Shuaiqiang Wang

CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation

Long-Attention Weaving: Synthesizing Long-Context Data with High-Quality Short Data

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning