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.

DeepXiv Paper Search & Progressive Reading Search topic or paper ID: $ARGUMENTS Role & Positioning DeepXiv is the progressive reading literature source: Skill Source Best for /arxiv arXiv API Batch search, PDF download, metadata /deepxiv DeepXiv SDK Progressive section level reading /semantic scholar S2 API Published venue metadata, citation counts /alphaxiv alphaxiv.org Instant LLM optimized summary of one paper, with LaTeX source fallback Use DeepXiv when you want to avoid loading full papers too early. Constants DEEPXIV FETCHER — canonical name deepxiv fetch.py , resolved per [ shared references/integration contract.md ](../shared references/integration contract.md) §2 (Policy D1 — primary + fallback cascade). If unresolved (canonical chain exhausted), fall back to the raw deepxiv CLI (documented per command below). MAX RESULTS = 10 — Default number of results to return. Overrides (append to arguments): /deepxiv "agent memory" max: 5 — top 5 results /deepxiv "2409.05591" brief — quick paper summary /deepxiv "2409.05591" head — metadata + section overview /deepxiv "2409.05591" section: Introduction — read one section only /deepxiv "trending" days: 14 max: 10 — trending papers /deepxiv "karpathy" web — DeepXiv web search /deepxiv "258001" sc — Semantic Scholar metadata by ID Setup DeepXiv is optional. If the CLI is not installed, tell the user: On first use, deepxiv auto registers a free token and stores it in ~/.env . Workflow Step 1: Parse Arguments Parse $ARGUMENTS for: Query or ID : a paper topic, arXiv ID, or Semantic Scholar ID max: N : override MAX RESULTS brief : fetch paper brief head : fetch metadata and section map section: NAME : fetch one named section trending or query trending : fetch trending papers days: 7 14 30 : trending time window web : run DeepXiv web search sc : fetch Semantic Scholar metadata by ID If the main argument looks like an arXiv ID and no explicit mode is given, default to brief . Step 2: Locate the Adapter Resolve $DEEPXIV FETCHER via the canonical strict safe chain (see [ shared references/integration contract.md ](../shared references/integration contract.md) §2). Policy D1 cascade: the resolved adapter is preferred; if unresolved (canonical chain exhausted), fall back to raw deepxiv CLI commands documented in Step 3. Step 3: Execute the Minimal Command Search papers Fallback: Brief summary Fallback: Section map Fallback: Specific section Fallback: Trending Fallback: Web search Fallback: Semantic Scholar metadata Fallback: Step 4: Present Results When searching, present a compact table: When reading a paper, show: title arXiv ID authors venue/date if available TLDR or abstract summary suggested next step: brief → head → section Step 5: Escalate Depth Only When Needed Use this progression: 1. search 2. paper brief 3. paper head 4. paper section 5. full paper only if necessary Do not jump to full paper reads when a brief or one section answers the question. Step 6: Update Research Wiki (if active) Required when research wiki/ exists in the project ; skip silently otherwise. When the wiki dir exists, resolve $WIKI SCRIPT per the canonical chain at [ shared references/wiki helper resolution.md ](../shared references/wiki helper resolution.md) (Variant B — warn and skip). Ingest papers that were meaningfully read (brief / head / section / full) during this invocation — mere search hits without a depth read do not need ingestion: The helper handles metadata / slug / dedup / page / index / log in one call — do not handwrite papers/<slug .md . See [ shared references/integration contract.md ](../shared references/integration contract.md). Backfill missed ingests with python3 "$WIKI SCRIPT" sync research wiki/ arxiv ids <id1 ,<id2 ,... after resolving $WIKI SCRIPT as above. Key Rules Prefer the adapter script over raw deepxiv commands when available. DeepXiv is optional. If unavailable, give the install command and suggest /arxiv or /research lit "topic" sources: web . Use section level reads to save tokens. Treat DeepXiv as complementary to /arxiv and /semantic scholar , not a replacement. If the result overlaps with a published venue paper from Semantic Scholar, keep the richer venue metadata in the final summary.