[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-tool-calling":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"5c0c1205-0e79-40c5-b6ab-4b53460b5d4f","tool calling","tool-calling",4,"Tool calling 指的是讓 LLM 依照結構化介面呼叫 API、查資料庫、觸發工作流或執行外部函式，是 agent 與生產系統接軌的核心。這個主題也涵蓋 JSON 合約、錯誤處理、迴圈控制與評估。","Tool calling is the mechanism that lets an LLM invoke APIs, query databases, trigger workflows, or run external functions through structured contracts. It sits at the center of agent systems, where JSON schemas, error handling, loop control, and evaluation shape reliability.",[12,21,29,37,44,52],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"13519d21-7023-407c-8974-7c633ebede9f","why-open-source-llms-should-be-judged-by-workload-not-hype-en","Why Open-Source LLMs Must Be Judged by Workload, Not Hype","Open-source LLMs in 2026 should be chosen by workload fit, not benchmark hype.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778095240831-b3wm.png","en","2026-05-06T19:20:22.800006+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"0a138d69-f477-4669-80e5-6dd87e24553f","microsoft-agent-framework-building-blocks-dotnet-part-3-en","Microsoft Agent Framework Adds Agent Building Blocks in .NET","Microsoft's Agent Framework adds agents, tools, sessions, memory, and workflows to .NET on top of MEAI and VectorData.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778059262925-7sqi.png","2026-05-06T09:20:35.862842+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":34,"image_url":35,"cover_image":35,"language":19,"created_at":36},"b5821216-6735-4554-bc10-6816c7e245cc","kimi-k26-256k-context-api-en","Kimi K2.6 Brings 256K Context to API Users","Kimi K2.6 adds 256K context, multimodal input, and stronger coding for developers using the Kimi API Platform.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777903860599-o5fz.png","2026-05-04T14:10:39.672693+00:00",{"id":38,"slug":39,"title":40,"summary":41,"category":26,"image_url":42,"cover_image":42,"language":19,"created_at":43},"574953d9-dafe-4fd3-b4da-133f2ed9f2c9","hermes-agent-agent-harness-framework-en","Hermes Agent: The Agent Harness Framework to Watch","Hermes Agent aims to make agent testing and orchestration easier, with tool use, evals, and workflow control in one stack.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775207577974-56eu.png","2026-04-03T09:12:33.141965+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":49,"image_url":50,"cover_image":50,"language":19,"created_at":51},"3f8ce806-cc89-41ac-aae7-83ed9afd34b7","what-agentic-workflows-actually-do-enterprise-ai-en","What Agentic Workflows Actually Do in Enterprise AI","Agentic workflows let AI agents plan, act, and adapt with little human input, changing how teams handle support, ops, and data work.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775149805983-zsy9.png","2026-04-02T17:09:38.973748+00:00",{"id":53,"slug":54,"title":55,"summary":56,"category":26,"image_url":57,"cover_image":57,"language":19,"created_at":58},"9afcaae9-1e3d-47c1-8cca-08a2a4cb3185","what-ai-agents-are-how-they-work-en","What AI Agents Are and How They Work","AI agents combine LLMs, memory, tools, and planning. IBM says they can call APIs, search data, and coordinate tasks autonomously.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775200012337-2kcd.png","2026-04-02T05:42:30.056009+00:00"]