Sakana AI’s LLM Peer Review System Catches 73% of Core-Claim Errors

תקציר מקורי באנגליתSakana AI has published Beyond Imitation , a TMLR research paper on LLM-assisted peer review built around error detection. Most AI reviewers are graded on how closely they copy human reviews. This work asks a harder question: can an AI reviewer find a planted mistake? The research team ships two pieces: a Contradiction Benchmark and a Multi-Layered Review (MLR) system. For developers building research agents, the lesson is practical. Both system design and model choice move error detection. TL;DR Size: 1,164 inserted contradictions across 257 papers from 5 venues. MLR reads up to 10 pages of main text. Runs on: Off-the-shelf API models (Claude Sonnet 4, Claude Haiku 3.5). No GPU, no fine-tuning. About $0.47 per review. Performance: Highest error detection of all 4 systems tested, with huma