自睡眠自研究系统

Auto-claude-code-research-in-sleep (ARIS ⚔️🌙)

<p align="center"> <a href="https://huggingface.co/papers/2605.03042"> <img src="docs/hf_daily_paper_1.svg" alt="Hugging Face Daily Paper · #1 Paper of the Day" width="360"> </a> </p>

· · · · · · -orange?style=flat) · · 💬 Join Community ·

💡 Use ARIS as a skill-based workflow in Claude Code / Codex CLI / Cursor / Trae / Antigravity / GitHub Copilot CLI / OpenClaw / DeepSeek Harness, or get the full experience with the standalone ARIS-Code CLI — enjoy any way you like!

🐋 On DeepSeek Harness it installs as one plugin: dsh plugin --profile web add dsh-aris (fetches from npm by itself — no separate install step, but pnpm must be on PATH) — all 82 skills unchanged, Codex still the independent reviewer. Setup and limits on the dsh-aris branch.

🌱 ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.

🤖 AI agents: Read AGENT_GUIDE.md instead — structured for LLM consumption, not human browsing.

🛡️ ARIS audits its own output → now Anti-Autoresearch audits everyone's. 61 signals — 46 integrity hack-patterns in 8 families, 13 AI-style impressions, 2 advisory — checked end-to-end into a deterministic, reviewer-ready report. Self-consistency + fabrication forensics, not an AI-text detector.

<p align="center"><em>The field has put up with unreliable autoresearch long enough —<br>Anti-Autoresearch is the read that finally catches it.</em></p>

🧱 ARIS's reviewer is good — and it also proposed hashes nobody reads → HERO is the contract that stops that. Hashing, Edge cases, Rubrics, Overbuild — the four shapes agents over-defend in, as a ~550-token block for CLAUDE.md / AGENTS.md. It bounds what the agent proposes, never what it looks for.

🎬 ARIS goes multimodal → ARIS-Movie-Director — hand it a rough story and get back a movie told in still frames, checked scene by scene (the reference run has 19 scenes). Long stories usually break when the model forgets earlier details or judges its own work — so ARIS keeps a research-wiki for memory and has other models check every frame.

<details> <summary>🗺️ <b>Method figure</b> — story brief → authored source of truth → per-panel audited spiral → assembly &amp; release, on one canvas</summary>

<p align="center"> <a href="https://github.com/wanshuiyin/ARIS-Movie-Director"> <img src="docs/aris-movie-director-method.png" alt="ARIS-Movie-Director method — the audited spiral: authored source of truth (asset library · outline · storyboard · comic.json) → per-panel image_gen + cross-model panel_gate (blind token-diff, single-vote veto) → research-wiki audit trace → assembly + release" width="100%"> </a> </p>

</details>

🧭 The same loop also makes clean method / flow diagrams — the figure above was made with it. Entry points in ARIS-Movie-Director: /movie-pipeline and /method-figure, the skill that made this figure.

<details> <summary>🎞️ <i>A few frames from the reference movie — the story's own integrity beat: a run that <b>reported <code>+6.2</code></b> but <b>really moved <code>+1.4</code></b>.</i> &nbsp;<b><a href="https://wanshuiyin.github.io/ARIS-Movie-Director/comic/">▶ watch all 19 scenes →</a></b></summary>

</details>

🎯 准备 2026 AI 秋招？ → 🌐 ARIS-in-AI-Offer · GitHub repo · 中文 README —— 23 篇双语 ML / LLM / 多模态 / 生成式 / Agent 面试 cheat sheet，每篇 = 公式推导 + 从零 PyTorch + 25 高频面试题（L1 / L2 / L3），全部由 ARIS 的 /render-html 自动生成。希望大家秋招轻松一点 🌱

<details> <summary><b>🖼️ Preview</b> — the three-pillar cheat-sheet strip (① Foundations · ② Interview Q&amp;A · ③ From-Scratch Code)</summary>

<p align="center"> <a href="https://github.com/wanshuiyin/ARIS-in-AI-Offer"> <img src="https://raw.githubusercontent.com/wanshuiyin/ARIS-in-AI-Offer/main/assets/preview_strip.jpg" alt="ARIS-in-AI-Offer preview — ① Foundations + ② Interview Q&A + ③ From-Scratch Code, three columns from a representative cheat sheet" width="100%"> </a> </p>

</details>

📝 Three long-form blogs, cross-model collaborative writing via /render-html — Continuous DLM — a representation-perspective survey (2026 H1) · Cosmos 3 — understanding + generation in one Transformer (MoT) · Diffusion × representation × manifold learning.

🛰 Keep an eye on your agent windows — Claude Fleet (by @tianyilt; local read-only dashboard for many parallel Claude Code / Codex windows, full-text transcript search — worth a ⭐), or the lighter built-in ARIS-Monitor (a tiny always-on-top macOS widget that lights up 🔴 when a session waits for your approval; click to jump there).

<details> <summary><b>🖼️ Preview</b> — Claude Fleet dashboard (full web) &amp; ARIS-Monitor widget (minimal, built-in)</summary>

Claude Fleet · 全功能网页看板	ARIS-Monitor · 极简悬浮小窗(自带)

</details>

<details> <summary><b>Run either in seconds</b> — ARIS-Monitor (5s) / Claude Fleet (30s)</summary>

ARIS-Monitor — built-in, no clone / no pip / no browser:

```bash cd aris-monitor && ./run.sh

2. 📢 What's New

⚠️ Any entry that touches skills: bash tools/smart_update.sh --apply pulls it.

• 2026-09-07 — 🧠 Default reviewer is now gpt-6-astra. Every reviewer call that pinned gpt-5.6-sol now pins gpt-6-astra; the two effort tiers (ultra for the seven deep audits, xhigh everywhere else) are unchanged, and so is the executor — whatever agent you run ARIS in. No access to the model yet? The capability fallback tries gpt-5.6-sol, then gpt-5.5, both at xhigh — nothing to configure.
• 2026-09-06 — 🧹 The installer stops dropping Copilot profiles into every project (#431, thanks @oblivion-1521). Since 2026-08 every run symlinked two Copilot reviewer profiles into your .github/agents/ whether or not anything used them — dead files for Claude Code and Codex users, broken links if you committed them. Now they are deployed only while auto-review-loop is installed; --no-agent-profiles switches them off for good (undo with --agent-profiles). Your next re-run removes the links the installer created earlier; files you wrote yourself are never touched.
• 2026-09-03 — 📣 Papers are launches, not progress reports (rules adopted from anti-defensive-writing-Skill by @Adkid-Zephyr — 🌟 it). The writing contract gains four rules: organize the narrative around the strongest genuine advantage; pick the contest the paper wins; unfavorable numbers stay in the tables, explained as a tradeoff where the evidence supports that and stated neutrally where it does not — never narrated as a defeat; every experiment carries an argumentative duty or leaves the main line; abstract and introduction open with problem → gap → idea → strongest result, and the conclusion never ends on new self-negation. /auto-paper-improvement-loop flags the same defects. Indexed under Awesome Community Skills.
• 2026-08-26 — 🧯 Two over-defense leftovers (#425). /research-review — the one reviewer prompt that never got the scope-limits block — now carries it, and its brief ends with "if the work holds up, say so clearly" instead of bare brutality; the adversarial stance itself is untouched. /research-pipeline no longer dies overnight on a missing VENUE: ideas, experiments, analysis and the narrative report are venue-independent and run to completion — only paper formatting defers, stamped clearly for a later resume. It had also been declaring VENUE = ICLR while forbidding silent defaults; the default is gone.
• 2026-08-26 — ✍️ Papers stop reading like confession letters (#423, #424; several rules adopted from humanize-paper). Claims are stated at the strength the evidence earns; generic caveats ("further research is needed") live in Limitations only; "don't mention X" means X is absent — never "we do not address X" in print; results are ordered by argument, not by the order experiments ran.
• 2026-08-26 — 💡 The idea pipeline stops killing ideas for having neighbors (#419–#422; community reports). ABANDON now has to name the published paper that already contains your result, and concurrent work is a race — your call, not a veto. Brainstorming runs two generator models (gpt-5.6-sol + gpt-5.5) and unions their ideas, aiming for creative direct attacks instead of corner-case stacks. Search digs as hard as ever.
• 2026-08-21 — 🔌 Optional HTTP reviewer fallback for when Codex MCP is unreachable (#413; by [@TheFlashForge]