Search Papers

Step 1: Parse Arguments

Parse $ARGUMENTS:

• Domain: first whitespace-delimited token (e.g. machine_learning)
• Query: text inside the first pair of double quotes, or everything after the domain if no quotes
• --max N: set MAX_RESULTS to N
• --download: set DOWNLOAD_PDF to true

Resolve papers directory:

WORKSPACE="${AUTO_RESEARCH_WORKSPACE:-workspace}"
PAPERS_DIR="$WORKSPACE/DOMAIN/papers"

If $PAPERS_DIR does not exist, stop and print:

❌ Papers directory not found: PAPERS_DIR
Run /init-domain DOMAIN first.

Step 2: Search arXiv

Run an inline Python search (no external dependencies required):

python3 - <<'PYEOF'
import json, sys, urllib.parse, urllib.request, xml.etree.ElementTree as ET

QUERY   = "SEARCH_QUERY"
MAX     = MAX_RESULTS
NS      = "http://www.w3.org/2005/Atom"
q       = urllib.parse.quote(QUERY)
url     = (f"https://export.arxiv.org/api/query"
           f"?search_query=all:{q}&start=0&max_results={MAX}"
           f"&sortBy=relevance&sortOrder=descending")