AutoResearchClaw Model Card
这是可索引项目报告证据页：它保留 AutoResearchClaw Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
AutoResearchClaw Model Card
| Field | Value |
|---|---|
| Repository | aiming-lab/AutoResearchClaw |
| Category | Self-Evolving Research Agent Pipeline |
| Stars / forks snapshot | 12600 / 1500 |
| Language | Python |
| License | MIT |
| Raw capture | raw-github/aiming-lab_autoresearchclaw.md |
| Updated by | hourly public metadata update, 2026-05-25 |
1. Role in Self Evolve
AutoResearchClaw 是从 research idea 到 paper 的自主/协作式科研 agent 管线，结合多 agent debate、实验沙箱、claim verification、HITL co-pilot、MetaClaw cross-run learning 和 ARC-Bench。
2. Working Principle
research idea -> multi-agent debate -> sandbox experiment -> claim verification -> lessons/evolution -> paper deliverables
3. Evidence Path
web GitHub page observed 239 commits, MIT license, Python primary language, v0.5.0 latest May 20 2026, 12.6k stars and 1.5k forks; README describes 23-stage autonomous/co-pilot research pipeline, PIVOT/REFINE loop, self-learning lessons, ARC-Bench, and A-Evolve skill integration. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Self-Evolving Research Agent Pipeline in the raw -> classification -> project card -> site/report pipeline. The reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.
5. Limits
当前未克隆源码，未运行 benchmark、SDK examples、skill install flows、memory experiments、agent evolution loops 或 production deployments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。