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

xinyuzhu, Yuzhu Cai, Zexi Liu, Bingyang Zheng, Cheng Wang, RuiYe, Jiaao Chen, Hanrui Wang, Wei Chen Wang, Yuzhi Zhang, Linfeng Zhang, Weinan E, Di Jin, Siheng Chen

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering: 34 upvotes on Hugging Face Daily Papers, #7 of 38 papers on 2026-01-16. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.