ResearchClaw

AutoResearchClaw is a fully autonomous 23-stage research pipeline that transforms a single research idea into a conference-ready academic paper with real literature from OpenAlex, Semantic Scholar, and arXiv.

Quick Start

Basic Usage

User says: "Research [topic]"

Agent workflow:

1. 1. Check if AutoResearchClaw is installed (which researchclaw)
2. If not installed: clone, setup venv, install with INLINECODE1
3. Copy config.researchclaw.example.yaml → INLINECODE3
4. Ask user for LLM provider choice (OpenAI-compatible or ACP agent)
5. Configure with API keys or ACP agent selection
6. Run: INLINECODE4
7. Monitor progress, return results from INLINECODE5

Configuration

Ask user for LLM backend preference:

Option 1: OpenAI-compatible API
CODEBLOCK0

Option 2: ACP Agent (Claude Code, Codex, Gemini)
CODEBLOCK1

Installation

Check Installation

Install AutoResearchClaw

Verify Installation

Running Research

Basic Command

With Specific Config

Output Location

Deliverables

After completion, the agent should:

1. 1. Check deliverables/ directory contents
2. Present key outputs:

1. 3. Copy/present relevant sections to user

Pipeline Stages (23 Total)

Phase A: Research Scoping

• - Stage 1: TOPICINIT
• Stage 2: PROBLEMDECOMPOSE

Phase B: Literature Discovery

• - Stage 3: SEARCHSTRATEGY
• Stage 4: LITERATURECOLLECT
• Stage 5: LITERATURESCREEN [gate]
• Stage 6: KNOWLEDGEEXTRACT

Phase C: Knowledge Synthesis

• - Stage 7: SYNTHESIS
• Stage 8: HYPOTHESIS_GEN

Phase D: Experiment Design

• - Stage 9: EXPERIMENTDESIGN [gate]
• Stage 10: CODEGENERATION
• Stage 11: RESOURCE_PLANNING

Phase E: Experiment Execution

• - Stage 12: EXPERIMENTRUN
• Stage 13: ITERATIVEREFINE
• Stage 14: RESULTANALYSIS
• Stage 15: RESEARCHDECISION

Phase F: Analysis & Decision

• - Stage 16: PAPEROUTLINE
• Stage 17: PAPERDRAFT
• Stage 18: PEERREVIEW
• Stage 19: PAPERREVISION

Phase G: Paper Writing

• - Stage 20: QUALITYGATE [gate]
• Stage 21: KNOWLEDGEARCHIVE
• Stage 22: EXPORTPUBLISH
• Stage 23: CITATIONVERIFY

Hardware Awareness

AutoResearchClaw auto-detects:

• - NVIDIA CUDA (GPU)
• Apple MPS (M1/M2/M3)
• CPU-only fallback

Adapts code generation, imports, and experiment scale accordingly.

Quality Features

• - Real Citations: OpenAlex, Semantic Scholar, arXiv - no hallucinated references
• 4-Layer Verification: arXiv ID → CrossRef DOI → Semantic Scholar → LLM relevance
• Multi-Agent Debate: Hypothesis generation, result analysis, peer review
• Self-Healing: NaN/Inf detection, automatic code repair
• Conference Templates: NeurIPS, ICLR, ICML support

OpenClaw Bridge Integration (Optional)

Enable in config.arc.yaml:
CODEBLOCK7

MetaClaw Integration (Optional)

For cross-run learning:
CODEBLOCK8

Troubleshooting

Installation Issues

LLM API Errors

• - Verify OPENAI_API_KEY is set
• Check API endpoint is accessible
• Fallback models configured correctly

Sandbox Issues

• - Ensure Python path is correct: INLINECODE17
• Check allowed imports in config
• Adjust memory limits if needed

Literature Collection Failures

• - Check internet connectivity
• Semantic Scholar API key optional (higher rate limits)
• OpenAlex should work without API key

Advanced Usage

Specify Research Domains

Target Specific Conference

Custom Prompts

Resources

• - GitHub: https://github.com/aiming-lab/AutoResearchClaw
• Integration Guide: See AutoResearchClaw docs/integration-guide.md
• Testing Guide: See AutoResearchClaw docs/TESTER_GUIDE.md
• Discord: https://discord.gg/u4ksqW5P

Comparison with Superpowers

• - ResearchClaw: Academic research, literature review, paper writing, experimental validation
• Superpowers: Software development, TDD, code review, production code

Use ResearchClaw for research/paper generation. Use Superpowers for production software implementation. They complement each other when researching then implementing findings.