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

TL;DR

AutoResearchClaw is a multi-agent autonomous research system that enhances scientific discovery through iterative hypothesis testing, human collaboration, and experience accumulation, outperforming previous AI systems on a benchmark.

Contribution

The paper introduces AutoResearchClaw, a novel multi-agent pipeline with mechanisms for debate, self-healing execution, verifiable results, human-in-the-loop collaboration, and cross-run learning.

Findings

AutoResearchClaw outperforms AI Scientist v2 by 54.7% on ARC-Bench.

Targeted human intervention at key decision points improves performance.

Cross-run learning converts past mistakes into future safeguards.

Abstract

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.