DISCOVER THE FUTURE OF AI AGENTSarrow_forward

ARIS — Auto-Research-In-Sleep

calendar_todayAdded Apr 24, 2026
categoryAgent & Tooling
codeOpen Source
PythonWorkflow Automation大语言模型Multi-Agent SystemAI AgentsMachine LearningAgent FrameworkCLIAgent & ToolingModel & Inference FrameworkAutomation, Workflow & RPAEducation & Research Resources

A zero-dependency, Markdown-native autonomous ML research workflow system covering the full research lifecycle from idea discovery to rebuttal via cross-model adversarial collaboration.

ARIS decomposes the research process into 4 major workflows (Idea Discovery → Experiment Bridge → Auto Review Loop → Paper Writing) plus a standalone Rebuttal skill, each defined as pure Markdown readable by any LLM. The core mechanism employs cross-model adversarial collaboration—Claude Code executes experiments and writing while external models like GPT-5.4 independently review, receiving only file paths to prevent information contamination. A four-layer Evidence & Claim assurance stack (experiment-audit → result-to-claim → paper-claim-audit → citation-audit) and Assurance Gate enforce mandatory audits under --effort: beast mode with non-zero exit codes blocking final reports.

Research Pipeline#

WorkflowCommandInput → Output
W1 — Idea Discovery/idea-discoveryResearch direction → Idea report + Experiment plan
W1.5 — Experiment Bridge/experiment-bridgeExperiment plan → Runnable code + Experiment log
W2 — Auto Review Loop/auto-review-loopPaper + results → Iteratively improved paper
W3 — Paper Writing/paper-writingNarrative report → Structured LaTeX paper + PDF
W4 — Rebuttal/rebuttalPaper + reviews → Character-limited response
Full Pipeline/research-pipelineResearch direction → W1→W1.5→W2→W3 chained output

Cross-Model Adversarial Collaboration#

  • Executor: Claude Code / Codex CLI — writes code, runs experiments, drafts papers
  • Reviewer: GPT-5.4 / Gemini / GLM — critiques, scores, requests revisions
  • Core Constraint: Executor and reviewer must be from different model families; reviewers receive only file paths, never executor summaries

Quality Assurance#

  • Four-layer assurance stack: experiment-audit → result-to-claim → paper-claim-audit → citation-audit
  • Assurance Gate: --effort: beast + --assurance: submission enforces submission-stage audits
  • Rebuttal safety gates: no fabrication / no over-promising / full coverage

Paper Output Tools#

/paper-slides (Beamer PPT), /paper-poster (poster PDF/PPTX/SVG), /paper-illustration (figure generation)

Persistence & Collaboration#

  • Research Wiki: optional persistent project memory shared across skills
  • Overleaf bidirectional sync via Overleaf Git Bridge

Compatible Environments#

Claude Code, Cursor, Trae (ByteDance), Antigravity (Google), Windsurf, Codex CLI, OpenClaw, etc. GPU backends: local / remote / vast / modal.

Zero-Dependency Design#

The entire system consists of pure Markdown files—no frameworks, databases, Docker, or daemons. Skills communicate via chained plain-text artifacts: IDEA_REPORT.md → EXPERIMENT_PLAN.md → EXPERIMENT_LOG.md → NARRATIVE_REPORT.md → paper/main.tex → paper/main.pdf.

Validated Output#

Multiple papers assisted by ARIS have been produced, including an accepted AAAI 2026 Main Technical Track paper.

Unconfirmed Information#

  • Whether ARIS itself has an accompanying technical report or paper (not explicitly stated)
  • Author wanshuiyin's institutional or academic background (not annotated)
  • Detailed configuration steps for ModelScope free-tier usage (not specified)
  • Independent website and HuggingFace page (not found)

Related Projects

View All arrow_forward

STAY UPDATED

Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.

rocket_launch