Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Xinyu, Cai, Yuzhu, Liu, Zexi, Zheng, Bingyang, Wang, Cheng, Ye, Rui, Zhang, Yuzhi, Zhang, Linfeng, E, Weinan, Chen, Siheng, Wang, Yanfeng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914420825784320
author Zhu, Xinyu
Cai, Yuzhu
Liu, Zexi
Zheng, Bingyang
Wang, Cheng
Ye, Rui
Zhang, Yuzhi
Zhang, Linfeng
E, Weinan
Chen, Siheng
Wang, Yanfeng
author_facet Zhu, Xinyu
Cai, Yuzhu
Liu, Zexi
Zheng, Bingyang
Wang, Cheng
Ye, Rui
Zhang, Yuzhi
Zhang, Linfeng
E, Weinan
Chen, Siheng
Wang, Yanfeng
contents The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles spanning days or weeks. While Large Language Models (LLMs) have demonstrated prowess in short-horizon reasoning, they are easily overwhelmed by execution details in the high-dimensional, delayed-feedback environments of real-world research, failing to consolidate sparse feedback into coherent long-term guidance. Here, we present ML-Master 2.0, an autonomous agent that masters ultra-long-horizon machine learning engineering (MLE) which is a representative microcosm of scientific discovery. By reframing context management as a process of cognitive accumulation, our approach introduces Hierarchical Cognitive Caching (HCC), a multi-tiered architecture inspired by computer systems that enables the structural differentiation of experience over time. By dynamically distilling transient execution traces into stable knowledge and cross-task wisdom, HCC allows agents to decouple immediate execution from long-term experimental strategy, effectively overcoming the scaling limits of static context windows. In evaluations on OpenAI's MLE-Bench under 24-hour budgets, ML-Master 2.0 achieves a state-of-the-art medal rate of 56.44%. Our findings demonstrate that ultra-long-horizon autonomy provides a scalable blueprint for AI capable of autonomous exploration beyond human-precedent complexities.
format Preprint
id arxiv_https___arxiv_org_abs_2601_10402
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Zhu, Xinyu
Cai, Yuzhu
Liu, Zexi
Zheng, Bingyang
Wang, Cheng
Ye, Rui
Zhang, Yuzhi
Zhang, Linfeng
E, Weinan
Chen, Siheng
Wang, Yanfeng
Artificial Intelligence
The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles spanning days or weeks. While Large Language Models (LLMs) have demonstrated prowess in short-horizon reasoning, they are easily overwhelmed by execution details in the high-dimensional, delayed-feedback environments of real-world research, failing to consolidate sparse feedback into coherent long-term guidance. Here, we present ML-Master 2.0, an autonomous agent that masters ultra-long-horizon machine learning engineering (MLE) which is a representative microcosm of scientific discovery. By reframing context management as a process of cognitive accumulation, our approach introduces Hierarchical Cognitive Caching (HCC), a multi-tiered architecture inspired by computer systems that enables the structural differentiation of experience over time. By dynamically distilling transient execution traces into stable knowledge and cross-task wisdom, HCC allows agents to decouple immediate execution from long-term experimental strategy, effectively overcoming the scaling limits of static context windows. In evaluations on OpenAI's MLE-Bench under 24-hour budgets, ML-Master 2.0 achieves a state-of-the-art medal rate of 56.44%. Our findings demonstrate that ultra-long-horizon autonomy provides a scalable blueprint for AI capable of autonomous exploration beyond human-precedent complexities.
title Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
topic Artificial Intelligence
url https://arxiv.org/abs/2601.10402