Wanyuan Wang

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

StarOR is a synergistic search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling and attains a 65.0\% average accuracy with a 4B backbone, matching the highest average and outperforming the evaluated same-backbone test-time baselines.

Large Language Model-Driven Symbolic Planning for Long-Horizon Robotic Manipulation Tasks

VLA-SP (Vision-Language-Action via Symbolic Planning), a two-stage Embodied Vision-Language-Action framework, enabling fully automated robotic execution from speech and vision inputs is proposed, demonstrating the strong interpretability, executability, and cross-platform applicability of the framework.

LOGO: A framework for language-based goal decomposition and skill recomposition in reinforcement learning