Wright E, Li Y, Hall A, Zhao B. Committee-of-Judges: Multi-Agent Consensus for Reliable LLM Evaluation under Difficult Reasoning Tasks. J.I.T.I.E [Internet]. 2025 Sep. 30 [cited 2026 Oct. 8];1(2):13-22. Available from: https://journal.jci.co.id/jitie/article/view/819