12,637 papers · updated 18 Sept 2026livingmeta.ai
← Browse all papers
Research theme

AI Peer Review

The AI Peer Review theme comprises 266 papers in this corpus published between 1981 and 2026. Work here is dominated by Empirical Study, Experimental, Design Science. 5 open research gaps have been surfaced in this area.

Methodology profile

  • Empirical Study45 (17%)
  • Experimental33 (12%)
  • Design Science29 (11%)
  • Position Paper29 (11%)
  • Literature Review26 (10%)
  • Case Study22 (8%)

Research domains

  • Peer Review262 (98%)
  • Academic Writing2 (1%)
  • Human-AI Collaboration1 (0%)
  • Research Integrity1 (0%)

Frequent sub-topics

evaluative misalignment in LLM-assisted policy analysis and qualitative coding · 1LLM-based reviewer matching using deep retrieval and deep thinking with information-gain rewards · 1peer review challenges and AI integration in Latin American publishing · 1LLM clinical decision support in oncology multidisciplinary tumor boards · 1LLM-radiologist collaboration in medical reporting · 1ChatGPT evaluation of student essays compared to human assessment · 1RAG-based evidence assessment for peer review · 1bias in LLM-assisted peer review · 1

Open research gaps

  • The authors identify several gaps: limited integration of disparate simulation models, lack of comparisons between different modeling approaches, rare empirical testing of model predictions, and the n
  • The paper identifies the need for further development and validation of AI systems for automating peer reviews, exploration of practical implementation challenges, and analysis of the implications for
  • Need for access to historical review data prior to 2021 from NeurIPS and ARR to establish longer-term trends
  • Expansion to non-English languages and scientific domains beyond computer science/machine learning
  • Development of additional review quality measurements beyond substantiveness, actionability, and grounding (e.g., relationships between reviews and papers, alignment between review texts and scores, f

Representative papers