Modeling LLM Agent Reviewer Dynamics in Elo-Ranked Review System
This work addresses reviewer dynamics in peer review for conference organizers, but it is incremental as it builds on existing Elo and LLM agent frameworks.
The study investigated how LLM agent reviewers behave in an Elo-ranked review system using real conference data, finding that incorporating Elo ratings improved Area Chair decision accuracy but led reviewers to adapt strategies without increasing effort.
In this work, we explore the Large Language Model (LLM) agent reviewer dynamics in an Elo-ranked review system using real-world conference paper submissions. Multiple LLM agent reviewers with different personas are engage in multi round review interactions moderated by an Area Chair. We compare a baseline setting with conditions that incorporate Elo ratings and reviewer memory. Our simulation results showcase several interesting findings, including how incorporating Elo improves Area Chair decision accuracy, as well as reviewers' adaptive review strategy that exploits our Elo system without improving review effort. Our code is available at https://github.com/hsiangwei0903/EloReview.