2 citations · 4 across the 12 of their papers we have counts for
4 papers · 2 filters
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Panrong Tong, Quyu Kong, Pengxiang Li +12
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challengin…
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…
SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation
Long Li, Zhijian Zhou, Jiangxuan Long +5
Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignme…
Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
Tianyi Wang, Long Li, Hongcan Guo +5
Reinforcement Learning with Verifiable Rewards (RLVR) is increasingly viewed as a tree pruning mechanism. However, we identify a systemic pathology termed Recursive Space Contracti…