Yuling Shi

Robust Preference Alignment via Directional Neighborhood Consensus

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models

DeepRepoQA: Code Repository Question Answering with Deep Agent Exploration

Turn-Level Trajectory Optimization for Robust Multi-Turn LLM Reasoning

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging