paper-discovery-sources

Multi-source paper discovery is consolidated by integrating local vec-db top-venue search, Semantic Scholar breadth search, and AlphaXiv full-text reading into a single reference framework for researchers and AI agents.

Use local vec-db for top-venue search and Semantic Scholar for breadth search across broader literature. AlphaXiv is used specifically for full-text reading within this unified multi-source strategy.

Yes, AlphaXiv full-text reading is integrated as part of a unified strategy designed to provide a stable integration point for AI agents and researchers building paper discovery workflows.

The best way is to reference a unified strategy framework that combines local vec-db, Semantic Scholar, and AlphaXiv, providing clear integration points and usage guidance for consistent results.

Yes, it serves as a centralized reference for other skills including research-survey, gap-to-method, paper_related_works, idea_refinery, and topic_survey workflows to ensure consistent multi-source results.

A unified reference framework ensures consistent multi-source results by standardizing how local vec-db, Semantic Scholar, and AlphaXiv are queried together, preventing fragmented or redundant paper discovery.