scholar-deep-research

这段内容是审核时保存的快照。外部来源才是完整且最新的版本。

---
name: scholar-deep-research
description: Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires academic grounding (e.g. "what's known about X", "compare approach A vs B in the literature", "summarize the field of Y"). Runs an 8-phase (Phase 0..7), script-driven research workflow across 7 federated sources (OpenAlex, arXiv, Crossref, PubMed, DBLP, bioRxiv, Exa) with optional Semantic Scholar / Brave MCP enrichment, with deduplication, transparent ranking, dual-backend citation chasing (OpenAlex + Semantic Scholar), self-critique, and structured report output with verifiable citations.
license: MIT
homepage: https://github.com/Agents365-ai/scholar-deep-research
compatibility: Requires Python 3.9+ with httpx and pypdf (see requirements.txt). Optional: `pip install docling` to enable layout-aware markdown PDF extraction (`extract_pdf.py --engine docling`); auto-used as a fallback for scanned/sparse PDFs. Works offline-first (no MCP required) but enriches with Semantic Scholar / Brave MCP tools when available.
platforms: [macos, linux, windows]
metadata: {"openclaw":{"requires":{"bins":["python3"]},"emoji":"🔬"},"hermes":{"tags":["research","literature-review","academic","papers","citations","survey"],"category":"research"},"pimo":{"tags":["research","literature-review","academic"],"category":"research"},"author":"Agents365-ai","version":"0.17.0"}
---

# Scholar Deep Research

End-to-end academic research workflow that turns a question into a cited, structured report. Built for depth: multi-source federation, transparent ranking, citation chasing, and a mandatory self-critique pass before the report ships.

## When to use

**Explicit triggers:** "literature review", "research report", "state of the art", "survey the field", "what's known about X", "deep research on Y", "systematic review", "scoping review", "compare papers on Z".

**Proactive triggers (use without being asked):**
- User asks a factual question whose honest answer is "it depends on the literature"
- User frames a research plan and needs the background section
- User is drafting a paper intro/related-work and hasn't yet scoped prior work
- User proposes a method and asks whether it's novel

**Do not use when:** a single known paper answers the question, the user wants a tutorial (not a survey), or they're debugging code.

## Guiding principles

1. **Scripts over vibes.** Every search, dedupe, rank, and export step runs through a script in `scripts/`. The same input should produce the same output. Do not improvise ranking or counting by eye.
2. **Sources are federated, not singular.** OpenAlex is the primary backbone (free, 240M+ works, no key). arXiv (CS/ML/physics preprints), Crossref (DOI metadata), PubMed (biomedical), DBLP (CS conferences/journals), bioRxiv (life-sci preprints via Europe PMC), and Exa (open-web, requires `EXA_API_KEY`) fill gaps. Semantic Scholar is also script-driven — `build_citation_graph.py --source s2|both` is the spine path for Phase 4, with better CS / arXiv / cross-disciplinary coverage than OpenAlex; the two graphs disagree more than you'd expect. The asta MCP tools (`mcp__asta__*`) and Brave Search are *skin* — used opportunistically for relevance ranking or non-academic context, never on the critical path. If MCP times out, research continues.
3. **State is persistent.** Everything goes through `research_state.json`. Queries ran, papers seen, decisions made, phase progress. Research becomes resumable and auditable.
4. **Citations are anchors, not decorations.** Every non-trivial claim in the draft carries `[^id]` where `id` matches a paper in state. Unanchored claims are treated as hallucinations and fail the gate.
5. **Saturation, not exhaustion, is the stop signal.** A