Zhiqiang Gao

Improved MOPSO algorithm based on cloud membership

2015

An improved MOPSO algorithm based on Cloud Membership is designed to cope with the problem of quantitative ParetoSort,as well as convergence rate and variety in solution distribution. In this paper, logistic mapping is adopted to …

Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning

2025 · arXiv (Cornell University)

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning. Existing methods, such as tree-based search …