Research Question

Research Question【免费下载链接】Agent-Skills-for-Context-EngineeringA comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.项目地址: https://gitcode.com/GitHub_Trending/ag/Agent-Skills-for-Context-Engineering{{research_question}}Gathered Findings{{#each findings}}Source {{index}}: {{source}}Date: {{date}}Type: {{type}}{{content}}{{/each}}[prompts/index.md](https://link.gitcode.com/i/3af6d90f2677abdd1a615951a6a99a2d) 说明了该类模板的变量语法约定 markdown {{variable}} # 简单替换 {{#if condition}}...{{/if}} # 条件区块 {{#each array}}...{{/each}} # 迭代这里{{research_question}}是简单替换{{#each findings}}...{{/each}}是对 findings 数组的迭代其中{{index}}输出从 0 开始的序号{{source}}、{{date}}、{{type}}、{{content}}为数组元素的字段。将每条来源包裹在content标签内是为了让模型清晰区分外部素材与待生成内容降低把来源文本误当成自己输出的风险。2.4 变量契约模板的输入变量契约如下原文档变量表变量描述必填research_question被研究的问题是findings调研发现数组是findings.source来源名称/URL是findings.date发布日期是findings.type来源类型article、paper 等是findings.content抽取的内容是这组字段与上游工具的输出结构天然匹配webSearch返回title/url/snippet/source/publishedDate/relevanceScore见 web-search.mdreadUrl返回含metadata.author/publishedDate/lastModified与content.sections的结构化文本见 read-url.md。因此findings.source可直接取webSearch结果的source域名或urlfindings.date取publishedDatefindings.type对应contentTypearticle/documentation/paper/code。从代码结构可以推断synthesize工具正是负责把上游结果组装成符合该变量契约的输入对象。三、七段式输出结构从摘要到可操作洞见模板要求模型产出的综合报告包含七个固定小节每一节都有明确的写作指令3.1 Executive Summary执行摘要23 句话概述核心发现供决策者快速获取结论。3.2 Key Themes关键主题归纳跨来源浮现的主要主题。最佳实践第 1 条要求模式识别需基于 3 个以上来源Look for patterns across 3 sources避免单来源偶发信息被放大为主题。3.3 Findings by Topic按主题组织的发现根据研究问题将发现组织为逻辑章节而不是简单按来源罗列——这是综合synthesis区别于汇总summary的关键内容按主题重组而非按来源堆叠。3.4 Areas of Consensus共识领域回答多个来源在哪些点上达成一致。共识通常意味着更高的置信度可作为结论性陈述的基础。3.5 Areas of Disagreement分歧领域记录来源之间冲突或差异之处。这是体现研究诚实度的部分与综合指南中be explicit about uncertainty呼应。3.6 Gaps and Limitations空白与局限指出尚未回答的问题与现有信息的局限。模板明确要求不要夸大来源所支持的内容见 Best Practices 第 4 条。3.7 Actionable Insights可操作洞见给出可实际采用的结论。Best Practices 第 5 条要求以实用要点收尾End with practical takeaways确保研究不只停留在描述层面。3.8 Source Quality Assessment来源质量评估对来源可靠性与相关性做简要评估。该小节与ResearchConfig.includeSourceQuality配置项对应——在 research-agent.md 中该配置默认值为true意味着默认输出包含来源质量评估。四、引用样式三种可配置的标注方式模板提供三种引用样式由ResearchConfig.citationStyle配置项控制默认inline4.1 Inline行内默认Finding or claim [Author/Source, Date]直接嵌在引用内容之后阅读与核验成本最低。4.2 Footnote脚注Finding or claim[1] --- [1] Author/Source, Date, URL适合需要干净正文、详细出处放在文末的正式报告。4.3 Endnote尾注Finding or claim (see Sources: Source Name) ## Sources - Source Name: Full citation以来源名称为键组织文末引用表便于按来源追溯。模板同时要求输出以参考文献区references section收尾保证每个论断都可回溯到具体来源。这与 read-url.md 输出的metadata字段author、publishedDate、source形成数据闭环引用所需的作者与日期信息在读取阶段即被结构化捕获。五、输入输出示例一次完整的综合调用5.1 输入示例原文档给出了可直接套用的 JSON 输入{ research_question: What are the best practices for implementing LLM-as-a-Judge evaluation?, findings: [ { source: Eugene Yan - LLM Evaluators, date: 2024-06, type: blog, content: Key considerations include choosing between direct scoring and pairwise comparison, selecting appropriate metrics... }, { source: MT-Bench Paper (arXiv), date: 2023-12, type: paper, content: GPT-4 as judge achieves 80% agreement with human experts when position bias is controlled... } ] }注意findings.type同时标记了blog与paper这正是按质量加权Best Practices 第 2 条学术来源优先于博客支撑事实性论断的前提——模型需要依据类型判断证据权重。5.2 预期输出结构## Executive Summary LLM-as-a-Judge evaluation has emerged as a scalable alternative to human annotation... ## Key Themes 1. **Scoring Methodology Selection** - Direct scoring for objective criteria - Pairwise comparison for subjective preferences 2. **Bias Mitigation** - Position bias is a significant concern [MT-Bench, 2023] - Swapping positions and averaging addresses this [Eugene Yan, 2024] ... ## References 1. Eugene Yan. Evaluating the Effectiveness of LLM-Evaluators. June 2024. https://eugeneyan.com/... 2. Zheng et al. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. arXiv, December 2023.【免费下载链接】Agent-Skills-for-Context-EngineeringA comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.项目地址: https://gitcode.com/GitHub_Trending/ag/Agent-Skills-for-Context-Engineering创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考