Yang Ruofeng

Check paper numbers, comparisons, and evaluation scope against raw experiment results. A fresh reviewer from a different model family examines only source evidence, then produces reports identifying rounding issues, inconsistent settings, aggregation errors, and unsupported claims.

中文简介正在准备中。当前显示英语简介。

• Verify paper numbers against raw results before submission
• Recalculate claimed percentage improvements
• Check run counts and experimental settings behind comparisons

Compare machine learning experiment results from JSON or CSV files. Calculate improvements over a baseline, summarize variation across repeated runs, identify trends and unusual results, and suggest experiments to test possible explanations.

中文简介正在准备中。当前显示英语简介。

• Compare model performance across experimental conditions
• Check variation across runs with different random seeds
• Identify trends as a parameter changes

Search open-access academic papers through DeepXiv, then move from brief summaries to section outlines and individual sections. Find trending papers and focus reading on the parts needed to answer a research question.

中文简介正在准备中。当前显示英语简介。

• Find papers on a research topic
• Read only a paper's Introduction section
• Explore papers trending over the past two weeks

Turn a rough invention idea into a structured disclosure for patent preparation. Organize the technical problem, mechanism, and benefits, distinguish essential and optional features, and plan claims—the scope of protection sought—and supporting drawings.

中文简介正在准备中。当前显示英语简介。

• Turning a rough invention idea into a disclosure
• Separating core features from supporting features
• Planning claim dependencies and supporting drawings

Checks a research idea against recent literature, comparing its main claims with the closest published work. Produces a structured report explaining overlap, meaningful differences, risks, and whether to proceed, proceed cautiously, or abandon the idea.

中文简介正在准备中。当前显示英语简介。

• Checking an idea before starting implementation
• Comparing a proposed method with prior work
• Clarifying the novelty of an experimental setting

Apply staged improvements to skill files after explicit user selection and a fresh review by a different model family. Each applied change includes a backup, review records, and provenance details for later inspection.

中文简介正在准备中。当前显示英语简介。

• Apply selected patches after reviewing an optimization report
• Require a fresh model review before changing skill files
• Keep backups and review records for skill updates

Format existing patent claims, descriptions, and abstracts for China, the United States, or Europe. Produce jurisdiction-specific document sets in Markdown or Word, checking numbering, reference signs, language, and abstract length without changing technical claim content.

中文简介正在准备中。当前显示英语简介。

• Formatting existing patent drafts for CN, US, or EP
• Generating all three jurisdiction formats together
• Preparing Word documents from patent draft sections

Turn a research proposal into an experiment plan tied to specific paper claims. Define comparisons, evaluation measures, tests that remove individual components, run order, and compute estimates, with a written plan and tracker for execution.

中文简介正在准备中。当前显示英语简介。

• Turning a research proposal into concrete experiments
• Designing comparisons and component-removal tests
• Prioritizing runs within a compute budget

Check running experiments, collect logs and result metrics, and summarize progress alongside baseline comparisons. It supports SSH servers, Vast.ai, and Modal, with optional Weights & Biases metrics and cost reporting for the supported compute services.

中文简介正在准备中。当前显示英语简介。

• Check whether remote experiments have finished
• Compare collected metrics with the matching baseline
• Investigate NaN values or diverging training runs

Build a PDF from a LaTeX paper, diagnose compilation errors, and repair reference or citation problems. Check the resulting layout, page count, anonymity, and embedded fonts, then report fixes and remaining warnings.

中文简介正在准备中。当前显示英语简介。

• Build a PDF from LaTeX source files
• Fix compilation, reference, and citation errors
• Check figure and table layout

Use Gemini to discover research papers through related problems and alternative terminology. Results are organized into a table with publication details, code links, and short summaries, with filters for year, venue, and available code.

中文简介正在准备中。当前显示英语简介。

• Discover papers beyond an exact keyword match
• Find research papers with open-source code
• Find papers from selected years or venues

Search academic papers by topic, year, citation count, and free availability. Organize abstracts and publication details into a comparison table, and investigate author affiliations, funding sources, and citation links through OpenAlex.

中文简介正在准备中。当前显示英语简介。

• Finding papers on a research topic
• Filtering papers available to read for free
• Checking author affiliations and research funding

Analyze ARIS usage logs to propose evidence-based changes to skill instructions, reviewer prompts, and workflow defaults. Receive a report and focused patch proposals, with selected patches staged for a separate application process.

中文简介正在准备中。当前显示英语简介。

• Investigate recurring workflow failures
• Review defaults that users frequently override
• Identify the current workflow bottleneck

Turn a completed research paper into conference slides tailored to the talk format and duration. Produce a PDF, an editable PowerPoint deck, speaker notes, and a full rehearsal script with anticipated questions.

中文简介正在准备中。当前显示英语简介。

• Preparing slides for a conference oral presentation
• Condensing a paper into a short spotlight talk
• Rehearsing with a timed script and anticipated questions

Turn a research paper into a conference poster using HTML/CSS and figures from the paper. Check claims against evidence, measure the print layout, and produce a PDF matched to the venue’s required dimensions.

中文简介正在准备中。当前显示英语简介。

• Creating a conference poster from a paper
• Redesigning an existing research poster
• Checking poster claims against the original paper

Explore hardware and electronic design configurations by repeatedly running programs, measuring results, and adjusting parameters. Track constraints and every trial, then report the best configuration found within the time and iteration limits.

中文简介正在准备中。当前显示英语简介。

• Tuning cache sizes and processor configuration
• Reducing circuit area while meeting timing constraints
• Comparing compiler flags for runtime or code size

Draft detailed patent embodiments, descriptions of how to make and use an invention. It organizes components, operating steps, conditions, and alternatives, aligns figure reference numbers, and checks that each claim element has supporting text.

中文简介正在准备中。当前显示英语简介。

• Draft detailed embodiments for a patent specification
• Turn a paper's technical setup into an operating description
• Align component reference numbers with patent figures

Create consistent paper figures and comparison tables from experiment data. The skill selects suitable chart types, saves reusable plotting scripts, prepares LaTeX insertion code, and checks rendered figures for readability and comparisons for consistency with the underlying data.

中文简介正在准备中。当前显示英语简介。

• Plot training curves from experiment results
• Create method comparison and ablation tables
• Combine results across datasets into multi-panel figures

Review communications research by searching existing libraries and notes before academic databases. Produce a paper comparison table covering methods, results, and limitations, then summarize major approaches, evidence strength, and remaining research gaps.

中文简介正在准备中。当前显示英语简介。

• Surveying research on wireless and satellite communications
• Finding related work from saved papers and notes
• Comparing assumptions, methods, and limitations across papers

Explore a broad research direction through literature searches, idea generation, novelty checks, small pilot experiments, and critical review. Receive ranked ideas plus a refined proposal and experiment plan for the leading candidate, with evidence recorded across stages.

中文简介正在准备中。当前显示英语简介。

• Finding concrete ideas within a broad research topic
• Exploring improvements to a reference paper
• Comparing promising ideas through small pilot experiments

Draft patent claims from invention disclosures, prior art reports, and novelty assessments. Create broad independent claims and narrower dependent claims, check their support in the specification, and adapt separate claim sets for China, the United States, or Europe.

中文简介正在准备中。当前显示英语简介。

• Drafting claims from an invention disclosure
• Preparing separate claim sets for China, the US, and Europe
• Adding narrower claims as fallback positions

Turn scattered research equations and notes into a structured derivation document. Clarify the target, assumptions, and notation; distinguish exact steps from approximations and interpretations; and report missing conditions or logical gaps when the derivation cannot be supported.

中文简介正在准备中。当前显示英语简介。

• Organize scattered equations into a coherent derivation
• Choose the central quantity for a theory
• Separate exact steps, approximations, and interpretations

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".

中文简介正在准备中。当前显示原文说明。

Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (every accusation tagged to an existing claim_id/finding_id), a defense decomposes it and rules each point against the anchored evidence. MEMO-ONLY: emits adversarial-case-builder.memo.md (fed to the adjudicator via --memo) and carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Honest-null allowed (the paper may survive). Run LAST. Detect-only. Adapted from ARIS kill-argument. Triggers: "adversarial case", "strongest objection", "rejection memo", "kill argument", "最强拒稿点".

中文简介正在准备中。当前显示原文说明。