alphaXiv

Returns raw filtered page content from one PDF as XML (<paper id="..."><page num="N">...</page>...</paper>). To read multiple papers, issue multiple tool calls in parallel. Construct citations directly from the returned <page> text. Multiple queries on the same paper are nearly free — batch every question you have for that paper into one call. Supports arXiv, alphaXiv, and Semantic Scholar abstract pages.

Get the content of an arXiv/alphaXiv paper as text. By default returns a structured AI-generated intermediate report (optimized for LLM consumption). If no report is available, automatically falls back to the full extracted text. Use the fullText option to skip the report and get the raw extracted text directly.

Reads the contents of a file or directory from the paper's codebase repository. Special behaviors: 1. When path is '/', returns repository structure and the contents of top-level files. Large repositories may be limited to top-level entries. 2. When path points to a directory, returns a list of files and directories, with contents of readable files fetched in parallel. Omitted files include a reason and raw URL when available. 3. When path points to a file, returns its contents. Binary files are rejected with a raw URL; PDFs should be queried with answer_pdf_queries.

Discovers and ranks multiple candidate papers for a research topic. Use this for literature discovery, related work, or broad topical coverage. Do not use it when the task is to locate one known paper/entity; use `lookup_paper` first for that.