AI RESEARCH

LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation

arXiv CS.CL

ArXi:2510.05138v4 Announce Type: replace The rapid growth of scientific publications has made it increasingly difficult to keep literature reviews comprehensive and up-to-date. Though prior work has focused on automating retrieval and screening, the writing phase of systematic reviews remains largely under-explored, especially with regard to readability and factual accuracy. To address this, we present LiRA (Literature Review Agents), a multi-agent collaborative workflow which emulates the human literature review process.