# ASI-Evolve: AI Accelerates AI

arXiv: https://arxiv.org/abs/2603.29640 · HTML: https://mlsanity.com/paper/2603.29640/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)
- [GraphCast: Learning skillful medium-range global weather forecasting](https://mlsanity.com/paper/2212.12794/) (2022)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [Robin: A multi-agent system for automating scientific discovery](https://mlsanity.com/paper/2505.13400/) (2025)
- [ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning](https://mlsanity.com/paper/2506.16499/) (2025)
- [AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization](https://mlsanity.com/paper/2602.20133/) (2026)
- [Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas](https://mlsanity.com/paper/2410.14255/) (2024)
- [SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?](https://mlsanity.com/paper/2507.05241/) (2025)
- [FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks](https://mlsanity.com/paper/2601.21165/) (2026)
- [Interpretable bilinear attention network with domain adaptation improves drug-target prediction](https://mlsanity.com/paper/2208.02194/) (2022)
- [LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm](https://mlsanity.com/paper/2512.24077/) (2025)
- [AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents](https://mlsanity.com/paper/2510.08511/) (2025)
- [Neural Architecture Discovery via Autonomous Evolution](https://mlsanity.com/paper/2507.18074/) (2025)
- [Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI](https://mlsanity.com/paper/2506.19613/) (2025)
- [Towards an AI Fluid Scientist: LLM-Powered Scientific Discovery in Experimental Fluid Mechanics](https://mlsanity.com/paper/2512.04716/) (2025)

## Built on by (most cited first, 5 of 5)

- [Harnessing Agentic Evolution](https://mlsanity.com/paper/2605.13821/) (2026)
- [What is Missing from AI Post-Training AI: An Empirical Analysis](https://mlsanity.com/paper/2608.19072/) (2026)
- [EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents](https://mlsanity.com/paper/2606.11182/) (2026)
- [Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration](https://mlsanity.com/paper/2606.30246/) (2026)
- [ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible](https://mlsanity.com/paper/2609.39933/) (2026)

## Abstract (arXiv)

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.