Search OpenAlex, Semantic Scholar, and arXiv, then internally merge, dedupe, screen, and rank papers. Returns only final selected papers.

Alias for auto_literature_screen. It keeps raw and deduped candidates internal and returns final selected papers only.

Use Semantic Scholar recommendations for a seed paper, then screen and rank related papers without exposing intermediate tables.

Return server metadata and configured optional API keys.

Export selected final papers to a Zotero user or group library. Intended for results from auto_literature_screen.

Produce heuristic, keyword-based research-idea scaffolding from a topic and selected papers. Ideas are derived from term overlap and research-gap templates, not from a language model, and scores are relative heuristics. Does not run experiments or execute code.

Heuristically review a proposed research idea against selected papers, scoring novelty, feasibility, and literature support from keyword overlap. Scores are relative heuristics, not a language-model judgment.