Computer Science / Artificial Intelligence

LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm

Reading time: 1 minute
...

📝 Original Info

  • Title: LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm
  • ArXiv ID: 2512.24077
  • Date: 2025-12-30
  • Authors: Chunhui Wan, Xunan Dai, Zhuo Wang, Minglei Li, Yanpeng Wang, Yinan Mao, Yu Lan, Zhiwen Xiao

📝 Abstract

The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and inefficient exploration in high-dimensional code spaces. To address these challenges, we introduce LoongFlow, a self-evolving agent framework that achieves state-of-the-art solution quality with significantly reduced computational costs. Unlike "blind" mutation operators, LoongFlow integrates LLMs into a cognitive "Plan-Execute-Summarize" (PES) paradigm, effectively mapping the evolutionary search to a reasoning-heavy process. To sustain long-term architectural coherence, we incorporate a hybrid evolutionary memory system. By synergizing Multi-Island models with MAP-Elites and adaptive Boltzmann selection, this system theoretically balances the exploration-exploitation trade-off, maintaining diverse behavioral niches to prevent optimization stagnation. We instantiate LoongFlow with a General Agent for algorithmic discovery and an ML Agent for pipeline optimization. Extensive evaluations on the AlphaEvolve benchmark and Kaggle competitions demonstr...

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)

Start searching

Enter keywords to search articles

↑↓
↵
ESC
⌘K Shortcut