Saved in:
Bibliographic Details
Main Authors: Huang, Hsiang-Wei, Lu, Junbin, Chen, Kuang-Ming, Hwang, Jenq-Neng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08829
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908762511507456
author Huang, Hsiang-Wei
Lu, Junbin
Chen, Kuang-Ming
Hwang, Jenq-Neng
author_facet Huang, Hsiang-Wei
Lu, Junbin
Chen, Kuang-Ming
Hwang, Jenq-Neng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08829
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Modeling LLM Agent Reviewer Dynamics in Elo-Ranked Review System
Huang, Hsiang-Wei
Lu, Junbin
Chen, Kuang-Ming
Hwang, Jenq-Neng
Computation and Language
Artificial Intelligence
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.
title Modeling LLM Agent Reviewer Dynamics in Elo-Ranked Review System
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.08829