FAR Paradigm: AI Automatically Filters Worthwhile Math Conjectures

rohanpaul_ai · x · 2026-08-31

As AI's mathematical capabilities improve, the bottleneck has shifted from solving problems to deciding which ones are worth the compute. This paper proposes FAR (Find, Attempt, Recommend), a new human-AI discovery paradigm. Instead of humans pre-selecting a single problem, the system searches, filters, and recommends conjectures based on a research direction. In a combinatorics pilot, the pipeline processed 5,245 papers, extracting and filtering down to 4,717 viable open conjectures and surfacing 598 potential resolutions, aiming to alleviate the scarcity of expert review resources.

Related event: FAR Framework Helps AI Rank Which Math Conjectures Deserve Attention(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →