Author

Hongke Zhao

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

This work proposes three exact old-logit acquisition strategies: snapshot-based version tracking, a dedicated old-logit model, and synchronization via partial rollout interruption, and compares their system trade-offs to adopt a revised PPO-EWMA method.

Zhong Guan, Yong-Jian Guo, Haoran Sun et al. · arXiv.org · 4 citations · ⚡1

#artificial intelligence Preprint Feb 2026

RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training

RL-VLA is the first fully asynchronous RL training framework tailored specifically for the system-level challenges of VLA training, and achieves throughput improvements of up to 85.2\% over synchronous baselines while maintaining identical sample efficiency, with scalability validated from 8 to 256 GPUs.

Haoran Sun, Yong-Jian Guo, Zhong Guan et al. · 7 citations

Jul 2026

From Understanding to Action: Feedback-Grounded Policy Discovery for Generative Recommendation

A feedback-driven agent framework is proposed that first induces task-oriented intent and then discovers recommendation policies according to their incremental utility over an intent-only baseline, enabling LLM-free online inference.

Zhi Chen, Minmao Wang, Xing-Chen Liu et al. · arXiv.org · 0 citations