[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-palmclaw-on-device-agent":3,"news-related-af056e63-5622-48ae-8629-5226aed64767":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"af056e63-5622-48ae-8629-5226aed64767","PalmClaw 把端侧 Agent 拉进「原生」时代:94.9% 完成时间压缩 + 11.5% 成功率提升","PalmClaw 框架由 ModalityDance 开源(GitHub 1.1k star),7月14日提交 arXiv(2607.13027)。把手机传感器、应用数据、设备能力抽象为带显式入参与边界的 device tool,让端侧 LLM Agent 摆脱 GUI 长链点击。对比最强 baseline 实现 11.5% 任务成功率提升与 94.9% 完成时间压缩,为端侧 Agent 工程化提供可复现的开源底盘。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.13027","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"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",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"9c7087ec-359a-473a-b069-e39e712ac70b","en","PalmClaw: native on-device agents, 94.9% less completion time","The PalmClaw framework, open-sourced by ModalityDance (GitHub 1.1k stars), was submitted to arXiv (2607.13027) on July 14. It abstracts phone sensors, app data, and device capabilities as device tools with explicit inputs and boundaries, freeing on-device LLM Agents from long chains of GUI clicks. Against the strongest baseline, it achieves an 11.5% task-success-rate improvement and 94.9% completion-time compression, providing a reproducible open-source chassis for on-device Agent engineering.","palmclaw-on-device-agent","2026-07-15T20:10:00Z","2026-07-15T20:11:08.066215Z","2026-08-19T02:08:40.142862Z",true,"agent",101,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"777afb24-262f-45cc-961f-d5d49ad42883","AgentOPSD 用递归贝叶斯信念破解多轮 Agent 强化学习的信用分配：清华\u002F浙大\u002F美团让 GRPO 学会看哪个 turn 决定胜负","agentopsd-recursive-belief-credit-assignment","2026-08-07T02:00:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"3ebeac99-ddd6-432d-a97f-aab8ec609baa","OPID 把\"已完成轨迹\"变成训练信号：Agentic RL 第一次有了\"事后诸葛亮\"式的密集监督","opid-agentic-rl-hindsight-skill","2026-06-27T20:10:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"98f60b3b-5001-4df9-bd5a-a661b1575724","OpenEnv 升格为多机构共治：HF、NVIDIA、Meta 等 9 家共建 agentic RL 的「通用插座」","openenv-hf-nvidia-meta-9-socket","2026-06-14T16:00:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"f26ace13-9c96-47ea-a528-b6682a22aa1e","Apodex 1.1 把推理搬进真实执行:PIVOT-RL 定位关键决策点,35B mini 开源","apodex-1-1-agentic-execution-pivot-rl","2026-08-25T14:30:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"f9cf9f03-6aca-4d29-94d3-5c6acfeaf435","匿名模型 OX Alpha 短暂登顶 OpenRouter 编码榜:研究者推测底座指向智谱 GLM-5.x","ox-alpha-stealth-openrouter-glm-5-zhipu","2026-08-24T03:00:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"e8965513-b56f-475b-b15f-22a5ea2d2a4e","Agent 取代人成为 HF Hub 一号用户:Claude Code 占 44.4%,还有一次 4.5 天未察觉的入侵","hf-hub-agent-user-claude-code-4-5-day-intrusion","2026-08-21T08:00:00+00:00"]