activity
20242026
collaborators

10 papers

cs.LG2026

From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation

Yihan Wang, Zhong Guan, Haoran Sun +3

Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot i…

cs.LG2026

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

Zhong Guan, Yongjian Guo, Haoran Sun +5

Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a c…

cs.AI2026

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

Haoran Sun, Yongjian Guo, Zhong Guan +13

Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to adapt and improve through environm…

q-bio.OT2025

Reinventing Clinical Dialogue: Agentic Paradigms for LLM Enabled Healthcare Communication

Xiaoquan Zhi, Hongke Zhao, Likang Wu +2

Clinical dialogue represents a complex duality requiring both the empathetic fluency of natural conversation and the rigorous precision of evidence-based medicine. While Large Lang…

cs.AI2025

Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval

Chuang Zhao, Hui Tang, Hongke Zhao +2

Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs)…

cs.LG2025

Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration

Zhong Guan, Likang Wu, Hongke Zhao +2

Many existing studies have achieved significant improvements in the reasoning capabilities of large language models (LLMs) through reinforcement learning with verifiable rewards (R…