Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
FreshmanDΒ 
posted an update 4 days ago
Post
2729
πŸ₯‡ 23 Kaggle Gold Medals. One Agent Framework.

Introducing LoongFlow: A Thinking & Learning Framework for Expert-Grade AI Agents.

Unlike traditional evolve agents(like OpenEvolve-Style), LoongFlow implements the PES (Plan-Execute-Summary) paradigm to learn from mistakes and avoid local optima.

πŸš€ Highlights:
* SOTA: Surpassed human mathematicians on 11 geometry/algebra problems.
* 23 Kaggle Gold Medals on MLE Bench.
* Efficiency: 60% more efficient than current baselines.

πŸ”— Code & Paper:
https://github.com/baidu-baige/LoongFlow
LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm (2512.24077)

#AutoML #Kaggle #Agents #OpenSource #LLM

Hey guys, If you're interested in LoongFlow, welcome to participate with us~

If you want to know more about LoongFlow, you can read these two articles: https://huggingface.co/blog/FreshmanD/loongflow-intro
https://huggingface.co/blog/FreshmanD/loongflow-vs-openevolve

In this post