literature-review-agent
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to flag hallucinated citations, build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the relat
npx skills add Ar9av/PaperOrchestra --skill literature-review-agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Literature Review Agent (Step 3) Faithful implementation of the Hybrid Literature Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, §4 Step 3, App. D.3, App. F.1 p.46). **Cost: ~20–30 LLM calls.** This is one of the two longest steps (the other is plotting). Wall-time floor is set by Semantic Scholar's 1 QPS verification limit. ## Inputs - `workspace/outline.json` — specifically `intro_related_work_plan` with the Introduction search directions and the 2-4 Related Work methodology clusters - `workspace/inputs/conference_guidelines.md` — used to derive `cutoff_date` - `workspace/inputs/idea.md`, `workspace/inputs/experimental_log.md` — for framing the Intro and grounding the Related Work positioning ## Outputs - `workspace/citation_pool.json` — verified Semantic Scholar metadata for every paper that survived verification - `workspace/refs.bib` — BibTeX file generated from the verified pool - `workspace/drafts/intro_relwork.tex` — drafted Introduction and Related Work sections, written into the template, with the rest of the template preserved verbatim ## Two-phase pipeline (App. D.3) ``` PHASE 1 — Parallel Candidate Discovery For each search direction in introduction_
- Inputs
- Outputs
- Two-phase pipeline (App. D.3)
- Step-by-step
- 0. Derive cutoffdate
- 1. Phase 1: Parallel Candidate Discovery
- 1.5. Pre-dedup before Phase 2
- 2. Phase 2: Sequential Verification via Semantic Scholar (with cache)
- 3. Dedup and assemble the pool
- 3.5. Cross-index verification (Crossref + OpenAlex)
- 4. Build the BibTeX file
- 5. Draft Introduction + Related Work
- 5b. Append §2 to researchbrief.md
- 6. Verify ≥90% citation coverage
export EXA_API_KEY="your-key-here" # get one at https://dashboard.exa.ai/ python skills/literature-review-agent/scripts/exa_search.py \ python skills/literature-review-agent/scripts/pre_dedup_candidates.py \ python skills/literature-review-agent/scripts/s2_cache.py \ exit 0 + prints JSON → use cached response, skip Step B exit 1 → proceed to Step B python skills/literature-review-agent/scripts/s2_search.py \ If SEMANTIC_SCHOLAR_API_KEY is set the key is forwarded automatically. If not, the public unauthenticated endpoint is used (≤1 QPS, still works). python skills/literature-review-agent/scripts/s2_search.py --check-key
What does the literature-review-agent skill do?
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to flag hallucinated citations, build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the relat
How do I install it?
Run `npx skills add Ar9av/PaperOrchestra --skill literature-review-agent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Ar9av/PaperOrchestra, a repository with 627 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.