AutoResearchClaw is a fully autonomous research pipeline that converts a single research idea into a conference-ready academic paper through 23 sequential stages across 8 phases, requiring zero human intervention. Built by the Aiming Lab, this Python framework implements multi-source literature discovery from OpenAlex, Semantic Scholar, and arXiv with 4-layer citation verification to prevent hallucinated references. The system includes hardware-aware sandboxed experiment execution with self-healing code repair, multi-agent peer review, and conference-grade LaTeX output targeting NeurIPS, ICML, and ICLR formats. Version 0.3.2 (March 22, 2026) added cross-platform support, ACP-compatible agent backend, anti-fabrication systems, and 100+ bug fixes. The pipeline covers research scoping, literature discovery, knowledge synthesis, hypothesis generation, experiment design, self-healing execution, analysis and decision, and paper writing. Users can run it standalone via CLI, integrate with OpenClaw, or wire it up through ACP-compatible agents such as Claude Code, Codex CLI, Copilot CLI, Gemini CLI, or Kimi CLI.