Peng Wei

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning

MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework

DARE‑Agent: Domain‑Aware, Resource‑Efficient, Evidence‑grounded Agentic RAG

HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment