deep-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deep Research

深度研究

Create high-fidelity research reports with strict format control, evidence mapping, and multi-pass synthesis.

生成具备严格格式控制、证据映射和多轮合成的高保真研究报告。

Quick Start

快速开始

Clarify the report spec and format contract
Build a research plan and query set
Collect evidence with the deepresearch tool (multi-pass if needed)
Triage sources and build an evidence table
Draft the full report in multiple complete passes (parallel subagents)
UNION merge, enforce format compliance, verify citations
Present draft for human review and iterate

明确报告规格与格式约定
制定研究计划与查询集合
使用deepresearch工具收集证据（必要时进行多轮操作）
筛选来源并构建证据表
通过多轮完整撰写生成报告初稿（并行子代理）
合并内容、强制执行格式合规性、验证引用
提交初稿供人工审核并迭代

Core Workflow

核心工作流

Copy this checklist and track progress:

Deep Research Progress:
- [ ] Step 1: Intake and format contract
- [ ] Step 2: Research plan and query set
- [ ] Step 3: Evidence collection (deepresearch tool)
- [ ] Step 4: Source triage and evidence table
- [ ] Step 5: Outline and section map
- [ ] Step 6: Multi-pass full drafting (parallel subagents)
- [ ] Step 7: UNION merge and format compliance
- [ ] Step 8: Evidence and citation verification
- [ ] Step 9: Present draft for human review and iterate

复制此检查清单并跟踪进度：

Deep Research Progress:
- [ ] Step 1: Intake and format contract
- [ ] Step 2: Research plan and query set
- [ ] Step 3: Evidence collection (deepresearch tool)
- [ ] Step 4: Source triage and evidence table
- [ ] Step 5: Outline and section map
- [ ] Step 6: Multi-pass full drafting (parallel subagents)
- [ ] Step 7: UNION merge and format compliance
- [ ] Step 8: Evidence and citation verification
- [ ] Step 9: Present draft for human review and iterate

Step 1: Intake and Format Contract

步骤1：需求接收与格式约定

Establish the report requirements before any research:

Confirm audience, purpose, scope, time range, and geography
Lock output format: Markdown, DOCX, slides, or user-provided template
Capture required sections and exact formatting rules
Confirm citation style (footnotes, inline, numbered, APA, etc.)
Confirm length targets per section
Ask for any existing style guide or sample report

Create a concise report spec file:

Report Spec:
- Audience:
- Purpose:
- Scope:
- Time Range:
- Geography:
- Required Sections:
- Section Formatting Rules:
- Citation Style:
- Output Format:
- Length Targets:
- Tone:
- Must-Include Sources:
- Must-Exclude Topics:

If a user provides a template or an example report, treat it as a hard constraint and mirror the structure.

在开展任何研究前先确定报告要求：

确认受众、目的、范围、时间范围和地域
锁定输出格式：Markdown、DOCX、幻灯片或用户提供的模板
记录所需章节和精确格式规则
确认引用格式（脚注、内联、编号、APA等）
确认各章节的篇幅目标
询问是否有现有风格指南或示例报告

创建简洁的报告规格文件：

Report Spec:
- Audience:
- Purpose:
- Scope:
- Time Range:
- Geography:
- Required Sections:
- Section Formatting Rules:
- Citation Style:
- Output Format:
- Length Targets:
- Tone:
- Must-Include Sources:
- Must-Exclude Topics:

如果用户提供了模板或示例报告，需将其视为硬性约束，严格镜像其结构。

Step 2: Research Plan and Query Set

步骤2：研究计划与查询集合

Define the research strategy before calling tools:

Break the main question into 3-7 subquestions
Define key entities, keywords, and synonyms
Identify primary sources vs secondary sources
Define disqualifiers (outdated, low quality, opinion-only)
Assemble a query set per section

Use references/research_plan_checklist.md for guidance.

在调用工具前定义研究策略：

将主问题拆解为3-7个子问题
定义关键实体、关键词和同义词
区分一手来源与二手来源
定义排除标准（过时、低质量、仅含观点的内容）
为每个章节组装查询集合

参考references/research_plan_checklist.md获取指导。

Step 3: Evidence Collection (Deepresearch Tool)

步骤3：证据收集（Deepresearch工具）

Use the deepresearch tool to collect evidence and citations.

Run multiple complete passes if coverage is uncertain
Vary query phrasing to reduce blind spots
Preserve raw tool output in files for traceability

File structure (recommended):

<output_dir>/research/<topic-name>/
  deepresearch_pass1.md
  deepresearch_pass2.md
  deepresearch_pass3.md

If deepresearch is unavailable, rely on user-provided sources only and state limitations explicitly.

使用deepresearch工具收集证据和引用。

如果覆盖范围不确定，执行多轮完整操作
变换查询措辞以减少盲区
将原始工具输出保存到文件中以保证可追溯性

推荐文件结构：

<output_dir>/research/<topic-name>/
  deepresearch_pass1.md
  deepresearch_pass2.md
  deepresearch_pass3.md

如果deepresearch不可用，则仅依赖用户提供的来源，并明确说明局限性。

Step 4: Source Triage and Evidence Table

步骤4：来源筛选与证据表

Normalize and score sources before drafting:

De-duplicate sources across passes
Score sources using references/source_quality_rubric.md
Build an evidence table mapping claims to sources

Evidence table minimum columns:

Source ID
Title
Publisher
Date
URL or reference
Quality tier (A/B/C)
Notes

在撰写前对来源进行标准化和评分：

去除多轮操作中的重复来源
使用references/source_quality_rubric.md对来源评分
构建将主张与来源关联的证据表

证据表的最小列数：

来源ID
标题
发布方
日期
URL或参考文献
质量等级（A/B/C）
备注

Step 5: Outline and Section Map

步骤5：大纲与章节映射

Create an outline that enforces the format contract:

Use the template in references/research_report_template.md
Produce a section map with required elements per section
Confirm ordering and headings match the report spec

创建符合格式约定的大纲：

使用references/research_report_template.md中的模板
生成包含各章节必填元素的章节映射
确认章节顺序和标题与报告规格一致

Step 6: Multi-Pass Full Drafting (Parallel Subagents)

步骤6：多轮完整撰写（并行子代理）

Avoid single-pass drafting; generate multiple complete reports, then merge.

避免单轮撰写；生成多份完整报告后再合并。

Preferred Strategy: Parallel Subagents (Complete Draft Each)

首选策略：并行子代理（每份生成完整初稿）

Use the Task tool to spawn parallel subagents with isolated context. Each subagent must:

Load the report spec, outline, and evidence table
Draft the FULL report (all sections)
Enforce formatting rules and citation style

Implementation pattern:

Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version1.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version2.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version3.md

Write drafts to files, not conversation context:

<output_dir>/intermediate/<topic-name>/version1.md
<output_dir>/intermediate/<topic-name>/version2.md
<output_dir>/intermediate/<topic-name>/version3.md

使用Task工具生成带有独立上下文的并行子代理。每个子代理必须：

加载报告规格、大纲和证据表
撰写完整报告（所有章节）
执行格式规则和引用格式

实现模式：

Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version1.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version2.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version3.md

将初稿写入文件，而非对话上下文：

<output_dir>/intermediate/<topic-name>/version1.md
<output_dir>/intermediate/<topic-name>/version2.md
<output_dir>/intermediate/<topic-name>/version3.md

Step 7: UNION Merge and Format Compliance

步骤7：合并与格式合规性

Merge using UNION, never remove content without evidence-based justification:

Keep all unique findings from all versions
Consolidate duplicates while preserving the most detailed phrasing
Ensure every claim in the merged draft has a cited source
Enforce the exact section order, headings, and formatting
Re-run formatting rules from references/formatting_rules.md

使用合并策略，除非有基于证据的理由，否则不得删除任何内容：

保留所有版本中的独特发现
合并重复内容时保留最详细的表述
确保合并后的初稿中每个主张都有对应的引用来源
执行精确的章节顺序、标题和格式
重新执行references/formatting_rules.md中的格式规则

Step 8: Evidence and Citation Verification

步骤8：证据与引用验证

Verify traceability:

Every numeric claim has at least one source
Every recommendation references supporting evidence
No orphan claims without citations
Dates and time ranges are consistent
Conflicts are explicitly called out with both sources

Use references/completeness_review_checklist.md.

验证可追溯性：

每个数值主张至少有一个来源支持
每个建议都引用了支撑证据
不存在无引用的孤立主张
日期和时间范围保持一致
明确指出存在冲突的内容并附上双方来源

使用references/completeness_review_checklist.md。

Step 9: Present Draft for Human Review and Iterate

步骤9：提交初稿供人工审核并迭代

Present the draft as a reviewable version:

Emphasize that format compliance and factual accuracy need human review
Accept edits to format, structure, and scope
If the user provides another AI output, cross-compare and UNION merge

提交可审核的初稿版本：

强调格式合规性和事实准确性需要人工审核
接受对格式、结构和范围的修改
如果用户提供了其他AI输出，进行交叉对比并合并

Output Requirements

输出要求

Match the requested language and tone
Preserve technical terms in English
Respect the report spec and formatting rules
Include a references section or bibliography

匹配请求的语言和语气
保留英文技术术语
遵守报告规格和格式规则
包含参考文献部分或书目

Reference Files

参考文件

File	When to Load
research_report_template.md	Build outline and draft structure
formatting_rules.md	Enforce section formatting and citation rules
source_quality_rubric.md	Score and triage sources
research_plan_checklist.md	Build research plan and query set
completeness_review_checklist.md	Review for coverage, citations, and compliance

文件	使用场景
research_report_template.md	构建大纲和初稿结构
formatting_rules.md	执行章节格式和引用规则
source_quality_rubric.md	对来源进行评分和筛选
research_plan_checklist.md	制定研究计划和查询集合
completeness_review_checklist.md	检查覆盖范围、引用和合规性

Anti-Patterns

反模式

Single-pass drafting without parallel complete passes
Splitting passes by section instead of full report drafts
Ignoring the format contract or user template
Claims without citations or evidence table mapping
Mixing conflicting dates without calling out discrepancies
Copying external AI output without verification
Deleting intermediate drafts or raw research outputs

未使用并行完整撰写的单轮撰写
按章节拆分撰写而非生成完整报告初稿
忽略格式约定或用户模板
无引用或未关联证据表的主张
混合冲突日期但未指出差异
直接复制外部AI输出而未验证
删除中间初稿或原始研究输出