Researchers propose a new approach to AI-assisted mathematical discovery. Instead of selecting problems in advance, humans provide a research direction and the system searches for suitable problems from a broad literature corpus. This pipeline, called FAR, automates problem search and filters out unsuitable candidates, freeing human experts to focus on reviewing promising artifacts. In a pilot study, FAR recovered 6,453 candidate conjectures or open problems from 5,245 combinatorics papers and identified many interesting discoveries. --- Why it matters: This work matters because it tackles the bottleneck of human effort in selecting suitable research problems and reviewing resulting artifacts. By automating this process, researchers can focus on higher-level tasks and make AI-assisted mathematical discovery more efficient. Source: https://arxiv.org/abs/2608.16977