Pesquisa e Web

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says \"知识库\", \"research wiki\", \"add paper\", \"wiki query\", \"查知识库\", or wants to build/query a persistent field map.

Assess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\", \"patentability check\", or wants to evaluate if an invention is patentable.

Verify research idea novelty against recent literature. Use when user says \"查新\", \"novelty check\", \"有没有人做过\", \"check novelty\", or wants to verify a research idea is novel before implementing.

Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.

Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.

Fill in the per-paper TODO sections (Problem/Method/Key Results/Limitations/Reusable Ingredients/...) of research-wiki/papers/<slug>.md pages that /research-lit, /arxiv, /alphaxiv, /deepxiv, /semantic-scholar, /exa-search ingest as bare scaffolds. Implements the Karpathy LLM-wiki principle that the LLM (not the human) writes and maintains wiki bodies. Use when user says 'enrich wiki', 'fill paper

Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".

Write the full patent specification from claims and invention disclosure. Use when user says \"撰写说明书\", \"write specification\", \"写说明书\", \"patent description\", or wants to draft the complete patent specification.

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Cross-model codex review checks math, code, historical citations, and style discipline; then /render-html produces a single-file HTML with academic-newspaper template. Output: docs/tutorials/<slug>_tu

Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with \"auto review loop llm\" or \"llm review\".