7 papers
Learning Stateful Predictive Knowledge From Experience
Yan Song, Xidong Feng, Bo Liu +7
As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through the lens of predicti…
Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
Weiyu Ma, Yongcheng Zeng, Yan Song +4
Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO,…
-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
Siting Wang, Xiaofeng Wang, Zheng Zhu +7
Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning…
Swimming Under Constraints: A Safe Reinforcement Learning Framework for Quadrupedal Bio-Inspired Propulsion
Xinyu Cui, Fei Han, Hang Xu +9
Bio-inspired aquatic propulsion offers high thrust and maneuverability but is prone to destabilizing forces such as lift fluctuations, which are further amplified by six-degree-of-…
Sim2Sea: Sim-to-Real Policy Transfer for Maritime Vessel Navigation in Congested Waters
Xinyu Cui, Xuanfa Jin, Xue Yan +7
Autonomous navigation in congested maritime environments is a critical capability for a wide range of real-world applications. However, it remains an unresolved challenge due to co…
Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
Yongcheng Zeng, Xinyu Cui, Xuanfa Jin +11
Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement,…