EZ_math_model

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".

Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the related work", or "build the bibliography".

Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper structure".

Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper from my experiments", "turn this idea and these results into a paper", "generate a conference submission", "run paper-orchestra on X", or otherwise wants the end-to-end paper-writing pipeline. Coordinates the outline-agent, plotting-agent, literature-review-agent, section-writing-agent, and content-refinement-agent skills.

Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.

Use when EZ_math_model needs to convert paper.md to paper.docx, read a DOCX problem statement, preserve equations and tables, or package a modeling report as a Word document.

Use after EZ_math_model writer creates paper.md and before quality audit when a long modeling paper needs less AI-like prose while preserving formulas, data, citations, tables, and figures.

EZMM writer-stage adapter for the vendored PaperOrchestra skill pack. Use by default during pipeline/04-paper-writing for outline-first paper drafting, literature-review planning, section writing, and refinement discipline. The adapter maps EZMM runtime artifacts to PaperOrchestra-style inputs, runs PaperOrchestra-first writing automatically, and returns EZMM-compatible paper.md.

Use when EZ_math_model needs to read or convert PDF problem statements, extract text or tables from PDF attachments, summarize reference papers, or fall back when MinerU is unavailable.

Use before EZ_math_model declares quality_audit, packaging, or final delivery complete, especially when pass/fail claims must be backed by files, commands, counts, or concrete evidence.

Use when EZ_math_model model selection is unclear after the modeling decision tree, the problem spans multiple domains, or modeler needs several candidate approaches before writing modeling_plan.md.

公开数据集发现入口。覆盖 Kaggle / UCI / HuggingFace / 天池。题目要求"自行 查找数据"或"补充外部数据"时启用；附件已含数据时**不调用**。

Use when EZ_math_model runs in multi or hybrid mode and has two or more independent subtasks that can be assigned to subagents without shared files, shared state, or dataflow dependencies.

Use when EZ_math_model multi or hybrid mode needs several domain-specialist subagents to gather outside knowledge, industry context, model theory, or sensitivity-analysis references in parallel.

PDF / 图片 / 网页高质量解析为 Markdown。三种部署形态全部免费：本地 CLI（开源）、 云 API（注册免费 token + 配额，超额才付费）、网页 flash（零注册，单文件 ≤10MB / ≤20页）。 在中文学术 PDF / 表格 / 公式上识别质量显著高于 pdfplumber。

论文检索子 skill。通过 OpenAlex API（默认）、arXiv、Semantic Scholar、CrossRef 四个免费源聚合搜索学术文献，返回结构化论文元信息（含 DOI / 摘要 / 引用数）。 默认零配置；可选 EZMM_OPENALEX_EMAIL / EZMM_S2_API_KEY 提升配额。

scholar 是 paper-search 的别名 / 软链。统一从这里入口可在内部代码中用更短的 命名空间。本子 skill 的实际实现指向 tools/paper_search/。

Use when the user explicitly asks EZ_math_model to create defense slides, academic presentation slides, Beamer slides, or PPT after the modeling paper has been packaged.

Use after EZ_math_model coding has produced src/*.py and before packaging when code quality, reuse, vectorization, naming, or unnecessary complexity should be reviewed without changing behavior.

Use when developing or extending EZ_math_model itself from a written implementation plan, especially adding algorithms, tool skills, templates, or multi-step repo changes.

Use when EZ_math_model coder or packaging fails repeatedly with the same error and needs root-cause analysis instead of another blind retry.

Use near the end of EZ_math_model intake when external/user-corpus contains user-provided papers, notes, PDFs, datasets, or examples that should become a local AGENTS.md reference index.

网页抓取与开放检索。Jina Reader（免费零配置）+ Firecrawl + Tavily + Exa + SerpAPI。题目背景涉及行业 / 政策 / 经济时启用；纯数学 / 物理机理题不启用。

Use when EZ_math_model needs to read, preview, clean, write, or summarize CSV, XLS, or XLSX attachments and result tables for modeling tasks.