Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
Search topic or paper ID: $ARGUMENTS
DeepXiv is the progressive-reading literature source:
| Skill | Best for |
|---|---|
/arxiv | Direct preprint search and PDF download |
/deepxiv | Layered reading: search → brief → head → section |
Use DeepXiv when you want to inspect papers incrementally instead of loading the full text immediately.
tools/deepxiv_fetch.py relative to the current project. If unavailable, fall back to the raw deepxiv CLI.Overrides (append to arguments):
/deepxiv "agent memory" - max: 5/deepxiv "2409.05591" - brief/deepxiv "2409.05591" - head/deepxiv "2409.05591" - section: Introduction/deepxiv "trending" - days: 14 - max: 10/deepxiv "karpathy" - web/deepxiv "258001" - scDeepXiv is optional:
pip install deepxiv-sdk
On first use, deepxiv auto-registers a free token and stores it in ~/.env.
Parse $ARGUMENTS for:
- max: N- brief- head- section: NAME- trending- days: 7|14|30- web- scIf the input looks like an arXiv ID and no explicit mode is provided, default to brief.
python3 tools/deepxiv_fetch.py --help
If the adapter is unavailable, fall back to raw deepxiv commands.
python3 tools/deepxiv_fetch.py search "QUERY" --max MAX_RESULTS
python3 tools/deepxiv_fetch.py paper-brief ARXIV_ID
python3 tools/deepxiv_fetch.py paper-head ARXIV_ID
python3 tools/deepxiv_fetch.py paper-section ARXIV_ID "SECTION_NAME"
python3 tools/deepxiv_fetch.py trending --days 7 --max MAX_RESULTS
python3 tools/deepxiv_fetch.py wsearch "QUERY"
python3 tools/deepxiv_fetch.py sc "SEMANTIC_SCHOLAR_ID"
Fallbacks:
deepxiv search "QUERY" --limit MAX_RESULTS --format json
deepxiv paper ARXIV_ID --brief --format json
deepxiv paper ARXIV_ID --head --format json
deepxiv paper ARXIV_ID --section "SECTION_NAME" --format json
deepxiv trending --days 7 --limit MAX_RESULTS --output json
deepxiv wsearch "QUERY" --output json
deepxiv sc "SEMANTIC_SCHOLAR_ID" --output json
For search results, present a compact literature table. For paper reads, summarize the title, authors, date, TLDR, and the next recommended depth step.
Use the progression:
searchpaper-briefpaper-headpaper-sectionOnly read the full paper when the user explicitly needs it.
deepxiv commands when available./arxiv or /research-lit "topic" - sources: web.