Researcher — paper.dinq.me

作者位次 #2/8ICLR 2026Poster· Reinforcement Learning / Everything Else

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Wenhao Zhang · Yuexiang Xie · Yuchang Sun · Yanxi Chen · Guoyin Wang · Yaliang Li · Bolin Ding · Jingren Zhou

强化学习与后训练安全OpenReview

作者位次 #3/7ACL 2026Poster· Natural Language Processing

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

Yi Yu · Liuyi Yao · Yuexiang Xie · Qingquan Tan · Jiaqi Feng · Yaliang Li · Libing Wu

摘要

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components, relying on heuristics o...

强化学习与后训练检索与知识推理OpenReview 项目页

Yuexiang Xie

获取完整研究档案

联系方式

2026 顶会论文

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

常见合作者