ScholarPeer introduces a multi-agent system with historian, scout, and Q&A agents that achieves higher win rates than prior models when evaluated on 1800 ICLR submissions for automated peer review tasks.
It accurately flags when papers ignore baselines published just months prior to the cutoff, whereas AI Scientist v2 often accepts the provided baselines as sufficient
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review
ScholarPeer introduces a multi-agent system with historian, scout, and Q&A agents that achieves higher win rates than prior models when evaluated on 1800 ICLR submissions for automated peer review tasks.