Checkpoints Are Not Enough: Trust Calibration in CoSLR, a Human-AI System for Systematic Literature Reviews
CoSLR is presented, a Human-AI collaborative multi-agent system that supports the SLR workflow through a modular three-phase pipeline using large language models and Retrieval-Augmented Generation, and that places explicit, mandatory human checkpoints on the path between generated output and its acceptance.
Aidul Islam, M. Sami, Muhammad Waseem et al.
· 0 citations