y0news
← Feed
Back to feed
🧠 AI🟢 BullishImportance 7/10

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

arXiv – CS AI|Xinyu Zhu, Yuzhu Cai, Zexi Liu, Bingyang Zheng, Cheng Wang, Rui Ye, Yuzhi Zhang, Linfeng Zhang, Weinan E, Siheng Chen, Yanfeng Wang|
🤖AI Summary

Researchers have developed ML-Master 2.0, an autonomous AI agent that achieves breakthrough performance in ultra-long-horizon machine learning tasks by using Hierarchical Cognitive Caching architecture. The system achieved a 56.44% medal rate on OpenAI's MLE-Bench, demonstrating the ability to maintain strategic coherence over experimental cycles spanning days or weeks.

Key Takeaways
  • ML-Master 2.0 introduces Hierarchical Cognitive Caching (HCC) to overcome the scaling limits of static context windows in long-term AI tasks.
  • The system achieved state-of-the-art 56.44% medal rate on OpenAI's MLE-Bench under 24-hour evaluation budgets.
  • The approach enables AI agents to decouple immediate execution from long-term experimental strategy through cognitive accumulation.
  • Ultra-long-horizon autonomy represents a key bottleneck in advancing artificial intelligence toward autonomous scientific discovery.
  • The research demonstrates a scalable blueprint for AI systems capable of autonomous exploration beyond human-precedent complexities.
Mentioned in AI
Companies
OpenAI
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles