10 papers
UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
Haoyuan Deng, Yitong Gao, Yudong Lin +3
Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance.…
Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning
Hongye Cao, Nuo Yan, Haoyuan Deng +5
Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tasks. However, integrating exter…
VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
Wenkai Guo, Guanxing Lu, Haoyuan Deng +3
Vision-Language-Action models (VLAs) achieve strong performance in general robotic manipulation tasks by scaling imitation learning. However, existing VLAs are limited to predictin…
UniManip: General-Purpose Zero-Shot Robotic Manipulation with Agentic Operational Graph
Haichao Liu, Yuanjiang Xue, Yuheng Zhou +4
Achieving general-purpose robotic manipulation requires robots to seamlessly bridge high-level semantic intent with low-level physical interaction in unstructured environments. How…
E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning
Haoyuan Deng, Yuanjiang Xue, Haoyang Du +3
Human-in-the-loop guidance has emerged as an effective approach for enabling faster convergence in online reinforcement learning (RL) of complex real-world manipulation tasks. Howe…
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
Chia-Yu Hung, Navonil Majumder, Haoyuan Deng +7
Vision--language--action (VLA) models have recently shown promising performance on a variety of embodied tasks, yet they still fall short in reliability and generalization, especia…