_version_ 1866917527678877696
author Liu, Jiaqi
Qiu, Shi
Li, Mairui
Li, Bingzhou
Ji, Haonian
Han, Siwei
Ye, Xinyu
Xia, Peng
Dong, Zihan
Chen, Meng
Zhang, Congyu
Zhang, Letian
Chen, Guiming
Tu, Haoqin
Yang, Xinyu
Feng, Lu
Zhao, Xujiang
Chen, Haifeng
Zhou, Jiawei
Wang, Xiao
Zhang, Weitong
Zhu, Hongtu
Li, Yun
Mei, Jieru
Fei, Hongliang
Zhang, Jiaheng
Li, Linjie
Zhang, Linjun
Zhou, Yuyin
Wang, Sheng
Xiong, Caiming
Zou, James
Zheng, Zeyu
Xie, Cihang
Ding, Mingyu
Yao, Huaxiu
author_facet Liu, Jiaqi
Qiu, Shi
Li, Mairui
Li, Bingzhou
Ji, Haonian
Han, Siwei
Ye, Xinyu
Xia, Peng
Dong, Zihan
Chen, Meng
Zhang, Congyu
Zhang, Letian
Chen, Guiming
Tu, Haoqin
Yang, Xinyu
Feng, Lu
Zhao, Xujiang
Chen, Haifeng
Zhou, Jiawei
Wang, Xiao
Zhang, Weitong
Zhu, Hongtu
Li, Yun
Mei, Jieru
Fei, Hongliang
Zhang, Jiaheng
Li, Linjie
Zhang, Linjun
Zhou, Yuyin
Wang, Sheng
Xiong, Caiming
Zou, James
Zheng, Zeyu
Xie, Cihang
Ding, Mingyu
Yao, Huaxiu
contents Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linear pipeline: they rely on single-agent reasoning, stop when execution fails, and do not carry experience across runs. We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a \textsc{Pivot}/\textsc{Refine} decision loop that transforms failures into information, verifiable result reporting that prevents fabricated numbers and hallucinated citations, human-in-the-loop collaboration with seven intervention modes spanning full autonomy to step-by-step oversight, and cross-run evolution that converts past mistakes into future safeguards. On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%. A human-in-the-loop ablation across seven intervention modes reveals that precise, targeted collaboration at high-leverage decision points consistently outperforms both full autonomy and exhaustive step-by-step oversight. We position AutoResearchClaw as a research amplifier that augments rather than replaces human scientific judgment. Code is available at https://github.com/aiming-lab/AutoResearchClaw.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20025
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Liu, Jiaqi
Qiu, Shi
Li, Mairui
Li, Bingzhou
Ji, Haonian
Han, Siwei
Ye, Xinyu
Xia, Peng
Dong, Zihan
Chen, Meng
Zhang, Congyu
Zhang, Letian
Chen, Guiming
Tu, Haoqin
Yang, Xinyu
Feng, Lu
Zhao, Xujiang
Chen, Haifeng
Zhou, Jiawei
Wang, Xiao
Zhang, Weitong
Zhu, Hongtu
Li, Yun
Mei, Jieru
Fei, Hongliang
Zhang, Jiaheng
Li, Linjie
Zhang, Linjun
Zhou, Yuyin
Wang, Sheng
Xiong, Caiming
Zou, James
Zheng, Zeyu
Xie, Cihang
Ding, Mingyu
Yao, Huaxiu
Artificial Intelligence
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linear pipeline: they rely on single-agent reasoning, stop when execution fails, and do not carry experience across runs. We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a \textsc{Pivot}/\textsc{Refine} decision loop that transforms failures into information, verifiable result reporting that prevents fabricated numbers and hallucinated citations, human-in-the-loop collaboration with seven intervention modes spanning full autonomy to step-by-step oversight, and cross-run evolution that converts past mistakes into future safeguards. On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%. A human-in-the-loop ablation across seven intervention modes reveals that precise, targeted collaboration at high-leverage decision points consistently outperforms both full autonomy and exhaustive step-by-step oversight. We position AutoResearchClaw as a research amplifier that augments rather than replaces human scientific judgment. Code is available at https://github.com/aiming-lab/AutoResearchClaw.
title AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
topic Artificial Intelligence
url https://arxiv.org/abs/2605.20025