Papers
arxiv:2605.20025

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Published on May 19
· Submitted by
taesiri
on May 20
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

AutoResearchClaw is a multi-agent autonomous research system that improves scientific discovery through structured debate, self-healing execution, verifiable reporting, human collaboration, and evolutionary learning, outperforming previous systems on a benchmark while maintaining human oversight.

AI-generated summary

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 Pivot/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.

Community

Paper submitter

AutoResearchClaw is a multi-agent, human-in-the-loop research framework that leverages self-reinforcing mechanisms, structured debate, and adaptive execution to autonomously improve scientific discovery and outperform existing autonomous research systems.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.20025
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.20025 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.20025 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.20025 in a Space README.md to link it from this page.

Collections including this paper 1