👋 About me

My research broadly focuses on LLM agent reasoning and Legal AI, with my current research centered on two closely connected directions:

  • Multi-Agent Communication & Collaboration Reasoning: Studying how collaboration structures, interaction protocols, feedback, and agent heterogeneity shape reasoning performance, reliability, and failure modes in multi-agent systems.

  • Legal AI and Long-Context Reasoning: Studying complex long-context documents for legal reasoning in LLM-based systems and Retrieval-Augmented Generation (RAG), with particular interest in evidence grounding, multi-perspective reasoning, and collaborative decision-making.