3 papers
cs.AI2026
Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional Rewards
Kai-Yuan Guo, Jiang Wang, Renjie Zhao +5
Large Language Models (LLMs) have become a key foundation for enabling personalized smart home experiences. While existing studies have explored how smart home assistants understan…
cs.AI2026
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Tianyi Wang, Yixia Li, Long Li +6
Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in th…
cs.LG2026
DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay
Long Li, Zhijian Zhou, Tianyi Wang +7
While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they discard past rollouts. Existing experience…