Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates

ArXi:2511.08317v2 Announce Type: replace Existing paper review methods often rely on superficial manuscript features or directly on large language models (LLMs), which are prone to hallucinations, biased scoring, and limited reasoning capabilities. Moreover, these methods often fail to capture the complex argumentative reasoning and negotiation dynamics inherent in reviewer-author interactions.