Survey Generation

by lingzhi2279e6c085d65e3No license386 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 7 months ago

Generate complete academic survey papers using multi-LLM parallel outline generation, RAG-based subsection writing, citation validation, and local coherence enhancement. Based on AutoSurvey pipeline. Use for writing comprehensive literature surveys.

AI-generated overview

Generates complete academic survey papers with multi-LLM outlines, RAG-based writing, citation validation and BibTeX output.

What it does
This skill guides an agent through producing a full academic literature survey on a given topic. It collects 50-200 papers from Semantic Scholar or arXiv, builds a merged outline through parallel outline generation, writes subsections with retrieved sources and inline citations, validates citations with NLI-based faithfulness checks, improves local coherence, and converts citations to BibTeX. It outputs a survey folder containing main.tex, references.bib, outline.json and individual section files.
When to use it
Use it when you need a comprehensive, citation-backed literature survey written from scratch on a research topic. It suits academic writing tasks where a structured outline, verified references and a LaTeX manuscript are expected.
Requirements
Requires an agent runtime able to run Python scripts and network access to Semantic Scholar or arXiv; the workflow references a search script at ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py and prompt templates at references/survey-prompts.md. The skill itself ships no scripts, only instructions and a reference file.

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, literature-search, literature-review
  • See also: related-work-writing

Source and attribution

Source:lingzhi227/agent-research-skillsinskills/survey-generationat commit9e6c085

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal