调查生成
- 作者仓库星标 90
- 作者仓库 agent-research-skills
- 领域
- 写作
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @lingzhi227 · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- Python
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
survey/
├── main.tex # Complete survey paper
├── references.bib # All citations
├── outline.json # Survey outline
└── sections/ # Individual section files
第一步:收集论文
搜索 Semantic Scholar / arXiv 查找有关该主题的论文 收集 50-200 篇带有标题和摘要的相关论文 按相关性和引用计数过滤
第2步:生成大纲(多LLM并行)
独立(并行)生成 N 个粗略大纲 将大纲合并为一个综合大纲 将每个部分展开为小节 编辑最终大纲以删除冗余
第 3 步:编写小节(基于 RAG)
对于每个小节: 检索该小节主题的相关论文 生成带内联引用的内容 `[paper_title]` 强制每个小节的最小字数 仅引用所提供列表中的论文
第 4 步:验证引文
对于每个小节: 检查引用的论文标题是否正确 验证引用是否支持所提出的主张 删除或更正不受支持的引用 使用 NLI(自然语言推理)确保声明来源的真实性
第五步:增强地方一致性
对于每个小节: 阅读前面和后面的小节 优化过渡和流程 保留核心内容和引文 确保流畅的阅读体验
第 6 步:将引文转换为 BibTeX
将 `[paper_title]` 替换为 `\cite{key}` 为所有引用的论文生成 BibTeX 条目 验证 .bib 文件中存在的所有引文键
# Survey Generation
Generate complete academic survey papers with structured outline, RAG-based writing, and citation validation.
## Input
- `$0` — Survey topic or research area
## Scripts
### Literature search
```bash
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
--query "relevant search query" --max-results 50
```
## References
- Survey prompts (outline, writing, citation, coherence): `~/.claude/skills/survey-generation/references/survey-prompts.md`
## Workflow (from AutoSurvey)
### Step 1: Collect Papers
1. Search Semantic Scholar / arXiv for papers on the topic
2. Collect 50-200 relevant papers with titles and abstracts
3. Filter by relevance and citation count
### Step 2: Generate Outline (Multi-LLM Parallel)
1. Generate N rough outlines independently (parallel)
2. Merge outlines into a single comprehensive outline
3. Expand each section into subsections
4. Edit final outline to remove redundancies
### Step 3: Write Subsections (RAG-Based)
For each subsection:
1. Retrieve relevant papers for the subsection topic
2. Generate content with inline citations `[paper_title]`
3. Enforce minimum word count per subsection
4. Only cite papers from the provided list
### Step 4: Validate Citations
For each subsection:
1. Check that cited paper titles are correct
2. Verify citations support the claims made
3. Remove or correct unsupported citations
4. Use NLI (Natural Language Inference) for claim-source faithfulness
### Step 5: Enhance Local Coherence
For each subsection:
1. Read previous and following subsections
2. Refine transitions and flow
3. Preserve core content and citations
4. Ensure smooth reading experience
### Step 6: Convert Citations to BibTeX
1. Replace `[paper_title]` with `\cite{key}`
2. Generate BibTeX entries for all cited papers
3. Validate all citation keys exist in .bib file
## Output Structure
```
survey/
├── main.tex # Complete survey paper
├── references.bib # All citations
├── outline.json # Survey outline
└── sections/ # Individual section files
```
## Rules
- Only cite papers from the collected paper list — never hallucinate citations
- Each subsection must meet minimum word count
- No duplicate subsections across sections
- Citation validation is mandatory before final output
- Local coherence enhancement must preserve all citations
- The survey should be comprehensive and logically organized
## Related Skills
- Upstream: [deep-research](../deep-research/), [literature-search](../literature-search/), [literature-review](../literature-review/)
- See also: [related-work-writing](../related-work-writing/)
章节与文件索引
按说明文件中的顺序排列。
输入
参考文献
第一步:收集论文
第2步:生成大纲(多LLM并行)
第 3 步:编写小节(基于 RAG)
文件/命令 -> ~/.claude/skills/survey-generation/references/survey-prompts.md · [paper_title] · \cite{key} · .claude/skills/deep-research/scripts/search_semantic_scholar.py · .claude/skills/survey-generation/references/survey-prompts.md · outline.js · ../deep-research · ../literature-search
内容校验值 -> 66a169fa69cc
当前原文的自动摘译,尚未人工审校。
输入
$0— 调查主题或研究领域参考文献
调查提示(大纲、写作、引用、连贯性):
~/.claude/skills/survey-generation/references/survey-prompts.md