Abstract
Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI research that closes this loop through a learn-design-experiment-analyze cycle. ASI-Evolve augments standard evolutionary agents with two key components: a cognition base that injects accumulated human priors into each round of exploration, and a dedicated analyzer that distills complex experimental outcomes into reusable insights for future iterations. To our knowledge, ASI-Evolve is the first unified framework to demonstrate AI-driven discovery across three central components of AI development: data, architectures, and learning algorithms. In neural architecture design, it discovered 105 SOTA linear attention architectures, with the best discovered model surpassing DeltaNet by +0.97 points, nearly 3x the gain of recent human-designed improvements. In pretraining data curation, the evolved pipeline improves average benchmark performance by +3.96 points, with gains exceeding 18 points on MMLU. In reinforcement learning algorithm design, discovered algorithms outperform GRPO by up to +12.5 points on AMC32, +11.67 points on AIME24, and +5.04 points on OlympiadBench. We further provide initial evidence that this AI-for-AI paradigm can transfer beyond the AI stack through experiments in mathematics and biomedicine. Together, these results suggest that ASI-Evolve represents a promising step toward enabling AI to accelerate AI across the foundational stages of development, offering early evidence for the feasibility of closed-loop AI research.
Abstract (translated)
人工智能能否加速其自身的发展？尽管近期的智能体系统在范围明确、反馈迅速的任务上展现出强劲性能，但它们能否应对那些驱动真正AI进步的高成本、长周期、弱监督的研究循环，仍不明确。我们提出了ASI-Evolve——一个面向AI研究的智能体框架，它通过“学习-设计-实验-分析”循环来闭合这一回路。ASI-Evolve通过两个关键组件增强了标准进化智能体：一是注入人类累积先验知识的认知库，用于每轮探索；二是将复杂实验结果提炼为可复用洞察的专用分析器，供后续迭代使用。据我们所知，ASI-Evolve是首个在AI发展的三大核心组件（数据、架构、学习算法）上均实现AI驱动发现的统一框架。在神经架构设计方面，它发现了105个最先进的线性注意力架构，其中最优模型超越DeltaNet达+0.97点，这一增益近乎近期人类设计改进的3倍。在预训练数据策划方面，进化管道将平均基准性能提升+3.96点，在MMLU（大学水平多学科理解测试）上的增益超过18点。在强化学习算法设计方面，发现的算法在AMC32、AIME24和OlympiadBench上分别超越GRPO达+12.5点、+11.67点和+5.04点。我们进一步通过数学与生物医学实验提供了初步证据，表明这种“AI for AI”范式能够超越AI技术栈进行迁移。综上，这些结果表明ASI-Evolve代表了一步有前景的探索，有望使AI在发展的基础阶段实现自我加速，并为闭环AI研究的可行性提供了早期证据。
URL
https://arxiv.org/abs/2603.29640
