aiming-lab/AutoResearchClaw：README 来源编辑指南

aiming-lab/AutoResearchClaw 的 README 将项目描述为"Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞"。本文只整理仓库能直接核验的内容，不把星标、Fork 或宣传语当成质量证明。README 在"README"下的说明是：📄 Our paper is on arXiv , come read it! AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration。这给出的首先是项目边界，而不是已经完成的生产验证。

从 README 的"🔥 News"和相关条目看，读者可以先判断它是否解决自己的具体问题：[04/01/2026] v0.4.0 , Human-in-the-Loop Co-Pilot System , AutoResearchClaw is no longer purely autonomous. New HITL system adds 6 intervention modes (full-auto, gate-only, checkpoint, step-by-step, co-pilot, custom), per-stage policies,。如果你的目标与这段说明不一致，就不应仅凭项目热度采用它。这里保留原项目名、命令和组件名，方便回到一手来源核对。 README 还列出了另一条可核对的信息：[05/19/2026] v0.5.0 , Multi-Domain Experiment Agents + ARC-Bench , Two headline updates. (1) Domain-specialist execution agents: the experiment stage (Stages 10,13) now routes beyond the default ML sandbox to specialist agents per field ,。这类原文条目可以帮助读者设计试运行步骤，但不能代替自己的环境测试。

README 把工作方式分散写在"🤔 What Is This?"等段落中。可确认的线索包括：You think it. AutoResearchClaw writes it. You guide the key decisions.。这篇整理没有把未写出的架构、性能或安全边界补成结论；真正的运行链仍应结合仓库目录、配置文件和版本标签检查。

第一次安装应从 README 给出的入口开始。当前可复核的命令是： # Fully autonomous , no human intervention pip install -e . && researchclaw setup && researchclaw init && researchclaw run --topic "Your research idea here" --auto-approve # Co-Pilot mode , collaborate with AI at key decision points researchclaw run --topic "Your research idea here" --mode co-pilot 如果仓库没有提供命令，本文不会替它编造安装步骤，而是建议先打开 README 的"⚡ One Command. One Paper."部分，确认系统依赖、默认端口和首次初始化动作。

日常使用的细节取决于项目实际文档。README 的"🤔 What Is This?"段落提到：Drop a research topic , get back a full academic paper with real literature from OpenAlex, Semantic Scholar & arXiv, hardware-aware sandbox experiments (GPU/MPS/CPU auto-detected), statistical analysis, multi-agent peer review, and。对于配置文件、环境变量、权限和数据目录，当前稿只记录来源明确的部分；未写明的默认值必须在测试环境中验证，并保留可回滚的配置副本。 同一部分还提到：[03/30/2026] Flexible Skill Loading , AutoResearchClaw now supports loading open-source and custom skills from any discipline to further enhance your research experience.。