"description":13,"color":13},"6ad31a14-c0da-42df-81fd-564281f768db","agentic-ai",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},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[21],{"id":22,"lang":23,"title":24,"summary":25,"content":13},"317ca01c-8d23-4ec7-a1aa-bcd7218cde70","en","OpenSkill: agents build their own skills and verifiers","arXiv 2606.06741's OpenSkill changes the problem setting for \"self-evolving Agents\" to something cleaner: in real open deployments, often there is no available learning loop — no curated skill library, no successful trajectories, no explicit verification signal; the only thing left to the Agent is the task prompt. OpenSkill lets the Agent acquire \"anchored\" domain knowledge and verification evidence from documentation, code repositories, and open web pages, then synthesize that knowledge into transferable skills, and use self-built virtual tasks for reinforcement — these tasks are based on anchors, not target answers, completing self-polish without ever touching target supervision.\n\nThe paper tests two target Agents on three benchmarks, achieving the highest auto pass rate under the \"unsupervised\" constraint. Two things are more interesting: the skills learned by OpenSkill can be transferred across models without targeted fine-tuning; its self-built verifiers, although never having seen real results, agree highly with ground-truth judgments.\n\nThe point worth saying is: over the past year, self-evolution-related work has almost all been built on the premise of \"available supervision first\" or \"golden trajectory first\" — a premise that is hard to assemble in industrial deployment. OpenSkill puts \"unsupervised + cross-model transferable\" on the table, equivalent to pulling the data threshold for Agent training back to the level of \"as long as there are public documents.\" Combined with the recent trend of frequent self-evolution papers, if this path works, the iteration cycle for enterprise Agents will shorten from \"months\" to \"weeks.\" But stay cool: the boundary of cross-model transfer on reasoning-heavy tasks, and the robustness of self-built verifiers on long-tail distributions, both still lack systematic data. The algorithm is elegant; the next thing to see is not the paper score, but whether it actually runs in real production environments.","openskill-unsupervised-agent-skill-verifier","2026-06-08T12:00:00Z","2026-06-08T20:13:09.960053Z","2026-08-19T02:08:40.142862Z",true,"agent",271,[34,43],{"slug":35,"tag_slug":35,"title_zh":36,"title_en":37,"intro_zh":38,"intro_en":39,"id":40,"is_active":30,"created_at":41,"modified_at":42},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":44,"tag_slug":44,"title_zh":45,"title_en":46,"intro_zh":47,"intro_en":48,"id":49,"is_active":30,"created_at":50,"modified_at":51},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":53},[54,59,64,69,74,79],{"id":55,"title":56,"news_slug":57,"published_at":58},"c542a40b-0b45-4184-9851-9134c951ae52","网站集体拉黑 AI 智能体:Agent 互联网撞上第一堵墙","websites-blocking-ai-agents","2026-10-19T13:10:00+00:00",{"id":60,"title":61,"news_slug":62,"published_at":63},"50687317-89b7-4857-ad66-86e2e251ff9d","阿里开源 OpenGCUA：8 个前沿模型电脑操控平均涨 19.6 分","opengcua-open-computer-use-stack","2026-10-18T13:10:17+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"c368ad9f-9308-4a0b-8f5c-3ae4601b48b9","D2K-Bench: 专家设计把 LLM 写 GPU 核提速 33.9%","d2k-bench-llm-gpu-kernel-design-guidance","2026-10-07T03:00:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"237d0bac-204c-4818-9262-e576f96df623","Agent 被自己的历史拖累:人大 AEWM 编辑任务状态,六项基准最高涨 6.7 分","agent-editing-world-model","2026-09-29T17:08:51+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"fe5546f3-09e4-42a3-bfde-6bbd0e8d474c","外星世界实测:探索 4 轮 87.6%,垫底 12.9%","explorationbench-alien-worlds","2026-09-28T21:07:30+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"dcd8b3e1-a3c7-4614-aba4-9002219ea5f6","LibreDB Studio 0.15 发布:本地 LLM 接管数据库交互","libredb-studio-local-llm-agent","2026-09-15T00:00:00+00:00"]