[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-agents":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"2681658f-3a3d-46c4-b423-550e0bbde828","agents",6,"Agents 指的是能分解任務、呼叫工具、維持狀態並反覆修正的 LLM 工作流，常見於編輯器自動化、資料分析、檔案檢索與結構化輸出。這個主題關係到模型是否能從對話走向可執行系統。","Agents are LLM-driven workflows that can break down tasks, call tools, keep state, and iterate on results. Here you’ll see editor automation, data-viz and file-retrieval benchmarks, plus structured-output patterns that determine whether models can operate as systems, not just chatbots.",[11,20,28,35],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"2834efcd-6c3d-424b-8436-68dbfade265b","ragflow-open-source-rag-agent-engine-en","RAGFlow adds agents to open-source RAG","RAGFlow pairs retrieval-augmented generation with agent features, Docker self-hosting, and support for newer models like GPT-5 and Gemini 3 Pro.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778526659080-t2is.png","en","2026-05-11T19:10:36.388185+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"b7440e79-eff3-4281-b536-c57ee13d7582","dv-world-tests-chart-agents-real-workflows-en","DV-World tests chart agents in real workflows","DV-World benchmarks data-viz agents on spreadsheet, evolution, and intent-alignment tasks that mirror real enterprise workflows.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777442826387-1etr.png","2026-04-29T06:06:46.563367+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":25,"image_url":33,"cover_image":33,"language":18,"created_at":34},"be5dca83-11ca-4d7b-b1b8-ec3eb4005a8c","hippocamp-benchmarks-contextual-agents-personal-computers-en","HippoCamp tests agents on your personal files","HippoCamp benchmarks multimodal agents on dense personal file systems, exposing weak retrieval, grounding, and cross-modal reasoning.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775115017182-8a6y.png","2026-04-02T06:03:26.745712+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":16,"image_url":40,"cover_image":40,"language":18,"created_at":41},"230429a8-0f35-4989-983f-09522be025c0","ai-cookbook-practical-llm-code-for-developers-en","AI Cookbook Packs Practical LLM Code for Developers","Dave Ebbelaar’s AI Cookbook offers 3,887-star Python examples for agents, Anthropic, and OpenAI workflows developers can copy today.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Fcover-1774595866498-425oei.png","2026-03-27T07:17:47.248776+00:00"]